Search

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduces an automatic score detection model using object detection techniques. The study contributes to the field of computer vision by comparing the performance of seven models (belonging to two different architectural setups) and by making the dataset publicly available. Another value-added aspect is the inclusion of three variants of the object detection model, YOLOv8, recently released in 2023 (at the time of writing). Five of the used models are single-shot detectors, while two belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640 × 640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among these models, YOLOv8m performed the best, with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3 ms) than YOLOv8m (5.7 ms) and yet generated a competitive mAP50 of 96.5%. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) has provided a significant breakthrough in many areas of research and industry. The development of Convolutional Neural Networks (CNNs) has enabled the improvement of computer vision-based techniques, making the information gathered from cameras more useful. For this reason, recently, studies have been carried out on the use of image-based DL in some areas of people's daily life. In this paper, an object detection-based algorithm is proposed to modify and improve the user experience in relation to the use of cooking appliances. The algorithm can sense common kitchen objects and identify interesting situations for users. Some of these situations are the detection of utensils on lit hobs, recognition of boiling, smoking and oil in kitchenware, and determination of good cookware size adjustment, among others. In addition, the authors have achieved sensor fusion by using a cooker hob with Bluetooth connectivity, so it is possible to automatically interact with it via an external device such as a computer or a mobile phone. Our main contribution focuses on supporting people when they are cooking, controlling heaters, or alerting them with different types of alarms. To the best of our knowledge, this is the first time a YOLO algorithm has been used to control the cooktop by means of visual sensorization. Moreover, this research paper provides a comparison of the detection performance among different YOLO networks. Additionally, a dataset of more than 7500 images has been generated and multiple data augmentation techniques have been compared. The results show that YOLOv5s can successfully detect common kitchen objects with high accuracy and fast speed, and it can be employed for realistic cooking environment applications. Finally, multiple examples of the identification of interesting situations and how we act on the cooktop are presented. [ABSTRACT FROM AUTHOR]

High dynamic range (HDR) imaging technology is increasingly being used in automated driving systems (ADS) for improving the safety of traffic participants in scenes with strong differences in illumination. Therefore, a combination of HDR video, that is video with details in all illumination regimes, and (HDR) object perception techniques that can deal with this variety in illumination is highly desirable. Although progress has been made in both HDR imaging solutions and object detection algorithms in the recent years, they have progressed independently of each other. This has led to a situation in which object detection algorithms are typically designed and constantly improved to operate on 8 bit per channel content. This makes these algorithms not ideally suited for use in HDR data processing, which natively encodes to a higher bit-depth (12 bits/16 bits per channel). In this paper, we present and evaluate two novel convolutional neural network (CNN) architectures that intelligently convert high bit depth HDR images into 8-bit images. We attempt to optimize reconstruction quality by focusing on ADS object detection quality. The first research novelty is to jointly perform tone-mapping with demosaicing by additionally successfully suppressing noise and demosaicing artifacts. The first CNN performs tone-mapping with noise suppression on a full-color HDR input, while the second performs joint demosaicing and tone-mapping with noise suppression on a raw HDR input. The focus is to increase the detectability of traffic-related objects in the reconstructed 8-bit content, while ensuring that the realism of the standard dynamic range (SDR) content in diverse conditions is preserved. The second research novelty is that for the first time, to the best of our knowledge, a thorough comparative analysis against the state-of-the-art tone-mapping and demosaicing methods is performed with respect to ADS object detection accuracy on traffic-related content that abounds with diverse challenging (i.e., boundary cases) scenes. The evaluation results show that the two proposed networks have better performance in object detection accuracy and image quality, than both SDR content and content obtained with the state-of-the-art tone-mapping and demosaicing algorithms. [ABSTRACT FROM AUTHOR]

Network pruning techniques have been widely used for compressing computational and memory intensive deep learning models through removing redundant components of the model. According to the pruning granularity, network pruning can be categorized into structured and unstructured methods. The structured pruning removes the large components in a model such as channels or layers, which might reduce the accuracy. The unstructured pruning directly removes mainly the parameters in a model as well as the redundant channels or layers, which might result in an inadequate pruning. To address the limitations of the pruning methods, this paper proposes a heuristic method for minimizing model size. This paper implements an algorithm to combine both the structured and the unstructured pruning methods while maintaining the target accuracy that is configured by its application. We use network slimming for the structured pruning method and deep compression for the unstructured one. Our method achieves a higher compression ratio than the case when the individual pruning method is applied. To show the effectiveness of our proposed method, this paper evaluates our proposed method with actual state-of-the-art CNN models of VGGNet, ResNet and DenseNet under the CIFAR-10 dataset. This paper discusses the performance of the proposed method with the cases of individual usage of the structured and unstructured pruning methods and then proves that our method achieves better performance with higher compression ratio. In the best case of the VGGNet, our method results in a 13× reduction ratio in the model size, and also gives a 15× reduction ratio regarding the pruning time compared with the brute-force search method. [ABSTRACT FROM AUTHOR]

