Search

With the increasing demand for surveillance applications, pedestrian detection has been a topic of interest for many researchers in recent time. The quality of a pedestrian detector is decided in terms of detection accuracy and rate of detection. This paper presents new pedestrian detectors based on two types of classifiers, linear support vector machine and cascade of boosted classifier. These classifiers are trained by using a feature set comprising of the histogram of oriented gradients and dense local difference binary features. Both the image pyramid and non-linear scale space are used to detect pedestrians of various sizes. In order to combine the benefits of the two classifiers, a new two-stage detection scheme is also presented. The detection accuracies of the proposed detectors are studied in terms of miss-rate versus false positive per image and miss-rate versus false positive per window. The performances of the detectors are also compared with the performances of existing detectors of similar type.

Most of the excellent methods for visual object tracking are based on RGB videos. With the popularity of depth cameras, the research on RGB-D(RGB+depth) tracking has gradually gained extensive attention. The depth map provides more available information for dealing with intractable tracking problems. How to make full use of depth maps to construct a better tracker is the foremost problem to be settled. The fully-convolutional siamese network shows excellent performance in 2D tracking, but still cannot achieve satisfying tracking performance in complex scenarios. Therefore, we have proposed the RGB-D tracker integrated with the single-scale siamese network as well as the adaptive bounding boxes, which achieves stable tracking performance under the challenges such as occlusion, scale variation and background clutter. Our proposed adaptive strategy enables the bounding box to adjust automatically when the target appearance changes during the tracking, instead of multi-scale input in the siamese network. We design an effective algorithm to quickly obtain the target depth and construct the 3D local visual field to eliminate the interference from background and similar objects. In addition, the total occlusion handling approach combined with RGB and depth information has achieved more reliable occlusion detection and target recovery. Our presented object tracker, including the strategies of 3D local visual field, adaptive bounding boxes and occlusion handling, has been evaluated on two widely utilized RGB-D tracking benchmarks and achieves suprior performance especially for the situations of occlusion and pedestrian detection.

Intelligent transportation systems (ITS) enable transportation participants to communicate with each other by sending and receiving messages, so that they can be aware of their surroundings and facilitate efficient transportation through better decision making. As an important part of ITS, autonomous vehicles can bring massive benefits by reducing traffic accidents. Correspondingly, much effort has been paid to the task of pedestrian detection, which is a fundamental task for supporting autonomous vehicles. With the progress of computational power in recent years, adopting deep learning–based methods has become a trend for improving the performance of pedestrian detection. In this article, we present design guidelines on deep learning–based pedestrian detection methods for supporting autonomous vehicles. First, we will introduce classic backbone models and frameworks, and we will analyze the inherent attributes of pedestrian detection. Then, we will illustrate and analyze representative pedestrian detectors from occlusion handling, multi-scale feature extraction, multi-perspective data utilization, and hard negatives handling these four aspects. Last, we will discuss the developments and trends in this area, followed by some open challenges.

To accomplish reliable pedestrian detection using unmanned aerial vehicles (UAVs) under night-time conditions, an image enhancement method is developed in this article to improve the low-illumination image quality. First, the image brightness is mapped to a desirable level by a hyperbolic tangent curve. Second, the block-matching and 3-D filtering methods are developed for an unsharp filter in YCbCr color space for image denoising and sharpening. Finally, pedestrian detection is performed using a convolutional neural network model to complete the surveillance task. Experimental results show that the Minkowski distance measurement index of enhanced images is increased to 0.975, and the detection accuracies, in F-measure and confidence coefficient, reach 0.907 and 0.840, respectively, which are the highest as compared with other image enhancement methods. This developed method has potential values for night-time UAV visual monitoring in smart city applications.

Pedestrian detection has always been a research hotspot in the Advanced Driving Assistance System (ADAS) with great progress in recent years. However, for the ADAS, we not only need to detect the behavior of pedestrians in front of the vehicle but also predict future action and the motion trajectory. Therefore, in this paper, we propose a human key point combined optical flow network (KPOF-Net) in the vehicle ADAS for the occlusion situation in the actual scene. When the vehicle encounters a blocked pedestrian at a traffic intersection, we used self-flow to estimate the global optical flow in the image sequence and then proposed a White Edge Cutting (WEC) algorithm to remove obstructions and simply modified the generative adversarial network to initialize pedestrians behind the obstructions. Next, we extracted pedestrian optical flow information and human joint point information in parallel, among which we trained four human key point models suitable for traffic intersections. At last, KPOF-GPDM fusion was proposed to predict the future status and walking trajectories of pedestrians, which combined optical flow information with human key point information. In the experiment, we did not merely compare our method with other four representative approaches in the same scene sequences. We also verified the accuracy of the pedestrian motion state and motion trajectory prediction of the system after fusion of human joint points and optical flow information. Taking into account the real-time performance of the system, in the low-speed and barrier-free environment, the comparative analysis only uses optical flow information, human joint point information, and KPOF-Net three prediction models. The results show that (1) in the same traffic environment, our proposed KPOF-Net can predict the change of pedestrian motion state about 5 frames (about 0.26 s) ahead of other excellent systems; (2) at the same time, our system predicts the trajectory of the pedestrian more accurately than the other four systems, which can achieve more stable minimum error ±0.04 m; (3) in a low-speed, barrier-free experimental environment, our proposed trajectory prediction model that integrates human joint points and optical flow information has higher prediction accuracy and smaller fluctuations than a single-information prediction model, and it can be well applied to automobiles’ ADAS.

In recent years, the neural network (NN) has shown its great potential in image recognition tasks of autonomous driving systems, such as traffic sign recognition, pedestrian detection, etc. However, theoretically well-trained NNs usually fail their performance when facing real-world scenarios. For example, adverse real-world conditions, e.g., bad weather and lighting conditions, can introduce different physical variations and cause considerable accuracy degradation. As for now, the generalization capability of NNs is still one of the most critical challenges for the autonomous driving system. To facilitate the robust image recognition tasks, in this work, we build the RobuTS dataset: a comprehensive Robust Traffic Sign Recognition dataset, which includes images with different environmental variations, e.g., rain, fog, darkening, and blurring. Then to enhance the NN’s generalization capability, we propose two generalization-enhanced training schemes: 1) REIN for robust training without data in adverse scenarios and 2) Self-Teaching (ST) for robust training with unlabeled adverse data. The great advantages of such two training schemes are they are data-free ( REIN ) and label-free ( ST ), thus effectively reducing the huge human efforts/cost of on-road driving data collection, as well as the expensive manual data annotation. We conduct extensive experiments to validate our methods’ performance on both classification and detection tasks. For classification tasks, our proposed training algorithms could consistently improve model performance by +15%–25% ( REIN ) and +16%–30% ( ST ) in all adverse scenarios of our RobuTS datasets. For detection tasks, our ST could also improve the detector’s performance by +10.1 mean average precision (mAP) on Foggy-Cityscapes, outperforming previous state-of-the-art works by +2.2 mAP.

