Road small target detection based on improved YOLO v5 algorithm

被引：1
作者：
Song, Cunli [1 ]
Chai, Weiqin [1 ]
Zhang, Xuesong [1 ]
机构：
[1] School of Softmare, Dalian Jiaotong University, Dalian
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2024年 / 46卷 / 10期
关键词：
context augmentation module (CAM); deformable convolutional networks (DCN); small target detection; you only look once v5 (YOLO v5);
D O I：
10.12305/j.issn.1001-506X.2024.10.04
中图分类号：
学科分类号：
摘要：
In order to solve the problems that small targets on traffic roads faces including detection difficulty, low precision, detection failures, a multi-scale feature fusion target detection improvement algorithm based on the YOLO v5 (you only look once v5) algorithm is proposed. Firstly, the small target detection head is added for adapting to the small target size and alleviating the missed detection. Then, deformable convolutional networks V2 (DCN V2) is introduced to improve the model's learning ability for small targets in motion. The context augmentation module (CAM) is introduced to improve the recognition ability of small targets at a long distance. The replacement loss function is used to improve the bounding box' s localization accuracy, and the spatial pyramid pooling and context spatial pyramid convolution_group (SPPCSPC_group) module is also used to improve the sensory field and feature expression ability of the network. The experiment results show that the proposed algorithm achieves an average accuracy of 95. 2% in the category of small targets in the KITTI dataset.compared with the original YOLO v5 algorithm, the overall average accuracy is improved by 2. 7%. For the detection of small targets, the average accuracy is improved by 3. 1% with a better detection effect, which proves the effectiveness of the proposed algorithm for the detection of small targets on roads. © 2024 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：3271 / 3278
页数：7
相关论文
共 31 条
[21]  
ZHANG Y, GUO Z Y, WU J Q, Et al., Real-time vehicle detection based on improved YOLO v5, Sustainability, 14, 19, (2022)
[22]  
ZHAO R, LIU H, LIU P L, Et al., Safety hat detection algorithm based on improved YOLOv5s, Journal of Beijing University of Aeronautics and Astronautics, 49, 8, pp. 2050-2061, (2023)
[23]  
LIANG Q K, XIANG S, HU Y C, Et al., PD2SE-Net: computer- assisted plant disease diagnosis and severity estimation net- work, Computers and Electronics in Agriculture, 157, pp. 518-529, (2019)
[24]  
ZHU X Z, HU H, LIN S, Et al., Deformable convnets v2 : more deformable, better results, Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308-9316, (2019)
[25]  
LUO Z X, SHEN T W, ZHOU L, Et al., ContextDesc: local descriptor augmentation with cross-modality context, Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2527-2536, (2019)
[26]  
GEIGER A, LENZ P, STILLER C, Et al., Vision meets robotics: the KITTI dataset, The International Journal of Robotics Research, 32, 11, pp. 1231-1237, (2013)
[27]  
ZHANG S F, CHI C, YAO Y Q, Et al., Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection, Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759-9768, (2020)
[28]  
LIN T Y, DOLLAR P, GIRSHICK R, Et al., Feature pyramid networks for object detection, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117-2125, (2017)
[29]  
LIU S, QI L, QIN H F, Et al., Path aggregation network for instance segmentation, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759-8768, (2018)
[30]  
RAO Y M, ZHAO W L, TANG Y S, Et al., HorNet: efficient high-order spatial interactions with recursive gated convolutions, Advances in Neural Information Processing Systems, 35, pp. 10353-10366, (2022)
1234