Nowadays, Convolution Neural Network (CNN) based deep learning methods are widely used in detecting and classifying fruits from faults, color and size characteristics. In this study, two different neural network model estimators are employed to detect apples using the Single-Shot Multibox Detection (SSD) Mobilenet and Faster Region-CNN (Faster R-CNN) model architectures, with the custom dataset generated from the red apple species. Each neural network model is trained with created dataset using 4000 apple images. With the trained model, apples are detected and counted autonomously using the developed Flying Robotic System (FRS) in a commercially produced apple orchard. In this way, it is aimed that producers make accurate yield forecasts before commercial agreements. In this paper, SSD-Mobilenet and Faster R-CNN architecture models trained with COCO datasets referenced in many studies, and SSD-Mobilenet and Faster R-CNN models trained with a learning rate ranging from 0.015–0.04 using the custom dataset are compared experimentally in terms of performance. In the experiments implemented, it is observed that the accuracy rates of the proposed models increased to the level of 93%. Consequently, it has been observed that the Faster R-CNN model, which is developed, makes extremely successful determinations by lowering the loss value below 0.1. [ABSTRACT FROM AUTHOR]

Intelligent driver assistance systems are becoming increasingly popular in modern passenger vehicles. A crucial component of intelligent vehicles is the ability to detect vulnerable road users (VRUs) for an early and safe response. However, standard imaging sensors perform poorly in conditions of strong illumination contrast, such as approaching a tunnel or at night, due to their dynamic range limitations. In this paper, we focus on the use of high-dynamic-range (HDR) imaging sensors in vehicle perception systems and the subsequent need for tone mapping of the acquired data into a standard 8-bit representation. To our knowledge, no previous studies have evaluated the impact of tone mapping on object detection performance. We investigate the potential for optimizing HDR tone mapping to achieve a natural image appearance while facilitating object detection of state-of-the-art detectors designed for standard dynamic range (SDR) images. Our proposed approach relies on a lightweight convolutional neural network (CNN) that tone maps HDR video frames into a standard 8-bit representation. We introduce a novel training approach called detection-informed tone mapping (DI-TM) and evaluate its performance with respect to its effectiveness and robustness in various scene conditions, as well as its performance relative to an existing state-of-the-art tone mapping method. The results show that the proposed DI-TM method achieves the best results in terms of detection performance metrics in challenging dynamic range conditions, while both methods perform well in typical, non-challenging conditions. In challenging conditions, our method improves the detection F2 score by 13%. Compared to SDR images, the increase in F 2 score is 49%. [ABSTRACT FROM AUTHOR]

Object detection is a fundamental task in computer vision. Over the past several years, convolutional neural network (CNN)-based object detection models have significantly improved detection accuracyin terms of average precision (AP). Furthermore, feature pyramid networks (FPNs) are essential modules for object detection models to consider various object scales. However, the AP for small objects is lower than the AP for medium and large objects. It is difficult to recognize small objects because they do not have sufficient information, and information is lost in deeper CNN layers. This paper proposes a new FPN model named ssFPN (scale sequence (S 2 ) feature-based feature pyramid network) to detect multi-scale objects, especially small objects. We propose a new scale sequence (S 2 ) feature that is extracted by 3D convolution on the level of the FPN. It is defined and extracted from the FPN to strengthen the information on small objects based on scale-space theory. Motivated by this theory, the FPN is regarded as a scale space and extracts a scale sequence (S 2 ) feature by three-dimensional convolution on the level axis of the FPN. The defined feature is basically scale-invariant and is built on a high-resolution pyramid feature map for small objects. Additionally, the deigned S 2 feature can be extended to most object detection models based on FPNs. We also designed a feature-level super-resolution approach to show the efficiency of the scale sequence (S 2 ) feature. We verified that the scale sequence (S 2 ) feature could improve the classification accuracy for low-resolution images by training a feature-level super-resolution model. To demonstrate the effect of the scale sequence (S 2 ) feature, experiments on the scale sequence (S 2 ) feature built-in object detection approach including both one-stage and two-stage models were conducted on the MS COCO dataset. For the two-stage object detection models Faster R-CNN and Mask R-CNN with the S 2 feature, AP improvements of up to 1.6% and 1.4%, respectively, were achieved. Additionally, the AP S of each model was improved by 1.2% and 1.1%, respectively. Furthermore, the one-stage object detection models in the YOLO series were improved. For YOLOv4-P5, YOLOv4-P6, YOLOR-P6, YOLOR-W6, and YOLOR-D6 with the S 2 feature, 0.9%, 0.5%, 0.5%, 0.1%, and 0.1% AP improvements were observed. For small object detection, the AP S increased by 1.1%, 1.1%, 0.9%, 0.4%, and 0.1%, respectively. Experiments using the feature-level super-resolution approach with the proposed scale sequence (S 2 ) feature were conducted on the CIFAR-100 dataset. By training the feature-level super-resolution model, we verified that ResNet-101 with the S 2 feature trained on LR images achieved a 55.2% classification accuracy, which was 1.6% higher than for ResNet-101 trained on HR images. [ABSTRACT FROM AUTHOR]