Autonomous driving systems in internet of vehicles (IoV) applications usually adopt a cloud computing mode. In these systems, information got at the edge of the cloud computing center for data analysis and situation response. However, the conventional IoV face enormous challenges to meet the requirements in terms of storage, communication, and computing problems because of the considerable amount of information on the traffic environment. The environment perception during the nighttime is poorer than that during the daytime that this problem also requires addressing. To solve these problems, we propose a nighttime object detection scheme based on a lightweight deep learning model in the edge computing mode. First, the pedestrian detection and the vehicle detection algorithm that using the thermal images based on the YOLO architecture. We can implement the model on edge devices that can achieve real-time detection through the designed lightweight strategy. Next, a spatial prior information and temporal prior information into the detection algorithm and divide the frames into key and non-key frames to increase the performance and speed of the system simultaneously. Finally, we implemented the detection network for performance and feasibility verification on the Jetson TX2 edge device. The experimental results show that the proposed system can achieve real-time and high-accuracy object detection on edge devices.

For the surveillance video images captured by monocular camera, this paper proposes a method combining foreground detection and deep learning to detect moving pedestrians, making full use of the invariable background of video image. Firstly, the motion region is extracted by the method of interframe difference and background difference. Then, the normalized motion region extracts the feature vectors based on the improved YOLOv3 tiny network. Finally, the trained linear support vector machine is used for pedestrian detection, and the performance of the fusion detection algorithm on caviar dataset is given, which proves the effectiveness of the proposed fusion detection algorithm. Experimental results show that the proposed method not only improves the practical application of pedestrian rerecognition but also reduces the detection range, computational complexity, and false detection rate compared with sliding window method.

Purpose Autonomous driving depends on the collection, processing and analysis of environmental information and vehicle information. Environmental perception and processing are important prerequisite for the safety of self-driving of vehicles; it involves road boundary detection, vehicle detection, pedestrian detection using sensors such as laser rangefinder, video camera, vehicle borne radar, etc. Design/methodology/approach Subjected to various environmental factors, the data clock information is often out of sync because of different data acquisition frequency, which leads to the difficulty in data fusion. In this study, according to practical requirements, a multi-sensor environmental perception collaborative method was first proposed; then, based on the principle of target priority, large-scale priority, moving target priority and difference priority, a multi-sensor data fusion optimization algorithm based on convolutional neural network was proposed. Findings The average unload scheduling delay of the algorithm for test data before and after optimization under different network transmission rates. It can be seen that with the improvement of network transmission rate and processing capacity, the unload scheduling delay decreased after optimization and the performance of the test results is the closest to the optimal solution indicating the excellent performance of the optimization algorithm and its adaptivity to different environments. Originality/value In this paper, the results showed that the proposed method significantly improved the redundancy and fault tolerance of the system thus ensuring fast and correct decision-making during driving.

Visible and infrared person re-identification (VI-ReID) describes the task of matching the images of a person, captured by visible-light and infrared cameras; this is a particular challenge in night time surveillance applications. Existing cross-modality recognition studies have been conducted mainly with a focus on learning the global and shareable feature representation of pedestrians to handle cross-modality discrepancies. However, the global features of pedestrian images cannot solve the unaligned image pairs efficiently, particularly when encountering the human appearance or posture misalignment caused by inaccurate pedestrian detection boxes. To mitigate the impact of these problems, we propose an end-to-end dual alignment and partitioning network to simultaneously learn global and local modal invariant features of pedestrians. First, we use two adaptive spatial transform modules to align the visible and infrared input images. Subsequently, the aligned image is divided horizontally, and the features of each local block are extracted. Then, we fuse these local features with global features. To alleviate the differences between heterogeneous modals and learn the common feature representation of heterogeneous modals, we map the features of heterogeneous modes into the same feature embedding space. Finally, we use the combination of identity loss and weighted regularized TriHard loss to improve the recognition accuracy. Extensive experimental results on two cross-modality datasets, RegDB and SYSU-MM01, demonstrate the superiority of the proposed method over other existing state-of-the-art methods.

Implementing pedestrian detection real-time embedded systems remains a major challenge. Detecting pedestrians in an advanced driver assistance system requires a lot of time and resources. The method based on Multi-Scale Region Covariance Descriptor (MSRCD) and Support Vector Machine (SVM) is one of the most effective approaches to perform pedestrian detection. However, such implementation is difficult to be executed in real time on embedded systems. This paper presents three improvements to adapt the solution based on the MSRCD descriptor and SVM classifier for embedded pedestrian detection. First, a new feature combination capable to provide the most accurate description at a minimum processing time for MSRCD is proposed. Second, to speed up the SVM classification, a new approach that adopts the mean SVM technique and Euclidian distance is proposed. Third, parallel implementation is exploited to accelerate processing time on multi-core architectures. The software implementation is performed using the INRIA data set. 18.94% processing time speed-up, 48.21% less memory usage, and 2.38% improved detection accuracy are achieved using the proposed descriptor. Moreover, 58.22% processing time speed-up is obtained for the proposed classifier while keeping the same testing accuracy. The parallel implementation is performed using dual ARM Cortex-A9 processors of a selected Xilinx zynq platform. The obtained results confirmed the effectiveness of the proposed parallelization at accelerating the computing time about 3 times the original sequential processing.

