Improving the Yolov5 Detection Accuracy Through Enhancing The K-means Algorithm
DOI:
https://doi.org/10.54097/ajst.v7i3.13263Keywords:
Yolov5, Automatic driving, K-means model.Abstract
As technology advances, various cutting-edge innovations have brought greater convenience to human life. One such influential advancement is autonomous driving technology, which revolutionizes the automotive industry. By harnessing image recognition techniques, autonomous vehicles now possess unprecedented perception and environmental interpretation capabilities. However, over time, the proliferation of autonomous driving has given rise to several challenges. The increasing traffic volume, complex road conditions, intersecting pedestrian pathways, and an array of traffic signs have intensified the issues that autonomous driving technology must address. Consequently, a growing number of individuals have also become actively engaged in the pursuit of enhancing autonomous driving technology.
Downloads
References
ZEILER M D, FERGUS R. (2014) Visualizing and understanding convolutional networks. In: European Conference on Computer Vision. Berlin. 818-833.
TAN M, LE Q V. (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning. Long Beach. 10691-10700.
RAJENDRAN S P, SHINE L, PRADEEP R, et al. (2019) Fast and accurate traffic sign recognition for self driving cars using retinanet based detector. In: 4th International Conference on Communication and Electronics Systems. Piscataway. 784-790.
TRAN A C, DIEN D L, HUYNH H X, et al. (2019) A model for real-time traffic signs recognition based on the yolo algorithm–a case study using vietnamese traffic signs. In: 6th International Conference on Future Data and Security Engineering. Berlin. 104-116.
KHAN J A, YEO D, SHIN H. (2018) New dark area sensitive tone mapping for deep learning based traffic sign recognition. Sensors, 18(11):1-13.
Li Menghao, and Yuan Sanan. (2023) Improved traffic sign detection algorithm of YOLOv5s. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 13.