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. [ABSTRACT FROM AUTHOR]

Logo detection is one of the crucial branches in computer vision due to various real-world applications, such as automatic logo detection and recognition, intelligent transportation, and trademark infringement detection. Compared with traditional handcrafted-feature-based methods, deep learning-based convolutional neural networks (CNNs) can learn both low-level and high-level image features. Recent decades have witnessed the great feature representation capabilities of deep CNNs and their variants, which have been very good at discovering intricate structures in high-dimensional data and are thereby applicable to many domains including logo detection. However, logo detection remains challenging, as existing detection methods cannot solve well the problems of a multiscale and large aspect ratios. In this paper, we tackle these challenges by developing a novel long-range dependence involutional network (LDI-Net). Specifically, we designed a strategy that combines a new operator and a self-attention mechanism via rethinking the intrinsic principle of convolution called long-range dependence involution (LD involution) to alleviate the detection difficulties caused by large aspect ratios. We also introduce a multilevel representation neural architecture search (MRNAS) to detect multiscale logo objects by constructing a novel multipath topology. In addition, we implemented an adaptive RoI pooling module (ARM) to improve detection efficiency by addressing the problem of logo deformation. Comprehensive experiments on four benchmark logo datasets demonstrate the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Economic and environmental sustainability is becoming increasingly important in today's world. Electronic waste (e-waste) is on the rise and options to reuse parts should be explored. Hence, this paper presents the development of vision-based methods for the detection and classification of used electronics parts. In particular, the problem of classifying commonly used and relatively expensive electronic project parts such as capacitors, potentiometers, and voltage regulator ICs is investigated. A multiple object workspace scenario with an overhead camera is investigated. A customized object detection algorithm determines regions of interest and extracts data for classification. Three classification methods are explored: (a) shallow neural networks (SNNs), (b) support vector machines (SVMs), and (c) deep learning with convolutional neural networks (CNNs). All three methods utilize 30 × 30-pixel grayscale image inputs. Shallow neural networks achieved the lowest overall accuracy of 85.6%. The SVM implementation produced its best results using a cubic kernel and principal component analysis (PCA) with 20 features. An overall accuracy of 95.2% was achieved with this setting. The deep learning CNN model has three convolution layers, two pooling layers, one fully connected layer, softmax, and a classification layer. The convolution layer filter size was set to four and adjusting the number of filters produced little variation in accuracy. An overall accuracy of 98.1% was achieved with the CNN model. [ABSTRACT FROM AUTHOR]

Haemoglobin (Hb) electrophoresis is a method of blood testing used to detect thalassaemia. However, the interpretation of the result of the electrophoresis test itself is a complex task. Expert haematologists, specifically in developing countries, are relatively few in number and are usually overburdened. To assist them with their workload, in this paper we present a novel method for the automated assessment of thalassaemia using Hb electrophoresis images. Moreover, in this study we compile a large Hb electrophoresis image dataset, consisting of 103 strips containing 524 electrophoresis images with a clear consensus on the quality of electrophoresis obtained from 824 subjects. The proposed methodology is split into two parts: (1) single-patient electrophoresis image segmentation by means of the lane extraction technique, and (2) binary classification (normal or abnormal) of the electrophoresis images using state-of-the-art deep convolutional neural networks (CNNs) and using the concept of transfer learning. Image processing techniques including filtering and morphological operations are applied for object detection and lane extraction to automatically separate the lanes and classify them using CNN models. Seven different CNN models (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, SqueezeNet and MobileNetV2) were investigated in this study. InceptionV3 outperformed the other CNNs in detecting thalassaemia using Hb electrophoresis images. The accuracy, precision, recall, f1-score, and specificity in the detection of thalassaemia obtained with the InceptionV3 model were 95.8%, 95.84%, 95.8%, 95.8% and 95.8%, respectively. MobileNetV2 demonstrated an accuracy, precision, recall, f1-score, and specificity of 95.72%, 95.73%, 95.72%, 95.7% and 95.72% respectively. Its performance was comparable with the best performing model, InceptionV3. Since it is a very shallow network, MobileNetV2 also provides the least latency in processing a single-patient image and it can be suitably used for mobile applications. The proposed approach, which has shown very high classification accuracy, will assist in the rapid and robust detection of thalassaemia using Hb electrophoresis images. [ABSTRACT FROM AUTHOR]