In real-world scenarios (i.e., in the wild), pedestrians are often far from the camera (i.e., small scale), and they often gather together and occlude with each other (i.e., heavily occluded). However, detecting these small-scale and heavily occluded pedestrians remains a challenging problem for the existing pedestrian detection methods. We argue that these problems arise because of two factors: 1) insufficient resolution of feature maps for handling small-scale pedestrians and 2) lack of an effective strategy for extracting body part information that can directly deal with occlusion. To solve the above-mentioned problems, in this article, we propose a key-point-guided super-resolution network (coined KGSNet) for detecting these small-scale and heavily occluded pedestrians in the wild. Specifically, to address factor 1), a super-resolution network is first trained to generate a clear super-resolution pedestrian image from a small-scale one. In the super-resolution network, we exploit key points of the human body to guide the super-resolution network to recover fine details of the human body region for easier pedestrian detection. To address factor 2), a part estimation module is proposed to encode the semantic information of different human body parts where four semantic body parts (i.e., head and upper/middle/bottom body) are extracted based on the key points. Finally, based on the generated clear super-resolved pedestrian patches padded with the extracted semantic body part images at the image level, a classification network is trained to further distinguish pedestrians/backgrounds from the inputted proposal regions. Both proposed networks (i.e., super-resolution network and classification network) are optimized in an alternating manner and trained in an end-to-end fashion. Extensive experiments on the challenging CityPersons data set demonstrate the effectiveness of the proposed method, which achieves superior performance over previous state-of-the-art methods, especially for those small-scale and heavily occluded instances. Beyond this, we also achieve state-of-the-art performance (i.e., 3.89% MR−2 on the reasonable subset) on the Caltech data set.

Multiple pedestrian tracking (MPT) has gained significant attention due to its huge potential in a commercial application. It aims to predict multiple pedestrian trajectories and maintain their identities, given a video sequence. In the past decade, due to the advancement in pedestrian detection algorithms, Tracking-by-Detection (TBD) based algorithms have achieved tremendous successes. TBD has become the most popular MPT framework, and it has been actively studied in the past decade. In this paper, we give a comprehensive survey of recent advances in TBD-based MPT algorithms. We systematically analyze the existing TBD-based algorithms and organize the survey into four major parts. At first, this survey draws a timeline to introduce the milestones of TBD-based works which briefly reviews the development of the existing TBD-based methods. Second, the main procedures of the TBD framework are summarized, and each stage in the procedure is described in detail. Afterward, this survey analyzes the performance of existing TBD-based algorithms on MOT challenge datasets and discusses the factors that affect tracking performance. Finally, open issues and future directions in the TBD framework are discussed.

Pedestrian detection based on visual sensors has made significant progress, in which region proposal is the key step. There are two mainstream methods to generate region proposals: anchor-based and anchor-free. However, anchor-based methods need more hyperparameters related to anchors for training compared with anchor-free methods. In this paper, we propose a novel multiscale anchor-free (MSAF) region proposal network to obtain proposals, especially for small-scale pedestrians. It usually has several branches to predict proposals and assigns ground truth according to the height of pedestrian. Each branch consists of two components: one is feature extraction, and the other is detection head. Adapted channel feature fusion (ACFF) is proposed to select features at different levels of the backbone to effectively extract features. The detection head is used to predict the pedestrian center location, center offsets, and height to get bounding boxes. With our classifier, the detection performance can be further improved, especially for small-scale pedestrians. The experiments on the Caltech and CityPersons demonstrate that the MSAF can significantly boost the pedestrian detection performance and the log-average miss rate (MR) on the reasonable setting is 3.97% and 9.5%, respectively. If proposals are reclassified with our classifier, MR is 3.38% and 8.4%. The detection performance can be further improved, especially for small-scale pedestrians.

Pedestrian detection and re-identification have progressed significantly in the last few years. However, occluded people are notoriously hard to detect and recognize, as their appearance varies substantially depending on a wide range of occlusion patterns. In this paper, we aim to propose a simple and compact method based on CNNs for occlusion handling. We start with interpreting CNN channel features of a pedestrian detector, and we find that different channels activate responses for different body parts respectively. These findings motivate us to employ an attention mechanism across channels to represent various occlusion patterns in one single model, as each occlusion pattern can be formulated as some specific combination of body parts. Therefore, an attention network with self or external guidances is proposed as an add-on to the baseline CNN method. Also, we propose an attention guided self-paced learning method to balance the optimization across different occlusion levels. Our proposed method shows significant improvements over the baseline methods for both pedestrian detection and re-identification tasks. For pedestrian detection, we achieve a considerable improvement of 8pp to the baseline FasterRCNN detector on the heavy occlusion subset of CityPersons and on Caltech we outperform the state-of-the-art method by 5pp. For pedestrian re-identification, our method surpasses the baseline and achieves state-of-the-art performance on multiple re-identification benchmarks.

The methods to tackle person search problem can be divided into two categories. One is to train an end-to-end person search model to search target person from scene images. The other is to train a detection model and a re-identification (re-ID) model, which are then cascaded to locate and crop persons in scene images and find target person from cropped person images. Training a detection model and a re-ID model separately to achieve person search can avoid the conflict of optimizing different losses in multi-task learning. However, the cascading solutions usually cost more time and have more parameters than the end-to-end solutions. To take advantages and avoid disadvantages of cascading person search methods, we intend to use the knowledge distillation method to teach the end-to-end person search model by using the Class Activation Map of the well-trained person re-ID model as an auxiliary supervise signal and loading well-trained pedestrian detection as a pre-trained model. Besides, we adjust the spatial size of the feature map and select Resnet models to make the student model have higher performance or faster inference speed. Experimental results show that the mAP performance of our framework outperforms the state-of-the-art methods on the PRW dataset.

Crowd simulations imitate the group dynamics of individuals in different environments. Applications in entertainment, security, and education require augmenting simulated crowds into videos of real people. In such cases, virtual agents should realistically interact with the environment and the people in the video. One component of this augmentation task is determining the navigable regions in the video. In this work, we utilize semantic segmentation and pedestrian detection to automatically locate and reconstruct the navigable regions of surveillance-like videos. We place the resulting flat mesh into our 3D crowd simulation environment to integrate virtual agents that navigate inside the video avoiding collision with real pedestrians and other virtual agents. We report the performance of our open-source system using real-life surveillance videos, based on the accuracy of the automatically determined navigable regions and camera configuration. We show that our system generates accurate navigable regions for realistic augmented crowd simulations.

