Content of Special Issue on YOLO Improvements and Applications in our journal

Published in last 1 year |  In last 2 years |  In last 3 years |  All Please wait a minute... For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails Select Improved YOLOv7-tiny Lightweight Infrared Vehicle Target Detection Algorithm XU Xiaoyang, GAO Chongyang Computer Engineering and Applications    2024, 60 (1): 74-83.   DOI: 10.3778/j.issn.1002-8331.2305-0312 Abstract （140）      PDF（pc） （655KB）（167）       Knowledge map    Save In order to solve the problems of large number of parameters and computation, low recognition accuracy, and difficult small target detection in infrared scene, a lightweight infrared vehicle target detection algorithm with improved YOLOv7-tiny is proposed: KD-YOLO-DW. Firstly, the ELAN-DW module is proposed by merging deep separable convolution, which greatly reduces the number of network parameters and the amount of computation. Secondly, by introducing GhostNet V2 module in the feature fusion layer, the fusion ability of different scale features is improved. The WIoU loss function of dynamic non-monotone FM is used to solve the problem of imbalanced samples in the infrared data set, and the detection ability of the lightweight algorithm is improved. Then, a cross-scale fusion strategy is proposed in combination with residual idea, which improves the detection effect of lightweight algorithm on different scale targets and reduces the missing rate of small targets. Finally, the lightweight model is reconcentrated by knowledge distillation, which further improves the accuracy of the model for detecting infrared targets. The experimental results show that compared with the YOLOv7-tiny model, KD-YOLO-DW model has 24.6% and 16.7% fewer parameters and 16.7% less computation, the model size is only 9.2 MB, and mAP is increased by 3.27 and 3.15 percentage points, respectively, with smaller model volume and better detection effect. Reference | Related Articles | Metrics Select Improved YOLOv5 Photovoltaic Module Thermal Spot and Occlusion Small Target Detection LIN Zhengwen, SONG Siyu, FAN Junwei, ZHAO Wei, LIU Guangchen Computer Engineering and Applications    2024, 60 (1): 84-95.   DOI: 10.3778/j.issn.1002-8331.2302-0061 Abstract （96）      PDF（pc） （1429KB）（79）       Knowledge map    Save Hot spots will seriously affect the power generation efficiency of photovoltaic modules, infrared image detection of hot spots is difficult to realize effective recognition of small foreign matters such as leaves and bird droppings, discovering and cleaning foreign matters timely can effectively reduce the hot spots caused by continuous covering. In order to realize more comprehensive recognition and treatment of hot spots, based on the image size of UAV inspection visible and infrared video and the characteristics of detection task, YOLOv5’s anchor frame setting scheme is improved by combining K-means++ algorithm and IoU index, the randomness of results has been improved. In the visible scene, aiming at the problem that small occluded objects make detection difficult, the small occluded objects detection model (CA-YOLOv5s6) is designed by embedding coordinate attention (CA) in YOLOv5s6’s backbone. In the infrared scene, the hot spot area is obvious in infrared image, the lightweight network YOLOv5n is selected as its detection model. The experimental results show that, compared with YOLOv5s6, the mAP of CA-YOLOv5s6 is increased by 2.97 percentage points to 83.78%, and the Parameters are reduced by 4.8×105 to 1.18×107, which effectively improves the detection accuracy of the occlusion small target. The mAP, FPS and Parameters of YOLOv5n are 93.31%, 83.3 and 1.76×106, which can better meet the task requirements of infrared image hot spot detection. Reference | Related Articles | Metrics Select Improved Complex Road Scene Object Detection Algorithm of YOLOv7 DU Juan, CUI Shaohua, JIN Meijuan, RU Chen Computer Engineering and Applications    2024, 60 (1): 96-103.   DOI: 10.3778/j.issn.1002-8331.2306-0021 Abstract （107）      PDF（pc） （556KB）（80）       Knowledge map    Save Although the target detection algorithm based on deep learning has achieved good results in the target detection in the road scene, for the dense targets in the complex road scene, the detection accuracy of distant small-scale targets is low, and the problem of missing detection and false detection is easy to occur. An improved YOLOv7 target detection algorithm in the complex road scene is proposed. It adds small target detection layer, increases the feature learning ability of small target; K-means++ is used to reunite the prior frame, which makes the prior frame fit the target better and increases the positioning accuracy of the target. WIoU (Wise-IoU) loss function is used to increase the attention of the network to the common mass anchor frame and improve the ability of the network to locate the target. CoordConv is introduced into the neck and detection head, so that the network can better sense the position information in the feature map. P-ELAN structure is proposed to reduce the number of algorithm parameters and the amount of computation. The experimental results show that the mAP of the improved algorithm under Huawei SODA10M dataset reaches 64.8%, which is 2.6 percentage points higher than the original algorithm. The number of model parameters and the amount of computation are reduced by 12% and 7% respectively, to achieve the balance of detection accuracy and detection speed. Reference | Related Articles | Metrics Select Lightweight Detection of Helmets and Reflective Clothings: Improved YOLOv5s Algorithm ZHANG Xueli, JIA Xinchun, WANG Meigang, ZHI Hanyu Computer Engineering and Applications    2024, 60 (1): 104-109.   