The growing aging population suffers from high levels of vision and cognitive impairment, often resulting in a loss of independence. Such individuals must perform crucial everyday tasks such as cooking and heating with systems and devices designed for visually unimpaired individuals, which do not take into account the needs of persons with visual and cognitive impairment. Thus, the visually impaired persons using them run risks related to smoke and fire. In this paper, we propose a vision-based fire detection and notification system using smart glasses and deep learning models for blind and visually impaired (BVI) people. The system enables early detection of fires in indoor environments. To perform real-time fire detection and notification, the proposed system uses image brightness and a new convolutional neural network employing an improved YOLOv4 model with a convolutional block attention module. The h-swish activation function is used to reduce the running time and increase the robustness of YOLOv4. We adapt our previously developed smart glasses system to capture images and inform BVI people about fires and other surrounding objects through auditory messages. We create a large fire image dataset with indoor fire scenes to accurately detect fires. Furthermore, we develop an object mapping approach to provide BVI people with complete information about surrounding objects and to differentiate between hazardous and nonhazardous fires. The proposed system shows an improvement over other well-known approaches in all fire detection metrics such as precision, recall, and average precision. [ABSTRACT FROM AUTHOR]

There has been substantial progress in small object detection in aerial images in recent years, due to the extensive applications and improved performances of convolutional neural networks (CNNs). Typically, traditional machine learning algorithms tend to prioritize inference speed over accuracy. Insufficient samples can cause problems for convolutional neural networks, such as instability, non-convergence, and overfitting. Additionally, detecting aerial images has inherent challenges, such as varying altitudes and illuminance situations, and blurred and dense objects, resulting in low detection accuracy. As a result, this paper adds a transformer backbone attention mechanism as a branch network, using the region-wide feature information. This paper also employs a generative model to expand the input aerial images ahead of the backbone. The respective advantages of the generative model and transformer network are incorporated. On the dataset presented in this study, the model achieves 96.77% precision, 98.83% recall, and 97.91% m A P by adding the Multi-GANs module to the one-stage detection network. These three indices are enhanced by 13.9%, 20.54%, and 10.27%, respectively, when compared to the other detection networks. Furthermore, this study provides an auto-pruning technique that may achieve 32.2 FPS inference speed with a minor performance loss while responding to the real-time detection task's usage environment. This research also develops a macOS application for the proposed algorithm using Swift development technology. [ABSTRACT FROM AUTHOR]

To overcome the limitations of standard datasets with data at a wide-variety of scales and captured in the various conditions necessary to train neural networks to yield efficient results in ADAS applications, this paper presents a self-built open-to-free-use 'iVS dataset' and a data annotation tool entitled 'ezLabel'. The iVS dataset is comprised of various objects at different scales as seen in and around real driving environments. The data in the iVS dataset are collected by employing a camcorder in vehicles driving under different conditions, e.g., light, weather and traffic, and driving scenarios ranging from city traffic during peak and normal hours to freeway traffics during busy and normal conditions. Thus, the collected data are wide-ranging and captured all possible objects at various scales appearing in real-time driving situations. The data collected in order to build the dataset has to be annotated before use in training the CNNs and so this paper presents an open-to-free-use data annotation tool, ezLabel, for data annotation purposes as well. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based deep learning (DL) has a wide variety of applications in the geospatial and remote sensing (RS) sciences, and consequently has been a focus of many recent studies. However, a review of accuracy assessment methods used in recently published RS DL studies, focusing on scene classification, object detection, semantic segmentation, and instance segmentation, indicates that RS DL papers appear to follow an accuracy assessment approach that diverges from that of traditional RS studies. Papers reporting on RS DL studies have largely abandoned traditional RS accuracy assessment terminology; they rarely reported a complete confusion matrix; and sampling designs and analysis protocols generally did not provide a population-based confusion matrix, in which the table entries are estimates of the probabilities of occurrence of the mapped landscape. These issues indicate the need for the RS community to develop guidance on best practices for accuracy assessment for CNN-based DL thematic mapping and object detection. As a first step in that process, we explore key issues, including the observation that accuracy assessments should not be biased by the CNN-based training and inference processes that rely on image chips. Furthermore, accuracy assessments should be consistent with prior recommendations and standards in the field, should support the estimation of a population confusion matrix, and should allow for assessment of model generalization. This paper draws from our review of the RS DL literature and the rich record of traditional remote sensing accuracy assessment research while considering the unique nature of CNN-based deep learning to propose accuracy assessment best practices that use appropriate sampling methods, training and validation data partitioning, assessment metrics, and reporting standards. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based deep learning (DL) is a powerful, recently developed image classification approach. With origins in the computer vision and image processing communities, the accuracy assessment methods developed for CNN-based DL use a wide range of metrics that may be unfamiliar to the remote sensing (RS) community. To explore the differences between traditional RS and DL RS methods, we surveyed a random selection of 100 papers from the RS DL literature. The results show that RS DL studies have largely abandoned traditional RS accuracy assessment terminology, though some of the accuracy measures typically used in DL papers, most notably precision and recall, have direct equivalents in traditional RS terminology. Some of the DL accuracy terms have multiple names, or are equivalent to another measure. In our sample, DL studies only rarely reported a complete confusion matrix, and when they did so, it was even more rare that the confusion matrix estimated population properties. On the other hand, some DL studies are increasingly paying attention to the role of class prevalence in designing accuracy assessment approaches. DL studies that evaluate the decision boundary threshold over a range of values tend to use the precision-recall (P-R) curve, the associated area under the curve (AUC) measures of average precision (AP) and mean average precision (mAP), rather than the traditional receiver operating characteristic (ROC) curve and its AUC. DL studies are also notable for testing the generalization of their models on entirely new datasets, including data from new areas, new acquisition times, or even new sensors. [ABSTRACT FROM AUTHOR]