Infrared Radiation (IR) images that capture the reflected IR signals from the surrounding environment have been applied to pedestrian detection and rescue tasks, especially for thermal images reflecting the surface temperature of the objects at nighttime. However, feature detection, extraction and matching are particularly challenging on thermal images as there are few textures compared to normal RGB images, which brings in an enormous gap in introducing various computer vision tasks such as image matching and retrieval, visual localization and SLAM. In this letter, we propose to design a full pipeline to learn a reliable and robust feature detector and descriptor. Our model trained on cross-spectral stereo and KAIST dataset is able to realize a reliable and accurate matching without further annotations. The proposed method is demonstrated to have superior performance compared with both widely used hand-crafted features and features extracted from the most recent learning-based models on visual and quantitative experiments. It also shows a good generalization and robustness ability on FLIR thermal benchmark even without training or fine-tuning on it.

Recently, CNN (convolutional neural networks) based pedestrian detection has made significant progress, but pedestrian detection in a crowd is still a challenge. Pedestrians are close to each other in a crowd, which is difficult for discriminating individuals. To address this issue, we propose an improved Multi-attribute pedestrian detection (MAPD) method, which coptimize person intra-class compactness and inter-class discrepancy. The contributions are fourfold: (1) We analyze the effect of positive setting on the detector and adopt a better positive settings strategy to mitigate extreme class imbalance problems. (2) Inspired by Person Reid, we employ the triplet loss function to learn the advanced id feature of pedestrians. (3) We propose a novel Piecewise NMS algorithm to reduce false positive of small objects. (4) We propose a novel multi-attribute NMS algorithm based on Piecewise NMS algorithm and id information, which can adaptively distinguish predicted boxes of different pedestrians and improve the detector performance. Finally, we evaluate the MAPD detector on two benchmark datasets, including CityPersons and CrowdHuman. Results show that our approach outperforms state-of-the-art methods with a big margin.

This paper proposes an acceleration technique to minimise the unnecessary operations on a state-of-the-art machine learning model and thus to improve the processing speed while maintaining the accuracy. After the study of the main bottlenecks that negatively affect the performance of convolutional neural networks, this paper designs and implements a discarding technique for YOLOv3-based algorithms to increase the speed and maintain accuracy. After applying the discarding technique, YOLOv3 can achieve a 22% of improvement in terms of speed. Moreover, the results of this new discarding technique were tested on Tiny-YOLOv3 with three output layers on an autonomous vehicle for pedestrian detection and it achieved an improvement of 48.7% in speed. The dynamic discarding technique just needs one training process to create the model and thus execute the approach, which preserves accuracy. The improved detector based on the discarding technique is able to readily alert the operator of the autonomous vehicle to take the emergency brake of the vehicle in order to avoid collision and consequently save lives.

Many deep learning detectors have been proposed to address the scale variation issue in pedestrian detection. However, it is still far from being fully solved because most of these detectors handle the issue by directly fusing multiple extracted features with the weighted average or concatenation. Therefore, this paper designs a novel and effective anchor-free network (namely MPAF-Net) for multi-scale pedestrian detection. Specifically, we first improve Res2Net as our backbone network by designing a novel bottleneck block to make the proposed detector has a strong multi-scale representation ability for pedestrians. Furthermore, based on Conditional Random Fields (CRFs), the multi-scale features obtained from three different feature pyramid levels of backbone network are refined with a designed message passing mechanism. By doing so, the complementary information from the features at other scales can be dynamically passed to enhance the scale-specific feature. Finally, pedestrian detection is simplified as a straightforward center and scale prediction task by performing convolution on the concatenation of refined multi-scale convolution features. This way, the proposed MPAF-Net can be trained in an end-to-end fashion. Experimental results show that MPAF-Net achieves state-of-the-art performance on CityPersons, Caltech, and CrowdHuman benchmarks.

In the past years, pedestrian detection has achieved significant progress via improving the visual description. However, the visual description is not robust to discover the occluded pedestrian, which is the bottleneck of the existing pedestrian methods. Targeting to overcome the shortcoming of visual description, we employ the human pose information, which is complementary to the visual description, to address the occlusion and false positive failure problems in pedestrian detection. The advantage of using human pose information is that the pose estimation model can localize the local part of the pedestrian once the pedestrian is occluded. By embedding the human pose information with the visual description, we propose a novel Pose-Embedding Network for pedestrian detection, which consists of two components: a Region Proposal Network, and a Pedestrian Recognization Network. The Region Proposal Network targets to generate lots of candidate proposals and corresponding confidence scores. Once obtaining the candidate proposals, the Pedestrian Recognization Network is proposed to distinguish pedestrian proposals by taking the visual information and pose information into consideration to refine the confidence scores and eliminate the false positives. Given the proposal image, the visual information is extracted with the Visual Feature Module. The Human Pose Module, which is proposed based on the pose estimation model, is used to predict the pose information. Further, the Classification Module is employed to fuse the visual and pose information and generates a pose-embedding pedestrian description. Extensive experiments on three challenging datasets, i.e., Caltech, CityPersons, and COCOPersons, show that the proposed approach achieves a significant improvement upon the state-of-the-art methods.

Pedestrian detection is a canonical problem for safety and security applications, and it remains a challenging problem due to the highly variable lighting conditions in which pedestrians must be detected. This article investigates several domain adaptation approaches to adapt RGB-trained detectors to the thermal domain. Building on our earlier work on domain adaptation for privacy-preserving pedestrian detection, we conducted an extensive experimental evaluation comparing top-down and bottom-up domain adaptation and also propose two new bottom-up domain adaptation strategies. For top-down domain adaptation, we leverage a detector pre-trained on RGB imagery and efficiently adapt it to perform pedestrian detection in the thermal domain. Our bottom-up domain adaptation approaches include two steps: first, training an adapter segment corresponding to initial layers of the RGB-trained detector adapts to the new input distribution; then, we reconnect the adapter segment to the original RGB-trained detector for final adaptation with a top-down loss. To the best of our knowledge, our bottom-up domain adaptation approaches outperform the best-performing single-modality pedestrian detection results on KAIST and outperform the state of the art on FLIR.

Pedestrian detection in traffic environment requires high accuracy and speed of the algorithm. Traditional methods can meet the speed requirement, but there is a long gap in accuracy. Traditional methods based on convolution neural network have higher accuracy, but the amount of calculation is enormous. Aiming at the problems of background confusion, there are pedestrian ambiguity and pedestrian multi-scale in pedestrian detection, this paper constructs a pedestrian detection method with higher accuracy and faster speed based on Faster Regions Convolutional Neural Network (Faster RCNN) method, which is the leading method in the field of target detection. We have mainly improved three aspects: (1) The design criteria based on the summary and the scale characteristics of pedestrians; (2) The setting of anchor windows and the way of creating regional networks have been adjusted, and the pooling layer of environmental regions has been added; (3) Fusion of different levels of features acquires more comprehensive features. Then, based on the open-source deep learning framework, the network is implemented on the California Institute of Technology pedestrian data set. The experimental results show that our method improves the detection accuracy by 2.9% and the detection speed by 10.1 frames/second compared with the original Faster RCNN on the same data set.

