Content of Improvement and Application of YOLO in our journal

        Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Lightweight Safety Helmet Detection Method of Improved YOLOX
    LV Zhixuan, WEI Xia, MA Zhigang
    Computer Engineering and Applications    2023, 59 (1): 61-71.   DOI: 10.3778/j.issn.1002-8331.2204-0405
    Abstract130)      PDF(pc) (1424KB)(82)       Save
    Aiming at the problems of poor robustness, low accuracy and long training time caused by few helmet data sets, small detected object targets and large amount of existing detection model parameters in the construction environment, a helmet detection method based on improved YOLOX network is proposed. Firstly, online difficult sample mining(OHEM) is used to find the difficult samples in the dataset, and Mosaic method is used to splice the difficult samples to expand the number of training sets. Then the branch attention module is added to the prediction part of the model, and the network output is divided into two parts. The input module extracts the key information at the spatial level and channel level. Finally, a new cosine annealing algorithm is proposed, which adds warm up at the beginning, reduces the oscillation amplitude of the learning rate curve segment by segment in the process, and reduces the convergence time of the model in training. The experimental results show that compared with the original method, the improved helmet detection method improves the mAP, accuracy and recall of helmet detection by 6.77%, 2.52% and 9.14% respectively.Using the CDWR cosine annealing algorithm in training, the loss value is reduced by 0.5~1.0 in the same period, and the training convergence time is reduced by 50% compared with the original algorithm.
    Reference | Related Articles | Metrics
    Improved YOLOv5s Small Target Smoke and Fire Detection Algorithm
    WANG Yixu, XIAO Xiaoling, WANG Pengfei, XIANG Jiafu
    Computer Engineering and Applications    2023, 59 (1): 72-81.   DOI: 10.3778/j.issn.1002-8331.2207-0087
    Abstract118)      PDF(pc) (1664KB)(67)       Save
    Aiming at the problems of low accuracy in smoke and fire detection and difficulty in small target detection in complex environments, an improved small target smoke, and fire detection algorithm based on YOLOv5s is proposed. Firstly, based on the public datasets, the paper builds 9 981 dissimilar smoke and flame image datasets to solve the limitations of existing datasets and improve the training efficiency and generalization ability of the model. Secondly, it adds a 3-D attention mechanism SimAM to the network, increases the feature extraction ability of the algorithm, and no additional parameters are added. It modifies the Neck structure in the network, changes the three-scale detection to the four-scale detection, and combines the weighted bidirectional feature pyramid network(BiFPN) structure to alter the feature fusion process to improve the detection ability of small targets and feature fusion ability. Finally, some hyperparameters in the network are optimized by genetic algorithm, and the detection ability of the model is further improved. The experimental results show that the average detection accuracy of the improved algorithm is improved by 7.2% compared with the original YOLOv5s algorithm, the detection accuracy of small targets is higher, and the false detection and missed detection are reduced.
    Reference | Related Articles | Metrics
    Improved Traffic Sign Detection Algorithm for YOLOv5
    HU Zhaohua, WANG Ying
    Computer Engineering and Applications    2023, 59 (1): 82-91.   DOI: 10.3778/j.issn.1002-8331.2207-0307
    Abstract143)      PDF(pc) (1654KB)(81)       Save
    Traffic sign detection is an important link in the fields of automatic driving and assisted driving, which is related to driving safety. Aiming at the difficulties of small targets and complex backgrounds in traffic signs, an algorithm based on improved YOLOv5 is proposed. Firstly, a regional context module is proposed, which uses dilated convolutions with various dilation rates to obtain different receptive fields, and then obtains the feature information of the target and its adjacent areas. The information of adjacent areas plays an important role in small objects detection in traffic signs. It can effectively solve the problem of small targets. Secondly, a feature enhancement module is introduced in the backbone part to further improve the feature extraction ability of the backbone, and the attention mechanism is combined with the original C3 module to make the network more focused on small target information and avoid complex backgrounds. Finally, in the multiscale detection part, the feature fusion of the shallow feature layer and the deep detection layer can take into account both the shallow position information and the deep semantic information, increase the target positioning accuracy and boundary regression, and is more conducive to small target detection. The experimental results show that the improved algorithm achieves 87.2% small target detection precision, 92.4% small target recall and 91.8% mAP on the traffic sign detection data set TT100K, which is improved by 3.5, 4.1 and 2.6 percentage points respectively compared with the original YOLOv5 algorithm, detection speed 83.3?frame/s. On the CCTSDB dataset, mAP is 98.0%, increases 2.0 percentage points, and the detection speed is 90.9?frame/s. Therefore, the proposed improved YOLOv5 algorithm can effectively improve the traffic signs detection precision and recall, and the detection speed is comparable.