Loop Closure Detection (LCD) is an important technique to improve the accuracy of Simultaneous Localization and Mapping (SLAM). In this paper, we propose an LCD algorithm based on binary classification for feature matching between similar images with deep learning, which greatly improves the accuracy of LCD algorithm. Meanwhile, a novel lightweight convolutional neural network (CNN) is proposed and applied to the target detection task of key frames. On this basis, the key frames are binary classified according to their labels. Finally, similar frames are input into the improved lightweight feature matching network based on Transformer to judge whether the current position is loop closure. The experimental results show that, compared with the traditional method, LFM-LCD has higher accuracy and recall rate in the LCD task of indoor SLAM while ensuring the number of parameters and calculation amount. The research in this paper provides a new direction for LCD of robotic SLAM, which will be further improved with the development of deep learning. [ABSTRACT FROM AUTHOR]

Public littering and discarded trash are, despite the effort being put to limit it, still a serious ecological, aesthetic, and social problem. The problematic waste is usually localised and picked up by designated personnel, which is a tiresome, time-consuming task. This paper proposes a low-cost solution enabling the localisation of trash and litter objects in low altitude imagery collected by an unmanned aerial vehicle (UAV) during an autonomous patrol mission. The objects of interest are detected in the acquired images and put on the global map using a set of onboard sensors commonly found in typical UAV autopilots. The core object detection algorithm is based on deep, convolutional neural networks. Since the task is domain-specific, a dedicated dataset of images containing objects of interest was collected and annotated. The dataset is made publicly available, and its description is contained in the paper. The dataset was used to test a range of embedded devices enabling the deployment of deep neural networks for inference onboard the UAV. The results of measurements in terms of detection accuracy and processing speed are enclosed, and recommendations for the neural network model and hardware platform are given based on the obtained values. The complete system can be put together using inexpensive, off-the-shelf components, and perform autonomous localisation of discarded trash, relieving human personnel of this burdensome task, and enabling automated pickup planning. [ABSTRACT FROM AUTHOR]

Deep learning is currently the mainstream method of object detection. Faster region-based convolutional neural network (Faster R-CNN) has a pivotal position in deep learning. It has impressive detection effects in ordinary scenes. However, under special conditions, there can still be unsatisfactory detection performance, such as the object having problems like occlusion, deformation, or small size. This paper proposes a novel and improved algorithm based on the Faster R-CNN framework combined with the Faster R-CNN algorithm with skip pooling and fusion of contextual information. This algorithm can improve the detection performance under special conditions on the basis of Faster R-CNN. The improvement mainly has three parts: The first part adds a context information feature extraction model after the conv5_3 of the convolutional layer; the second part adds skip pooling so that the former can fully obtain the contextual information of the object, especially for situations where the object is occluded and deformed; and the third part replaces the region proposal network (RPN) with a more efficient guided anchor RPN (GA-RPN), which can maintain the recall rate while improving the detection performance. The latter can obtain more detailed information from different feature layers of the deep neural network algorithm, and is especially aimed at scenes with small objects. Compared with Faster R-CNN, you only look once series (such as: YOLOv3), single shot detector (such as: SSD512), and other object detection algorithms, the algorithm proposed in this paper has an average improvement of 6.857% on the mean average precision (mAP) evaluation index while maintaining a certain recall rate. This strongly proves that the proposed method has higher detection rate and detection efficiency in this case. [ABSTRACT FROM AUTHOR]