Detecting small-scale pedestrians in aerial images is a challenging task that can be difficult even for humans. Observing that the single image based method cannot achieve robust performance because of the poor visual cues of small instances. Considering that multiple frames may provide more information to detect such difficult case instead of only single frame, we design a novel video based pedestrian detection method with a two-stream network pipeline to fully utilize the temporal and contextual information of a video. An aggregated feature map is proposed to absorb the spatial and temporal information with the help of spatial and temporal sub-networks. To better capture motion information, a more refined flow net (SPyNet) is adopted instead of a simple flownet. In the spatial stream subnetwork, we modified the backbone network structure by increasing the feature map resolution with relatively larger receptive field to make it suitable for small-scale detection. Experimental results based on drone video datasets demonstrate that our approach improves detection accuracy in the case of small-scale instances and reduces false positive detections. By exploiting the temporal information and aggregating the feature maps, our two-stream method improves the detection performance by 8.48% in mean Average Precision (mAP) from that of the basic single stream R-FCN method, and it outperforms the state-of-the-art method by 3.09% on the Okutama Human-action dataset.

The multispectral information, including both visible information and infrared information, can describe the detection target in a comprehensive manner. The deep learning (DL)-based detectors that fuse the multispectral features can detect pedestrians robustly in various environments. Therefore, this paper puts forward a robust multispectral feature fusion network (MSFFN) for pedestrian detection, which fully integrates the features extracted from visible light and infrared channels. Specifically, multiscale semantic features were extracted by two core modules, namely, multiscale feature extraction of visible images (MFEV) and multiscale feature extraction of infrared images (MFEI), and fused by the improved YOLOv3 network for pedestrian recognition. Through experiments on the KAIST dataset, it is proved that the MSFFN model can detect pedestrians more accurately than both MFEV and MFEI over daytime and nighttime images on multiple scales. The experimental results on the KAIST multispectral data set in the last section showed that our proposed MFMFN model was superior to a number of state-of-the-art multispectral pedestrian detectors methods in accuracy and speed. The model was also found to strike a good balance between accuracy and speed, and perform excellently on small input images. The research results shed important new light on the design of self-driving vehicles.

In recent years, the performance of the convolutional neural network-based pedestrian detection method has improved significantly. However, an imbalance remains between detection accuracy and speed. In this paper, we employ a one-stage object detection framework and propose a pedestrian detection method based on the multi-scale attention mechanism of a convolutional neural network to improve the imbalance between accuracy and speed. First, a multi-scale convolution module is designed to extract corresponding features at different scales. Second, using the attention module, association information between features is mined from space and channel perspectives to strengthen the original features. Then, the enhanced features are passed through a classification and regression module to perform object positioning and bounding box regression. Finally, to learn more pedestrian location information, we improve the loss function to realise better network training. The proposed method achieved considerable results on the challenging CityPersons and Caltech pedestrian detection datasets.

International audience; The combination of multi-modal image fusion schemes with deep learning classification methods, and particularly with Convolutional Neural Networks (CNNs) has achieved remarkable performances in the pedestrian detection field. The late fusion scheme has significantly enhanced the performance of the pedestrian recognition task. In this paper, the late fusion scheme connected with CNN learning is deeply investigated for pedestrian recognition based on the Daimler stereo vision dataset. Thus, an independent CNN for each imaging modality (Intensity, Depth, and Optical Flow) is used before the fusion of the CNN's probabilistic output scores with a Multi-Layer Perceptron which provides the recognition decision. We propose four different learning patterns based on Cross-Modality deep learning of Convolutional Neural Networks: (1) a Particular Cross-Modality Learning; (2) a Separate Cross-Modality Learning; (3) a Correlated Cross-Modality Learning and (4) an Incremental Cross-Modality Learning model. Moreover, we also design a new CNN architecture, called LeNet+, which improves the classification performance not only for each modality classifier, but also for the multi-modality late-fusion scheme. Finally, we propose to learn the LeNet+ model with the incremental cross-modality approach using optimal learning settings, obtained with a K-fold Cross Validation pattern. This method outperforms the state-of-the-art classifier provided with Daimler datasets on both non-occluded and partially-occluded pedestrian tasks.

In driver assistance or self-driving systems, millimeter-wave radar is an indispensable sensing tool because of its applicability to all weather conditions or non-line-of-sight (NLOS) sensing.This study focuses on a human recognition issue in the NLOS scenario by applying the support vector machine (SVM)-based machine learning approach to a diffraction signal.We show that there is a significant difference in diffraction signals between man-made objects (e.g., metallic cylinder and human body) even without motion.Hence, by exploiting such difference, an SVM achieves a high recognition rate, even in deeply NLOS situations.The experimental investigation, using a 24-GHz millimeter-wave radar in an anechoic chamber demonstrates that a diffraction signal-based recognition accurately classifies the real human and human mimicking man-made object, even in the NLOS scenario shielded by the parking vehicle.

Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance on heavily occluded pedestrians remains far from satisfactory. The main culprits are intra-class occlusions involving other pedestrians and inter-class occlusions caused by other objects, such as cars and bicycles. These result in a multitude of occlusion patterns. We propose an approach for occluded pedestrian detection with the following contributions. First, we introduce a novel mask-guided attention network that fits naturally into popular pedestrian detection pipelines. Our attention network emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features. Second, we propose the occlusion-sensitive hard example mining method and occlusion-sensitive loss that mines hard samples according to the occlusion level and assigns higher weights to the detection errors occurring at highly occluded pedestrians. Third, we empirically demonstrate that weak box-based segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts. Experiments are performed on CityPersons, Caltech and ETH datasets. Our approach sets a new state-of-the-art on all three datasets. Our approach obtains an absolute gain of 10.3% in log-average miss rate, compared with the best reported results on the heavily occluded HO pedestrian set of the CityPersons test set. Code and models are available at: https://github.com/Leotju/MGAN .

