Improved Road Target Detection Algorithm for YOLOv7-Tiny

Shuyan Chen; Dongmei Ma; Xiaoyun Luo

doi:10.54097/fryn6w30

Authors

Shuyan Chen
Dongmei Ma
Xiaoyun Luo

DOI:

https://doi.org/10.54097/fryn6w30

Keywords:

Road target detection, YOLOv7-Tiny, H-swish, Darknetblock, Pcconv, Multi-source dataset

Abstract

In complex road scenes, we propose an enhanced road target detection algorithm for YOLOv7-Tiny to address issues such as large model size, misclassification, and low localization accuracy. Our approach involves several key modifi-cations. Firstly, we replace the LeakyReLU activation function in YOLOv7-Tiny with H-swish. This replacement not only reduces the number of parameters in the model but also enhances its feature extraction capabilities. Additionally, we replace the ELAN module in the Neck with the DPCH-ELAN module and introduce the darknetblock module along with the pcconv convolution. These modifications improve the network's ability to comprehend complex patterns and semantics, thereby enabling it to capture features at different levels of input data. Moreover, we introduce the pcconv convolution building block at the output side to handle heterogeneous information in complex road scenes, thereby enhancing the network's performance in detecting road targets and abnormalities. In our experiments using a mul-ti-source dataset, the improved model exhibits a reduction in GFLOPs by 20.90% and a decrease in the number of pa-rameters by 24.49%. Furthermore, the mean average precision scores (map) at thresholds of 0.5 and 0.5~0.9 are im-proved to 77.3% and 51.8%, respectively, compared to the original YOLOv7-Tiny model. These experimental results demonstrate that our enhanced model achieves a reduction in model size while simultaneously enhancing detection accuracy, thereby meeting the requirements for real-time detection. To assess the generalizability of our approach, we conducted comparison experiments on the VOC2012 dataset. The results indicate that the improved algorithm exhibits robust generalization capabilities across different datasets.

References

[1] YUAN Lei, TANG Hai, CHEN Yanrong et al. Improvement of YOLOv5 for road target detection in complex environments[J]. Computer Engineering and Applications, 2023, 59(16): 212-222.

[2] Zhu Youwei. Research on fast road target detection algorithm based on YOLO [D]. Yunnan University, 2022. doi:10.27456/d.cnki.gyndu.2022.002492.

[3] Fan Zhihan. Research and application of road target detection based on YOLO [D]. Sichuan University, 2021. DOI:10.27342/d.cnki.gscdu.2021.000109

[4] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.

[5] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

[6] Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.

[7] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, June 26-July 1, 2016, Las Vegas, NV, USA. New York: IEEE, 2016: 779-788.

[8] Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263 -7271.

[9] Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.

[10] Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:2004.10934, 2020.

[11] Li C, Li L, Jiang H, et al. YOLOv6: A single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:2209.02976, 2022.

[12] Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//Computer Vision-ECCV 2016: 14th European Conference, Amsterdam , The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.

[13] Tan M, Pang R, Le Q V. Efficientdet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790.

[14] Qiu M, Huang L, Tang B H. ASFF-YOLOv5: Multielement detection method for road traffic in UAV images based on multiscale feature fusion[J]. Remote Sensing, 2022, 14(14): 3498.

[15] Jiang T, Li C, Yang M, et al. An improved YOLOv5s algorithm for object detection with an attention mechanism[J]. Electronics, 2022, 11(16): 2494.

[16] Wang C Y, Liao H Y M, Yeh I H. Designing network design strategies through gradient path analysis[J]. arXiv preprint arXiv:2211.04800, 2022.

[17] Qi Linglong, Gao Jiantai. Small target detection based on improved YOLOv7[J/OL]. (2022-12-08).

[18] QI Xiangming, DONG Xu. Improved Yolov7-tiny algorithm for steel surface defect detection[J]. Computer Engineering and Applications, 2023, 59(12): 176-183.

[19] LIU Haohan, FAN Yiming, HE Huaiqing et al. A lightweight model for target detection with improved YOLOv7-tiny[J]. Computer Engineering and Applications, 2023, 59(14): 166-175.

[20] ZHAO Min, YANG Guoliang, WANG Jixiang et al. Improved real-time helmet detection algorithm for YOLOv7-tiny[J]. Radio Engineering, 2023, 53(08): 1741-1749.

[21] Li C, Li L, Jiang H, et al. YOLOv6: A single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:2209.02976, 2022.

[22] Ge Z, Liu S, Wang F, et al. Yolox: Exceeding yolo series in 2021[J]. arXiv preprint arXiv:2107.08430, 2021.

[23] Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314- 1324.

[24] Lyon M, Armitage P, Álvarez M A. Spatio-Angular Convolutions for Super-resolution in Diffusion MRI[J]. arXiv preprint arXiv:2306.00854, 2023.

[25] Li B, Pan E, Kang Z. PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering[J]. arXiv preprint arXiv:2312.14438, 2023.