DOI: 10.3778/j.issn.1002-8331.2303-0458 Abstract （70）      PDF（pc） （532KB）（63）       Knowledge map    Save Safety helmet and reflective clothing testing is of great significance to the safety management of production and traffic environment. Aiming at the problems such as large number of parameters, large amount of computation and large model size, an improved detection algorithm based on YOLOv5s is proposed in this paper. Firstly, Ghost module in GhostNet network structure is introduced to replace the original partial convolution and C3 module, which greatly reduces the complexity of the model. Then, CA attention mechanism is added to the backbone network to suppress invalid information and enhance the extraction of feature-rich regions. Finally, the C3 module of neck layer is replaced by C3CBAM, which not only reduces the number of parameters, but also improves the detection accuracy. The experimental results show that the mAP (average accuracy) of the improved model is 93.6%, the number of parameters is 4.28×106, the calculation amount is 9.2 GFLOPs, and the model size is 8.58 MB. Compared with the YOLOv5 model, the number of parameters is reduced by 39%, the amount of calculation is reduced by 41.7%, and the model size is reduced by 37.3%. The detection algorithm not only guarantees the recognition accuracy of the detection, but also realizes the lightweight of the detection algorithm. Reference | Related Articles | Metrics Select Improved YOLOv5s UAV View Small Target Detection Algorithm LIU Tao, GAO Yimeng, CHAI Rui, LI Zhengtong Computer Engineering and Applications    2024, 60 (1): 110-121.   DOI: 10.3778/j.issn.1002-8331.2304-0150 Abstract （86）      PDF（pc） （879KB）（69）       Knowledge map    Save The small target image from the UAV perspective has the characteristics of dense target distribution, unbalanced category and inconspicuous features, which leads to the problem of missed detection and false detection in the target detection task. To solve these problems, an improved YOLOv5s small target detection method is proposed to improve the accuracy and accuracy of target detection. First, it reclusters the anchor box to lock the detection area more accurately. Secondly, the backbone network structure is changed and convolution is added to the spatial pyramid pool layer to ensure that the detection target features are fully obtained. At the same time, the C3 module in the network structure is replaced with a lightweight SEC2f module that fuses the channel attention mechanism to improve the local feature acquisition ability of the network for small target detection. Finally, the features of the target area are extracted effectively by combining the decoupled detection head with the adaptive anchor frame calculation. Under the same parameters and environmental conditions, the detection accuracy on DOTA data set and VisDrone data set is improved by 6.1% and 5.2%, respectively, indicating the effectiveness of the improved method on small target detection tasks. The comparison experiment on voc2007+2012 public data set shows the universality of the improved algorithm. Reference | Related Articles | Metrics Select Research on Improving YOLOv7’s Small Target Detection Algorithm LI Anda, WU Ruiming, LI Xudong Computer Engineering and Applications    2024, 60 (1): 122-134.   DOI: 10.3778/j.issn.1002-8331.2307-0004 Abstract （285）      PDF（pc） （884KB）（166）       Knowledge map    Save With the continuous application of deep learning in domestic object detection, conventional large and medium object detection has made astonishing progress. However, due to the limitations of convolutional networks themselves, there are still issues of missed and false detections in small object detection. Taking dataset Visdrone 2019 and dataset FloW-Img as examples, the YOLOv7 model is studied, and the ELAN module of the backbone network is improved in the network structure. The Focal NeXt block is integrated into the long and short gradient paths of the ELAN module to enhance the feature quality of small targets and improve the contextual information content contained in the output features. The RepLKDeXt module is introduced into the head network, which not only replaces the SPPCSPC module to simplify the overall structure of the model, but also optimizes the ELAN-H structure using multi-channel, large convolutional kernels, and Cat operations. Finally, the SIOU loss function is introduced to replace the CIOU function to improve the robustness of the model. The results show that the improved YOLOv7 model reduces the number of parameters and computational complexity, and its detection performance remains approximately unchanged on the Visdrone 2019 dataset with high small target density. It increases by 9.05 percentage points on the sparse FloW-Img dataset with small targets, further simplifying the model and increasing its applicability. Reference | Related Articles | Metrics