Detecting pedestrians at high speed in high resolution (HR) images is important for preventing collisions in autonomous vehicle. The HR images provide more detail information while creating a heavy computational load, resulting in slower detection speed. We find that the pedestrians are usually not present in the upper part of the HR image, due to the camera vertical field of view and the distance between pedestrian and camera. We named this area a non-pedestrian area (NPA). Therefore, we are able to reduce the calculation time while maintaining the detection accuracy by removing NPA from the HR image. According to this concept, we propose a novel pedestrian detection acceleration algorithm called Non-Pedestrian Area Estimation (NPAE). The NPAE algorithm estimates and removes non-pedestrian areas of the image, followed by pedestrian detection of the NPAE output image. Two datasets with three different resolution images are used to test our proposed NPAE algorithm on both GPU and CPU platforms. The RetinaNet is chosen as the reference pedestrian detector. Our algorithm increases the detection speed with 42% on the GPU platform and with 52% speed increase on the CPU platform, for the test images with a resolution of $1920 \times 1080$ pixel. In terms of detection accuracy, NPAE improves by up to 37.94% compared to classical data optimization acceleration methods. The detection accuracy results are well preserved in both platforms.

In the past decades, pedestrian detection has attracted more attention in many practical applications. In this paper, a novel pedestrian detection method using Quaternion Gradient based Weber Local Descriptor (QGWLD) is proposed. Unlike many other local pedestrian detectors that only extracted features from the gray-scale image, which ignored the color information, a new powerful and robust local pedestrian detector is developed, which integrates the advantages of both the color and texture information and can be used to address the pedestrian detection problem well. As we know, the quaternion can entirely characterize a color object well and the WLD feature consisting of the gradient orientation and differential excitation has acquired a good performance for pedestrian detection. Therefore, combining the WLD feature with the quaternion representation, the QGWLD pedestrian detector is presented. Firstly, the quaternion gradient representation is performed on the color image in the sliding window, and then the Weber Local Descriptor (WLD) is extracted over the quaternion gradient feature map. After that, the QGWLD histogram is constructed to characterize the sliding window. Experimental results on INRIA and PennFudanPed pedestrian databases validate the effectiveness of the proposed QGWLD pedestrian detector. Comparing with the similar pedestrian detectors, the proposed QGWLD pedestrian detector performs better.

Small-object detection is a basic and challenging problem in computer vision tasks. It is widely used in pedestrian detection, traffic sign detection, and other fields. This paper proposes a deep learning small-object detection method based on image super-resolution to improve the speed and accuracy of small-object detection. First, we add a feature texture transfer (FTT) module at the input end to improve the image resolution at this end as well as to remove the noise in the image. Then, in the backbone network, using the Darknet53 framework, we use dense blocks to replace residual blocks to reduce the number of network structure parameters to avoid unnecessary calculations. Then, to make full use of the features of small targets in the image, the neck uses a combination of SPPnet and PANnet to complete this part of the multi-scale feature fusion work. Finally, the problem of image background and foreground imbalance is solved by adding the foreground and background balance loss function to the YOLOv4 loss function part. The results of the experiment conducted using our self-built dataset show that the proposed method has higher accuracy and speed compared with the currently available small-target detection methods.

In natural systems, many species are able to coordinate their individual intelligences to perform complex tasks. Swarm Intelligence also denotes the concept of distributed intelligence which relies on the coordination between a massive number of individual intelligences. In this paper, we develop a logical approach to consider distributed intelligence. Our proposal is based on a pedestrian safety issue. So, we extend the bases of a distributed non-monotonic theory to model the “vehicle-pedestrian” interaction system. This extension concerns the preliminary approach proposed in our previous work. Non-monotonic reasoning processes for distributed intelligent logic agents strongly contribute to the development of Pedestrian Collision Warning Systems. These systems benefit greatly from the efficiency of pedestrian detection which has reached a high level thanks to several technologies. We demonstrate the validity of our construction and we specify the knowledge representation of driver-pedestrian interaction in the context of the proposed theory.

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting ismall-scaled pedestrians and occluded pedestrians remains a challenging problem. In this paper, we propose a pedestrian detection method with a couple-network to simultaneously address these two issues. One of the sub-networks, the gated multi-layer feature extraction sub-network, aims to adaptively generate discriminative features for pedestrian candidates in order to robustly detect pedestrians with large variations on scale. The second sub-network targets on handling the occlusion problem of pedestrian detection by using deformable regional region of interest (RoI)-pooling. We investigate two different gate units for the gated sub-network, namely, the channel-wise gate unit and the spatio-wise gate unit, which can enhance the representation ability of the regional convolutional features among the channel dimensions or across the spatial domain, repetitively. Ablation studies have validated the effectiveness of both the proposed gated multi-layer feature extraction sub-network and the deformable occlusion handling sub-network. With the coupled framework, our proposed pedestrian detector achieves promising results on both two pedestrian datasets, especially on detecting small or occluded pedestrians. On the CityPersons dataset, the proposed detector achieves the lowest missing rates (i.e. 40.78% and 34.60%) on detecting small and occluded pedestrians, surpassing the second best comparison method by 6.0% and 5.87%, respectively.

Over the years, unmanned aerial vehicles (UAVs) have been regarded as a potential solution to surveil public spaces, providing a cheap way for data collection, while covering large and difficult-to-reach areas. This kind of solutions can be particularly useful to detect, track and identify subjects of interest in crowds, for security/safety purposes. In this context, various datasets are publicly available, yet most of them are only suitable for evaluating detection, tracking and short-term re-identification techniques. This paper announces the free availability of the P-DESTRE dataset, the first of its kind to provide video/UAV-based data for pedestrian long-term re-identification research, with ID annotations consistent across data collected in different days. As a secondary contribution, we provide the results attained by the state-of-the-art pedestrian detection, tracking, short/long term re-identification techniques in well-known surveillance datasets, used as baselines for the corresponding effectiveness observed in the P-DESTRE data. This comparison highlights the discriminating characteristics of P-DESTRE with respect to similar sets. Finally, we identify the most problematic data degradation factors and co-variates for UAV-based automated data analysis, which should be considered in subsequent technologic/conceptual advances in this field. The dataset and the full specification of the empirical evaluation carried out are freely available at http://p-destre.di.ubi.pt/ .