    Reference | Related Articles | Metrics
    Lightweight Research of YOLOv5 Target Detection
    HE Yu, TIAN Junwei, ZHANG Zhen, WANG Qin, ZHAO Peng
    Computer Engineering and Applications    2023, 59 (1): 92-99.   DOI: 10.3778/j.issn.1002-8331.2206-0231
    Abstract114)      PDF(pc) (906KB)(58)       Save
    The existing target detection algorithms usually have problems such as large size and complex structure, which leads to poor recognition speed and accuracy in the process of indoor robot operation. To solve this problem, based on indoor target detection, a lightweight detection method of improved YOLOv5s is proposed. This method mainly introduces the ShuffleNet v2 feature extraction mechanism based on the YOLOv5s network to realize the lightweight of the network. At the same time, the weighted bidirectional feature pyramid BiFPN and the frame regression loss EIOU are used to obtain the feature map with richer feature information to improve the accuracy of target detection, so as to obtain a new indoor target detection model. The experimental results show that the parameters of the improved model are significantly reduced, the complexity of the model is reduced by 46%, and the average accuracy rate is increased to 63.9%. The balance between lightweight and detection accuracy is achieved, which provides a reference for target lightweight research.
    Reference | Related Articles | Metrics
    Improved Small Target Detection Method of Bearing Defects in YOLOX Network
    LI Yadong, MA Xing, MU Chunyang, LI Jiandong
    Computer Engineering and Applications    2023, 59 (1): 100-107.   DOI: 10.3778/j.issn.1002-8331.2206-0100
    Abstract103)      PDF(pc) (1007KB)(60)       Save
    Aiming at the problems of high miss detection rate of small targets and insufficient model feature fusion in multi-target case of deep learning model in industrial bearing surface defect detection, a small target defect detection algorithm based on multi-attention feature weighted fusion is proposed based on YOLOX. In the backbone network, a more fine-grained Res2Block module for feature extraction is introduced, and a self-attention mechanism is embedded to increase the regional features of hidden small targets and reduce the missed detection rate. It designs a two-way Pyramid feature fusion network with embedded coordinate attention as a weighting condition to improve the interactive fusion ability of shallow detail features and deep high-level semantic features. In the post-processing stage, the Focal Loss function is introduced to increase the learning of the model on the target of positive samples and further reduce the missed detection rate. The experimental results show that compared with the original YOLOX algorithm, the improved algorithm improves the mAP by 4.04 percentage points on the self-made small train bearing surface defect dataset, which significantly improves the recognition rate of dense small targets.
    Reference | Related Articles | Metrics
    Improving UAV Object Detection Algorithm for YOLOv5s
    SONG Puyi, CHEN Hong, GOU Haobo
    Computer Engineering and Applications    2023, 59 (1): 108-116.   DOI: 10.3778/j.issn.1002-8331.2205-0200
    Abstract125)      PDF(pc) (1276KB)(66)       Save
    In the field of intelligence, reconnaissance and surveillance, automatic target detection can provide accurate target location and category for reconnaissance and other tasks, and provide detailed target information for ground commanders. Based on the complex background, high resolution and target scale difference of UAV images, a modified YOLOv5s object detection algorithm is proposed. Firstly, the compression-excitation module is introduced into the YOLOv5s algorithm to improve the feature extraction ability of the network. Secondly, the double-cone feature fusion(bifrustum feature fusion, BFF) structure is introduced to improve the detection accuracy of the algorithm for smaller targets. Finally, CIoU Loss replaces GIoU Loss as the loss function of the algorithm to improve the positioning accuracy of improving the bounding box regression rate. The experimental results show that the improved YOLOv5s achieves an average mean accuracy(mAP) of 86.3%, 16.8 percentage points higher compared to the original algorithm YOLOv5s, and can still significantly improve the UAV image target detection performance in a complex background.
    Reference | Related Articles | Metrics
    Research on Road Target Detection Algorithm Based on YOLOv5
    WANG Peng, WANG Yulin, JIAO Bowen, WANG Hongchang, YU Yixuan
    Computer Engineering and Applications    2023, 59 (1): 117-125.   DOI: 10.3778/j.issn.1002-8331.2206-0316
    Abstract117)      PDF(pc) (1096KB)(81)       Save
    In order to improve the accuracy of road target detection, based on the YOLOv5 network model, this paper introduces a bottom-up PANet network structure to enhance feature fusion, adopts a target attention mechanism with direction awareness and location information to enhance the perception of the target position, and a YOLO detection head is added to enhance the learning ability of small targets. The improved CIOU(ICIOU) target regression loss function is adopted, the learning ability of the entire model for image features and the target detection accuracy are significantly improved. Experimental results show that the mAP of this model under the Huawei SODA10M dataset has reached 68.2%, which is 15.4 percentage points higher than the original YOLOv5 network mAP, and the detection accuracy has been significantly improved. On this basis, the paper explores the influence of image size on detection time and accuracy. The results show that appropriately increasing the image input size can significantly improve mAP(3.8?percentage points) on the premise that the detection speed is not significantly reduced(23.3 percentage points).
    Reference | Related Articles | Metrics