Author(s)

Xude Zhang ¹

Affiliation(s)

¹ Micro-nano and Intelligent Manufacturing Engineering Research Centre of Ministry of Education, Kaili University, Kaili, China

Corresponding Author

Xude Zhang

ABSTRACT

The detection of traffic signs is an important part of the research on automatic driving. Road traffic signs occupy the edge of the image, the image is small, and the detection accuracy is low. The improved YOLOv4 target detection algorithm is used to detect road traffic signs. The original activation function is modified to the h-swish activation function. The input image is convolved by 1x1 to obtain the image feature concentration. The main feature extraction network adds depth separable convolution and residual edge parts, and introduces attention mechanism to enhance the feature extraction performance. The road sign prior frame is regenerated using K-means clustering algorithm, The clustering algorithm can achieve network convergence. After the test, it is shown that by training and evaluating the CCTSDB dataset, [email protected] 83.47%, 2.78% higher than the original YOLOv4; The parameter quantity of the network model is 45.60M, which is 18.5% of the size of the original YOLOv4 model. The network becomes lightweight, and the target detection of road signs can be well achieved through testing.

KEYWORDS

Target detection, Depth separable convolution, Attention mechanism

CITE THIS PAPER

Xude Zhang, Road sign detection algorithm based on improved YOLOV4. Journal of Electronics and Information Science (2024) Vol. 9: 116-123. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2024.090316.

REFERENCES

[1] Pan Huiping, Wang Minqin, Zhang Fuquan. Traffic sign detection and recognition method based on optimized YOLO-V4 [J]. Computer Science 2022, 49(11): 179-184.
[2] Wang Jingyi, Liu Shuhui. Traffic Sign Recognition Method Based on Improved YOLOv4 [J]. Electronic Design Engineering 2022, 30(18): 184-188.
[3] Shen Zhi, Xu Li, Fu Xiangyuan. Traffic sign detection based on improved YOLO v4 light blur scene [J]. Computers and Modernization 2022, (07): 27-32
[4] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[5] GIRSHICK R, DONHUE, 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.
[6] JOSEPH REDMON, SANTOSH DIVVALA, ROSS GIRSHICK, ALI FARHADI. You Only Look Once: Unified, Real-Time Object Detection. [C]Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779-788.
[7] WEI LIU, DRAGOMIR ANGUELOV, DUMITRU ERHAN, CHRISTIAN SZEGEDY, SCOTT REED, CHENGYANG FU, ALEXANDER SSD: Single Shot MultiBox Detector [C], ECCV 2016: Computer Vision-ECCV 2016 pp 21-37.
[8] CHIEN-YAO WANG, HONG-YUAN MARK LIAO, I-HAU YEH, YUEN-HUA WU, PING-YANG CHEN, JUN-WEI HSIEH. CSPNet: A New Backbone That Can Enhance Learning Capability of CNN, [C].Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.
[9] Gezgin H , Alkan R M .Traffic sign detection and recognition based on MMS data using YOLOv4-Tiny algorithm[J].Neural Computing and Applications, 2024, 36(33):20633-20651.DOI:10.1007/s00521-024-10279-y.
[10] JOSEPH REDMON, ALI FARHADI.YOLOv3: An Incremental Improvement. [C].Computer Vision and Pattern Recognition, 2018.
[11] KAIMING HE, XIANGYU ZHANG, SHAOQING REN.Deep Residual Learning for Image Recognition. [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.770-778.
[12] KAI HAN, YUNHE WANG, QI TIAN, JIANYUAN GUO, CHUNJING XU, CHANG XU. GhostNet: More Features from Cheap Operations, [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.1580-1589.
[13] Yin Songlin, Tan Fei, Zhou Qing, Xianyang. Traffic Sign Detection Based on Improved YOLOv4 Model [J]. Radio Engineering, 2022, 2022, 52 (11): 2087-2093.
[14] Wang Zehua, Song Weihu, Wu Jianhua A Lightweight Traffic Sign Detection Model Based on Improved YOLOv4 Network [J] Computer Knowledge and Technology, 2022,18 (05): 98-101+104. 
[15] JIANMING ZHANG, ZHIPENG XIE, JUAN SUN, XINZOU, JIN WANG. A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection[C]. IEEE Access, 2020, vol.8, pp.29742-29754.

Sponsors, Associates, and Links

---

• Information Systems and Signal Processing Journal
  
  
• Intelligent Robots and Systems
  
  
• Journal of Image, Video and Signals
  
  
• Transactions on Real-Time and Embedded Systems
  
  
• Journal of Electromagnetic Interference and Compatibility
  
  
• Acoustics, Speech and Signal Processing
  
  
• Journal of Power Electronics, Machines and Drives
  
  
• Journal of Electro Optics and Lasers
  
  
• Journal of Integrated Circuits Design and Test
  
  
• Journal of Ultrasonics
  
  
• Antennas and Propagation
  
  
• Optical Communications
  
  
• Solid-State Circuits and Systems-on-a-Chip
  
  
• Field-Programmable Gate Arrays
  
  
• Vehicular Electronics and Safety
  
  
• Optical Fiber Sensor and Communication
  
  
• Journal of Low Power Electronics and Design
  
  
• Infrared and Millimeter Wave
  
  
• Detection Technology and Automation Equipment
  
  
• Journal of Radio and Wireless
  
  
• Journal of Microwave and Terahertz Engineering
  
  
• Journal of Communication, Control and Computing
  
  
• International Journal of Surveying and Mapping
  
  
• Information Retrieval, Systems and Services
  
  
• Journal of Biometrics, Identity and Security
  
  
• Journal of Avionics, Radar and Sonar