Mez is a novel publish-subscribe messaging system for latency sensitive multi-camera machine vision applications at the IoT Edge. The unlicensed wireless communication in IoT Edge systems are characterized by large latency variations due to intermittent channel interference. To achieve user specified latency in the presence of wireless channel interference, Mez takes advantage of the ability of machine vision applications to temporarily tolerate lower quality video frames if overall application accuracy is not too adversely affected. Control knobs that involve lossy image transformation techniques that modify the frame size, and thereby the video frame transfer latency, are identified. Mez implements a network latency feedback controller that adapts to channel conditions by dynamically adjusting the video frame quality using the image transformation control knobs, so as to simultaneously satisfy latency and application accuracy requirements. Additionally, Mez uses an application domain specific design of the storage layer to provide low latency operations. Experimental evaluation on an IoT Edge testbed with a pedestrian detection machine vision application indicates that Mez is able to tolerate latency variations of up to 10x with a worst-case reduction of 4.2% of the application accuracy F1 score metric. The performance of Mez is also experimentally evaluated against state-of-the-art low latency NATS messaging system.

Current deep learning methods seldom consider the effects of small pedestrian ratios and considerable differences in the aspect ratio of input images, which results in low pedestrian detection performance. This study proposes the ratio-and-scale-aware YOLO (RSA-YOLO) method to solve the aforementioned problems. The following procedure is adopted in this method. First, ratio-aware mechanisms are introduced to dynamically adjust the input layer length and width hyperparameters of YOLOv3, thereby solving the problem of considerable differences in the aspect ratio. Second, intelligent splits are used to automatically and appropriately divide the original images into two local images. Ratio-aware YOLO (RA-YOLO) is iteratively performed on the two local images. Because the original and local images produce low- and high-resolution pedestrian detection information after RA-YOLO, respectively, this study proposes new scale-aware mechanisms in which multiresolution fusion is used to solve the problem of misdetection of remarkably small pedestrians in images. The experimental results indicate that the proposed method produces favorable results for images with extremely small objects and those with considerable differences in the aspect ratio. Compared with the original YOLOs (i.e., YOLOv2 and YOLOv3) and several state-of-the-art approaches, the proposed method demonstrated a superior performance for the VOC 2012 comp4, INRIA, and ETH databases in terms of the average precision, intersection over union, and lowest log-average miss rate.

The early recognition and understanding of the actions performed by pedestrians in traffic scenes leads to an anticipation of pedestrian intentions in advance and helps in the process of collision warning and avoidance in the context of autonomous vehicles. An environment with low visibility conditions such as night-time, fog, heavy rain or smoke increases the number of difficult situations in traffic. A complete and original model for assessing if a pedestrian is engaged in a street cross action using only infrared monocular scene perception is proposed in this paper. The assessment of a street cross action is done by the time series analysis of features like: pedestrian motion, position of pedestrians with respect to the drivable area and their distance with respect to the ego-vehicle. The extraction of these features emerges from the combination of a deep learning based pedestrian detector with an original tracking algorithm, a semantic segmentation of the road surface and a time series long-short term memory network based action recognition. In order to validate the proposed method we introduce a new dataset named CROSSIR. It is formed of pedestrian annotations, action annotations and semantic labels for the road. The CROSSIR dataset is suitable for several common computer vision algorithms: (1) pedestrian detection and tracking algorithms because each pedestrian has a unique identifier over the frames in which it appears; (2) pedestrian action recognition; (3) semantic segmentation of the road pixels in the infrared image.

Pedestrian detection is a challenging and hot research topic in the field of computer vision, especially for the crowded scenes where occlusion happens frequently. In this paper, we propose a novel AutoPedestrian scheme that automatically augments the pedestrian data and searches for suitable loss functions, aiming for better performance of pedestrian detection especially in crowded scenes. To our best knowledge, it is the first work to automatically search the optimal policy of data augmentation and loss function jointly for the pedestrian detection. To achieve the goal of searching the optimal augmentation scheme and loss function jointly, we first formulate the data augmentation policy and loss function as probability distributions based on different hyper-parameters. Then, we apply a double-loop scheme with importance-sampling to solve the optimization problem of data augmentation and loss function types efficiently. Comprehensive experiments on two popular benchmarks of CrowdHuman and CityPersons show the effectiveness of our proposed method. In particular, we achieve 40.58% in MR on CrowdHuman datasets and 11.3% in MR on CityPersons reasonable subset, yielding new state-of-the-art results on these two datasets.

International audience; Recent advances in machine-learning, especially in deep neural networks have significantly accelerated the development and deployment of transport-oriented intelligent designs with increasingly high efficiency. While these technologies are exceptionally promising toward revolutionizing our current mobility and reducing the number of road accidents, the way to safe Intelligent Transportation Systems (ITS) remains long. Since pedestrians are the most vulnerable road users, designing accurate pedestrian detection methods is a priority task. However, traditional monocular pedestrian detection methods are limited, especially in occlusion handling. Hence, a collaborative perception scheme in which vehicles no longer restrict their input data to their immediate embedded sensors and rather exploit data from remote sensors is necessary to achieve a more comprehensive environment perception. In this work, we propose a novel public dataset: Infrastructure to Vehicle Multi-View Pedestrian Detection Database (I2V-MVPD) that combines synchronized images from both a mobile camera embedded in a car and a static camera in the road infrastructure. We also propose a new multi-view pedestrian detection framework based on collaborative intelligence between vehicles and infrastructure. Our results show a significant improvement in detection performance over monocular detection.

In this article, we address visual surveillance of human activities for a network of cameras with controllable orientations based on gradient-based coverage control techniques. We first formulate the problem as an optimization problem on the matrix manifold $SO(3)$ and then derive the gradient for the cost function using a density function defined on the image plane of each camera. We then develop a real-time density estimation algorithm using computer vision techniques including a real-time pedestrian detection algorithm and examine its real-time feasibility through simulation. We finally demonstrate the complete algorithm including the gradient descent algorithm, the density estimation algorithm, image acquisition/processing and physical motion on a simulator built on a 3-D animation software and an experimental testbed.

The task of pedestrian detection in video surveillance applications will face challenges like dynamic background changes, false human detection (shadow), and illumination variations. In literature, many approaches have been proposed to resolve these challenges. But their performance is not up to the mark. Thus this paper proposes efficient pedestrian detection including shadow removal and automatic dynamic background update. For this firstly, a background frame is initialized where no moving object is present. Then a background subtraction algorithm is applied to each of the key frames from the live video to detect the foreground objects (using fuzzy C means clustering followed by mean absolute difference). Later on this segmented foreground a contour is estimated and passed through the HOG classifier for pedestrian detection. The performance of the proposed approach has been compared using various datasets & state-of-the-art approaches and found to the best with an average precision of 98 %, unlike the others.