In high-resolution earth observation systems, object detection in high spatial resolution remote sensing images (HSRIs) is the key technology for automatic extraction, analysis and understanding of image information. With respect to the multi-angle features of object orientation in HSRIs object detection, this paper presents a novel HSRIs object detection method based on convolutional neural networks (CNN) with adaptive object orientation features. First, an adaptive object orientation regression method is proposed to obtain object regions in any direction. In the adaptive object orientation regression method, five coordinate parameters are used to regress the object region with any direction. Then, a CNN framework for object detection of HSRIs is designed using the adaptive object orientation regression method. Using multiple object detection datasets, the proposed method is compared with some state-of-the-art object detection methods. The experimental results show that the proposed method can more accurately detect objects with large aspect ratios and densely distributed objects than some state-of-the-art object detection methods using a horizontal bounding box, and obtain better object detection results for HSRIs. [ABSTRACT FROM AUTHOR]

Video surveillance systems process high volumes of image data. To enable long-term retention of recorded images and because of the data transfer limitations in geographically distributed systems, lossy compression is commonly applied to images prior to processing, but this causes a deterioration in image quality due to the removal of potentially important image details. In this paper, we investigate the impact of image compression on the performance of object detection methods based on convolutional neural networks. We focus on Joint Photographic Expert Group (JPEG) compression and thoroughly analyze a range of the performance metrics. Our experimental study, performed over a widely used object detection benchmark, assessed the robustness of nine popular object-detection deep models against varying compression characteristics. We show that our methodology can allow practitioners to establish an acceptable compression level for specific use cases; hence, it can play a key role in applications that process and store very large image data. [ABSTRACT FROM AUTHOR]

Simple Summary: Owing to climate change and human overdevelopment, the number of endangered species has been increasing. To face this challenge, the CITES treaty has been adopted by many countries worldwide to prevent the extinction of endangered plants and animals. Additionally, since customs clearance inspections for goods at airports and ports take a long time, and due to the difficulty of distinguishing such species by nonexperts, smugglers have been exploiting this vulnerability to illegally import or export endangered parrot species. If these cases continue to increase, the extinction of species with fewer populations can be accelerated by illegal trade. To tackle this problem, in this study, we constructed an object detection model using convolutional neural networks (CNNs) to classify 11 endangered species of parrots. Utilizing artificial intelligence techniques, the procedures for inspection of goods can be simplified and the customs clearance inspection systems at airports and ports can be enhanced, thus protecting endangered species. Owing to climate change and human indiscriminate development, the population of endangered species has been decreasing. To protect endangered species, many countries worldwide have adopted the CITES treaty to prevent the extinction of endangered plants and animals. Moreover, research has been conducted using diverse approaches, particularly deep learning-based animal and plant image recognition methods. In this paper, we propose an automated image classification method for 11 endangered parrot species included in CITES. The 11 species include subspecies that are very similar in appearance. Data images were collected from the Internet and built in cooperation with Seoul Grand Park Zoo to build an indigenous database. The dataset for deep learning training consisted of 70% training set, 15% validation set, and 15% test set. In addition, a data augmentation technique was applied to reduce the data collection limit and prevent overfitting. The performance of various backbone CNN architectures (i.e., VGGNet, ResNet, and DenseNet) were compared using the SSD model. The experiment derived the test set image performance for the training model, and the results show that the DenseNet18 had the best performance with an mAP of approximately 96.6% and an inference time of 0.38 s. [ABSTRACT FROM AUTHOR]

The collapse of buildings caused by the earthquake seriously threatened human lives and safety. So, the quick detection of collapsed buildings from post-earthquake images is essential for disaster relief and disaster damage assessment. Compared with the traditional building extraction methods, the methods based on convolutional neural networks perform better because it can automatically extract high-dimensional abstract features from images. However, there are still many problems with deep learning in the extraction of collapsed buildings. For example, due to the complex scenes after the earthquake, the collapsed buildings are easily confused with the background, so it is difficult to fully use the multiple features extracted by collapsed buildings, which leads to time consumption and low accuracy of collapsed buildings extraction when training the model. In addition, model training is prone to overfitting, which reduces the performance of model migration. This paper proposes to use the improved classic version of the you only look once model (YOLOv4) to detect collapsed buildings from the post-earthquake aerial images. Specifically, the k-means algorithm is used to optimally select the number and size of anchors from the image. We replace the Resblock in CSPDarkNet53 in YOLOv4 with the ResNext block to improve the backbone's ability and the performance of classification. Furthermore, to replace the loss function of YOLOv4 with the Focal-EOIU loss function. The result shows that compared with the original YOLOv4 model, our proposed method can extract collapsed buildings more accurately. The AP (average precision) increased from 88.23% to 93.76%. The detection speed reached 32.7 f/s. Our method not only improves the accuracy but also enhances the detection speed of the collapsed buildings. Moreover, providing a basis for the detection of large-scale collapsed buildings in the future. [ABSTRACT FROM AUTHOR]

