Search

In recent years, highway accidents occur frequently, the main reason is that there is always foreign body invasion on the highway, which makes people unable to respond to emergencies in time. In order to reduce the occurrence of highway incidents, an object detection algorithm for highway intrusion was proposed in this paper. Firstly, a new feature extraction module was proposed to better preserve the main information. Secondly, a new feature fusion method was proposed to improve the accuracy of object detection. Finally, a lightweight method was proposed to reduce the computational complexity. We compare the algorithm in this paper with existing algorithms, the experimental results showed that: On the Visdrone dataset (small size targets), (a) the CS-YOLO was 3.6% more accurate than the YOLO v8. (b) The CS-YOLO was 1.2% more accurate than the YOLO v8 on the Tinypersons dataset (minimal size targets). (c) CS-YOLO was 1.4% more accurate than YOLO v8 on VOC2007 data set (normal size). [ABSTRACT FROM AUTHOR]

As the road traffic situation becomes complex, the task of traffic management takes on an increasingly heavy load. The air-to-ground traffic administration network of drones has become an important tool to promote the high quality of traffic police work in many places. Drones can be used instead of a large number of human beings to perform daily tasks, as: traffic offense detection, daily crowd detection, etc. Drones are aerial operations and shoot small targets. So the detection accuracy of drones is less. To address the problem of low accuracy of Unmanned Aerial Vehicles (UAVs) in detecting small targets, we designed a more suitable algorithm for UAV detection and called GBS-YOLOv5. It was an improvement on the original YOLOv5 model. Firstly, in the default model, there was a problem of serious loss of small target information and insufficient utilization of shallow feature information as the depth of the feature extraction network deepened. We designed the efficient spatio-temporal interaction module to replace the residual network structure in the original network. The role of this module was to increase the network depth for feature extraction. Then, we added the spatial pyramid convolution module on top of YOLOv5. Its function was to mine small target information and act as a detection head for small size targets. Finally, to better preserve the detailed information of small targets in the shallow features, we proposed the shallow bottleneck. And the introduction of recursive gated convolution in the feature fusion section enabled better interaction of higher-order spatial semantic information. The GBS-YOLOv5 algorithm conducted experiments showing that the value of mAP@0.5 was 35.3 % and the mAP@0.5:0.95 was 20.0 % . Compared to the default YOLOv5 algorithm was boosted by 4.0 % and 3.5 % , respectively. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) is widely used for mental stress classification, but effective feature extraction and transfer across subjects remain challenging due to its variability. In this paper, a novel deep neural network combining convolutional neural network (CNN) and adversarial theory, named symmetric deep convolutional adversarial network (SDCAN), is proposed for stress classification based on EEG. The adversarial inference is introduced to automatically capture invariant and discriminative features from raw EEG, which aims to improve the classification accuracy and generalization ability across subjects. Experiments were conducted with 22 human subjects, where each participant’s stress was induced by the Trier Social Stress Test paradigm while EEG was collected. Stress states were then calibrated into four or five stages according to the changing trend of salivary cortisol concentration. The results show that the proposed network achieves improved accuracies of 87.62% and 81.45% on the classification of four and five stages, respectively, compared to conventional CNN methods. Euclidean space data alignment approach (EA) was applied and the improved generalization ability of EA-SDCAN across subjects was also validated via the leave-one-subject-out-cross-validation, with the accuracies of four and five stages being 60.52% and 48.17%, respectively. These findings indicate that the proposed SDCAN network is more feasible and effective for classifying the stages of mental stress based on EEG compared with other conventional methods. [ABSTRACT FROM AUTHOR]

YOLOv3 is a popular and effective object detection algorithm. However, YOLOv3 has a complex network, and floating point operations (FLOPs) and parameter sizes are large. Based on this, the paper designs a new YOLOv3 network and proposes a lightweight object detection algorithm. First, two excellent networks, the Cross Stage Partial Network (CSPNet) and GhostNet, are integrated to design a more efficient residual network, CSP-Ghost-Resnet. Second, combining CSPNet and Darknet53, this paper designs a new backbone network, the ML-Darknet, to realize the gradient diversion of the backbone network. Finally, we design a lightweight multiscale feature extraction network, the PAN-CSP-Network. The newly designed network is named mini and lightweight YOLOv3 (ML-YOLOv3). Based on the helmet dataset, the FLPSs and parameter sizes of ML-YOLOv3 are only 29.7% and 29.4% of those of YOLOv3. Compared with YOLO5, ML-YOLOv3 also exhibits obvious advantages in calculation cost and detection effect. [ABSTRACT FROM AUTHOR]

This paper reprocesses the information of the boundary intelligent contour so as to effectively extract the codes of image contour features. The algorithm based on the coordinates of contour extracted through the level set evolution algorithm is used to obtain several 2D contour matrixes with the same size after repeated conversions. Moreover, the matrixes are diagonally, column-wise and horizontally coded to obtain new coded features. The anti-interference analysis of algorithm indicates that the algorithm of extracting feature code has variable and flexible extraction schemes and high stability. Distinguishable information can be obtained in similar images more easily. In order to prove the validity of the proposed algorithm, feature code exaction algorithm is used to facial expression recognition, and a facial expression recognition model on the basis of facial part contour code exaction is established. According to the experimental results, this facial expression recognition system can eliminate the interference with recognition resulted from the similarity of samples. The comprehensive recognition rate of facial expression is up to 97.20%. [ABSTRACT FROM AUTHOR]