The growth in the number of vehicles in the world makes it hard to safely share the environment with pedestrians. Pedestrian’s safety is an important task that needs to be granted in the traffic environment. New cars are equipped with advanced driver assistance systems (ADAS) with a variety of applications. Pedestrian detection application is one of the most important applications for an ADAS that needs to be enhanced. In this paper, we propose a pedestrian detection system to be implemented in an ADAS. The proposed system is based on convolutional neural networks thanks to its performance when solving computer vision applications. On the other side, the proposed system ensures real-time processing and high detection performance. The proposed system will be designed by tacking the advantage of building lightweight convolution blocks and model compression techniques to ensure an embedded implementation. Those blocks will guarantee high precision and fast processing speed. To train and evaluate the proposed system, we used the Caltech dataset. The evaluation of the proposed system resulted in 87% of mean average precision and an inference speed of 35 frames per second.

Effectively detecting pedestrians in various environments would significantly improve driving safety for autonomous vehicles. However, the degrpted visibility and blurred outline and appearance of pedestrian images captured during hazy weather strongly limit the effectiveness of current pedestrian detection methods. To solve this problem, this article presents three novel deep learning approaches based on you only look once. The depth wise separable convolution and linear bottleneck skills were used to reduce the computational cost and number of parameters, rendering our network more efficient. We also innovatively developed a weighted combination layer in one of the approaches by combining multiscale feature maps and a squeeze and excitation block. Collected pedestrian images in hazy weather were augmented using six strategies to enrich the database. Experimental results show that our proposed methods can effectively detect pedestrians in hazy weather, significantly outperforming state-of-the-art methods in both accuracy and speed.

Pedestrian detection has remained an important research topic in both the computer vision and multimedia communities because of its importance in practical applications, such as driving assistance and video surveillance. Existing methods compare the response score with a fixed threshold to determine whether a candidate region contains pedestrians and produce dissatisfactory results that contain either missed detections or false detections, which are difficult to balance. This situation has a serious impact under the condition of variable scale. This paper investigates the functional relationship between the scores and scales of pedestrians. By designing experiments with multiple scales, we have found a discriminant surface in the score scale space. Pedestrians can be distinguished at various scale levels according to their locations on the discriminant surface. The proposed approach is evaluated using four challenging pedestrian detection datasets, including Caltech, INRIA, ETH, and KITTI, and the superior experimental results are achieved when compared with baseline methods.

A critical bottleneck in pedestrian detection is the detection of small-scale pedestrians, which have low contrast and blurry shapes in images and videos. Considered that the body shape of a pedestrian is always rectangular (the height is greater than the width), we propose an asymmetric multi-stage network (AMS-Net) for small-scale pedestrian detection. The proposed method has two main advantages. (1) It considers the asymmetry of a pedestrian’s body shape in pedestrian detection. The rectangular anchors are used to generate various rectangular proposals that have a height greater than the width. In addition, asymmetric rectangular convolution kernels are adopted for capturing the compact features of the pedestrian body. (2) The proposed AMS-Net gradually rejects the non-pedestrian boxes according to coarse-to-fine features in a three-stage framework. The proposed AMS-Net significantly improves the performance of pedestrian detection on the Far subset of the Caltech testing set (the miss rate decreases from 60.79% to 51.36%). It also achieves competitive performance on the INRIA, ETH, KITTI and CityPersons benchmarks.

In this paper, an efficient framework for counting pedestrians crossing a line of interest is proposed. Nowadays, the convolutional neural networks have very good results on pedestrian detection and tracking. However, the major drawback of the neural networks is that they require heavy computing resources. This limits the application of neural networks in low-cost systems. Thus, the low power consuming pedestrian counting systems with comparable performance are still important. To achieve this goal, the proposed method distils the pedestrian detection knowledge from a neural network to train the local binary patterns (LBP) cascade classifier model to detect pedestrians. Then a matching and tracking algorithm is used to count the number of pedestrians. An automaton was developed to eliminate the bouncing position of the detected pedestrians. The experimental comparisons show that, compared to Ma et al. and Felzenszwalb et al.’s methods, the quality of the line of interest counting of the proposed method is about the same and, at the same time, the execution time of the proposed method is much less.

Recently pedestrian detection has progressed significantly. However, detecting pedestrians of small scale or in heavy occlusions is still notoriously difficult. Besides, the generalization ability of pre-trained detectors across different datasets remains to be improved. Both of these issues can be attributed to insufficient training data coverage. To cope with this, we present an efficient data augmentation scheme by transferring pedestrians from other datasets into the target scene with a novel Attribute Preserving Generative Adversarial Networks (APGAN). The proposed methodology consists of two steps: pedestrian embedding and style transfer. The former step can simulate pedestrian images of various scale and occlusion, in any pose or background, thus greatly promoting the data variation. The latter step aims to make the generated samples more realistic while guarantee the data coverage. To achieve this goal, we propose APGAN, which pursues both good visual quality and attribute preserving after style transfer. With the proposed method, we can make effective sample augmentations to improve the generalization ability of the trained detectors and enhance its robustness to scale change and occlusions. Extensive experiment results validate the effectiveness and advantages of our method.

Focusing on data imbalance and intraclass variation, an improved pedestrian detection with a cascade of complex peer AdaBoost classifiers is proposed. The series of the AdaBoost classifiers are learned greedily, along with negative example mining. The complexity of classifiers in the cascade is not limited, so more negative examples are used for training. Furthermore, the cascade becomes an ensemble of strong peer classifiers, which treats intraclass variation. To locally train the AdaBoost classifiers with a high detection rate, a refining strategy is used to discard the hardest negative training examples rather than decreasing their thresholds. Using the aggregate channel feature (ACF), the method achieves miss rates of 35% and 14% on the Caltech pedestrian benchmark and Inria pedestrian dataset, respectively, which are lower than that of increasingly complex AdaBoost classifiers, i.e., 44% and 17%, respectively. Using deep features extracted by the region proposal network (RPN), the method achieves a miss rate of 10.06% on the Caltech pedestrian benchmark, which is also lower than 10.53% from the increasingly complex cascade. This study shows that the proposed method can use more negative examples to train the pedestrian detector. It outperforms the existing cascade of increasingly complex classifiers.