In this paper, we present a real-time object detection and depth estimation approach based on deep convolutional neural networks (CNNs). We improve object detection through the incorporation of transfer connection blocks (TCBs), in particular, to detect small objects in real time. For depth estimation, we introduce binocular vision to the monocular-based disparity estimation network, and the epipolar constraint is used to improve prediction accuracy. Finally, we integrate the two-dimensional (2D) location of the detected object with the depth information to achieve real-time detection and depth estimation. The results demonstrate that the proposed approach achieves better results compared to conventional methods. [ABSTRACT FROM AUTHOR]

Object detection is a challenging computer vision task with numerous real-world applications. In recent years, the concept of the object relationship model has become helpful for object detection and has been verified and realized in deep learning. Nonetheless, most approaches to modeling object relations are limited to using the anchor-based algorithms; they cannot be directly migrated to the anchor-free frameworks. The reason is that the anchor-free algorithms are used to eliminate the complex design of anchors and predict heatmaps to represent the locations of keypoints of different object categories, without considering the relationship between keypoints. Therefore, to better fuse the information between the heatmap channels, it is important to model the visual relationship between keypoints. In this paper, we present a knowledge-driven network (KDNet)—a new architecture that can aggregate and model keypoint relations to augment object features for detection. Specifically, it processes a set of keypoints simultaneously through interactions between their local and geometric features, thereby allowing the modeling of their relationship. Finally, the updated heatmaps were used to obtain the corners of the objects and determine their positions. The experimental results conducted on the RIDER dataset confirm the effectiveness of the proposed KDNet, which significantly outperformed other state-of-the-art object detection methods. [ABSTRACT FROM AUTHOR]

An early estimation of the exact number of fruits, flowers, and trees helps farmers to make better decisions on cultivation practices, plant disease prevention, and the size of harvest labor force. The current practice of yield estimation based on manual counting of fruits or flowers by workers is a time consuming and expensive process and it is not feasible for large fields. Automatic yield estimation based on robotic agriculture provides a viable solution in this regard. In a typical image classification process, the task is not only to specify the presence or absence of a given object on a specific location, while counting how many objects are present in the scene. The success of these tasks largely depends on the availability of a large amount of training samples. This paper presents a detector of bunches of one fruit, grape, based on a deep convolutional neural network trained to detect vine bunches directly on the field. Experimental results show a 91% mean Average Precision. [ABSTRACT FROM AUTHOR]

Compared with ordinary images, each of the remote sensing images contains many kinds of objects with large scale changes, providing more details. As a typical object of remote sensing image, ship detection has been playing an essential role in the field of remote sensing. With the rapid development of deep learning, remote sensing image detection method based on convolutional neural network (CNN) has occupied a key position. In remote sensing images, the objects of which small scale objects account for a large proportion are closely arranged. In addition, the convolution layer in CNN lacks ample context information, leading to low detection accuracy for remote sensing image detection. To improve detection accuracy and keep the speed of real-time detection, this paper proposed an efficient object detection algorithm for ship detection of remote sensing image based on improved SSD. Firstly, we add a feature fusion module to shallow feature layers to refine feature extraction ability of small object. Then, we add Squeeze-and-Excitation Network (SE) module to each feature layers, introducing attention mechanism to network. The experimental results based on Synthetic Aperture Radar ship detection dataset (SSDD) show that the mAP reaches 94.41%, and the average detection speed is 31FPS. Compared with SSD and other representative object detection algorithms, this improved algorithm has a better performance in detection accuracy and can realize real-time detection. [ABSTRACT FROM AUTHOR]