In order to pre-warning the product quality risk of the e-commerce platform, this paper studies the machine learning algorithm for the products quality risk assessment, which propose the Fuzzy C-Means clustering algorithm for the feature extraction and the Cost Sensitive Leaning (CSL)-Naive Bayesian algorithm to construct the assessment model for E-commerce product quality risk form the massive and unbalanced data. The experimental results show that the Machine Learning algorithm based on Spark has better scalability and superiority in the large-scale data environment, which can accurately identify e-commerce product quality risk. [ABSTRACT FROM AUTHOR]

Rich image information is one of the important means through which unmanned surface vehicles effectively and reliably identify targets during autonomous navigation. However, the adaptability of traditional artificial design feature methods in target representation and differentiation remains limited due to the diversity of ship target types, different scales, and complex and dynamic outdoor scenes. This study proposed a ship target recognition method based on single shot multi-box detector (SSD) deep learning. First, training and test sample sets were constructed by acquiring and creating a ship's target image and background image under different types and scenes in an actual river environment. Subsequently, the sample set was used to train and optimize the SSD depth model to achieve adaptive extraction and recognition of target features. Lastly, ship identification experiments with different background environments and foreground targets were performed to test the effectiveness of the proposed method. The support vector machine method based on artificial feature extraction was used for the comparative experiments. Experiment results showed that the SSD-based deep learning method achieved better results than the artificial design feature method in terms of recall and precision rates. [ABSTRACT FROM AUTHOR]

In this paper, we propose a normalized difference vector (NDV) for texture representation. Compared to local-binary-pattern-based descriptors, the proposed NDV takes full advantage of the local difference, and the size can be extended flexibly to cover a large local region. We further employ the bag-of-words model to integrate the local descriptors into a global feature representation of an image. In addition, two strategies are introduced for the proposed NDV to achieve rotation invariance. We test the proposed texture descriptor on benchmark datasets, such as AniTex, VehApp, KTH-TIPS2a, OpenSurface, and Kylberg. Classification results demonstrate the superiority of the proposed descriptor over state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

The goal of room layout estimation is to predict the three-dimensional box that represents the room spatial structure from a monocular image. In this paper, a deconvolution network is trained first to predict the edge map of a room image. Compared to the previous fully convolutional networks, the proposed deconvolution network has a multilayer deconvolution process that can refine the edge map estimate layer by layer. The deconvolution network also has fully connected layers to aggregate the information of every region throughout the entire image. During the layout generation process, an adaptive sampling strategy is introduced based on the obtained high-quality edge maps. Experimental results prove that the learned edge maps are highly reliable and can produce accurate layouts of room images. [ABSTRACT FROM PUBLISHER]

This paper proposes a computationally efficient method for traffic sign recognition (TSR). This proposed method consists of two modules: 1) extraction of histogram of oriented gradient variant (HOGv) feature and 2) a single classifier trained by extreme learning machine (ELM) algorithm. The presented HOGv feature keeps a good balance between redundancy and local details such that it can represent distinctive shapes better. The classifier is a single-hidden-layer feedforward network. Based on ELM algorithm, the connection between input and hidden layers realizes the random feature mapping while only the weights between hidden and output layers are trained. As a result, layer-by-layer tuning is not required. Meanwhile, the norm of output weights is included in the cost function. Therefore, the ELM-based classifier can achieve an optimal and generalized solution for multiclass TSR. Furthermore, it can balance the recognition accuracy and computational cost. Three datasets, including the German TSR benchmark dataset, the Belgium traffic sign classification dataset and the revised mapping and assessing the state of traffic infrastructure (revised MASTIF) dataset, are used to evaluate this proposed method. Experimental results have shown that this proposed method obtains not only high recognition accuracy but also extremely high computational efficiency in both training and recognition processes in these three datasets. [ABSTRACT FROM PUBLISHER]

Bottom-up visual attention is an automatic behavior to guide visual perception to a conspicuous object in a scene. This paper develops a new object-based bottom-up attention (OBA) model for robots. This model includes four modules: Extraction of preattentive features, preattentive segmentation, estimation of space-based saliency, and estimation of proto-object-based saliency. In terms of computation, preattentive segmentation serves as a bridge to connect the space-based saliency and object-based saliency. This paper therefore proposes a preattentive segmentation algorithm, which is able to self-determine the number of proto-objects, has low computational cost, and is robust in a variety of conditions such as noise and spatial transformations. Experimental results have shown that the propsoed OBA model outperforms space-based attention model and other object-based attention methods in terms of accuracy of attentional selection, consistency under a series of noise settings and object completion. [ABSTRACT FROM PUBLISHER]