Sand theft or illegal mining in river dredging areas has been a problem in recent decades. For this reason, increasing the use of artificial intelligence in dredging areas, building automated monitoring systems, and reducing human involvement can effectively deter crime and lighten the workload of security guards. In this investigation, a smart dredging construction site system was developed using automated techniques that were arranged to be suitable to various areas. The aim in the initial period of the smart dredging construction was to automate the audit work at the control point, which manages trucks in river dredging areas. Images of dump trucks entering the control point were captured using monitoring equipment in the construction area. The obtained images and the deep learning technique, YOLOv3, were used to detect the positions of the vehicle license plates. Framed images of the vehicle license plates were captured and were used as input in an image classification model, C-CNN-L3, to identify the number of characters on the license plate. Based on the classification results, the images of the vehicle license plates were transmitted to a text recognition model, R-CNN-L3, that corresponded to the characters of the license plate. Finally, the models of each stage were integrated into a real-time truck license plate recognition (TLPR) system; the single character recognition rate was 97.59%, the overall recognition rate was 93.73%, and the speed was 0.3271 s/image. The TLPR system reduces the labor force and time spent to identify the license plates, effectively reducing the probability of crime and increasing the transparency, automation, and efficiency of the frontline personnel's work. The TLPR is the first step toward an automated operation to manage trucks at the control point. The subsequent and ongoing development of system functions can advance dredging operations toward the goal of being a smart construction site. By intending to facilitate an intelligent and highly efficient management system of dredging-related departments by providing a vehicle LPR system, this paper forms a contribution to the current body of knowledge in the sense that it presents an objective approach for the TLPR system. [ABSTRACT FROM AUTHOR]

As key-components of the urban-drainage system, storm-drains and manholes are essential to the hydrological modeling of urban basins. Accurately mapping of these objects can help to improve the storm-drain systems for the prevention and mitigation of urban floods. Novel Deep Learning (DL) methods have been proposed to aid the mapping of these urban features. The main aim of this paper is to evaluate the state-of-the-art object detection method RetinaNet to identify storm-drain and manhole in urban areas in street-level RGB images. The experimental assessment was performed using 297 mobile mapping images captured in 2019 in the streets in six regions in Campo Grande city, located in Mato Grosso do Sul state, Brazil. Two configurations of training, validation, and test images were considered. ResNet-50 and ResNet-101 were adopted in the experimental assessment as the two distinct feature extractor networks (i.e., backbones) for the RetinaNet method. The results were compared with the Faster R-CNN method. The results showed a higher detection accuracy when using RetinaNet with ResNet-50. In conclusion, the assessed DL method is adequate to detect storm-drain and manhole from mobile mapping RGB images, outperforming the Faster R-CNN method. The labeled dataset used in this study is available for future research. [ABSTRACT FROM AUTHOR]

With the increasing number of drones, the danger of their illegal use has become relevant. This has necessitated the creation of automatic drone protection systems. One of the important tasks solved by these systems is the reliable detection of drones near guarded objects. This problem can be solved using various methods. From the point of view of the price–quality ratio, the use of video cameras for a drone detection is of great interest. However, drone detection using visual information is hampered by the large similarity of drones to other objects, such as birds or airplanes. In addition, drones can reach very high speeds, so detection should be done in real time. This paper addresses the problem of real-time drone detection with high accuracy. We divided the drone detection task into two separate tasks: the detection of moving objects and the classification of the detected object into drone, bird, and background. The moving object detection is based on background subtraction, while classification is performed using a convolutional neural network (CNN). The experimental results showed that the proposed approach can achieve an accuracy comparable to existing approaches at high processing speed. We also concluded that the main limitation of our detector is the dependence of its performance on the presence of a moving background. [ABSTRACT FROM AUTHOR]

Smoke detection technology based on computer vision is a popular research direction in fire detection. This technology is widely used in outdoor fire detection fields (e.g., forest fire detection). Smoke detection is often based on features such as color, shape, texture, and motion to distinguish between smoke and non-smoke objects. However, the salience and robustness of these features are insufficiently strong, resulting in low smoke detection performance under complex environment. Deep learning technology has improved smoke detection performance to a certain degree, but extracting smoke detail features is difficult when the number of network layers is small. With no effective use of smoke motion characteristics, indicators such as false alarm rate are high in video smoke detection. To enhance the detection performance of smoke objects in videos, this paper proposes a concept of change-cumulative image by converting the YUV color space of multi-frame video images into a change-cumulative image, which can represent the motion and color-change characteristics of smoke. Then, a fusion deep network is designed, which increases the depth of the VGG16 network by arranging two convolutional layers after each of its convolutional layer. The VGG16 and Resnet50 (Deep residual network) network models are also arranged using the fusion deep network to improve feature expression ability while increasing the depth of the whole network. Doing so can help extract additional discriminating characteristics of smoke. Experimental results show that by using the change-cumulative image as the input image of the deep network model, smoke detection performance is superior to the classic RGB input image; the smoke detection performance of the fusion deep network model is better than that of the single VGG16 and Resnet50 network models; the smoke detection accuracy, false positive rate, and false alarm rate of this method are better than those of the current popular methods of video smoke detection. [ABSTRACT FROM AUTHOR]