Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions

Kaizhe Liu

doi:10.47297/wspciWSP2516-252724.20261002

PDF
导出
分享
收藏
专辑

Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions

10卷第2期

浏览量: 0 Downloads: 0

Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions
Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions
School of Economics and Management, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
2026年10卷第2期页码：115-118
纸质出版：2026-04-30
DOI：10.47297/wspciWSP2516-252724.20261002
Accepted：

Scan QR Code

Kaizhe Liu. (2026). Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions. 创意与创新（英文版）, 10(2), 115-118.

Liu Kaizhe.Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions[J].Creativity and Innovation,2026,10(02):115-118.
Kaizhe Liu. (2026). Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions. 创意与创新（英文版）, 10(2), 115-118. DOI： 10.47297/wspciWSP2516-252724.20261002.

Liu Kaizhe.Current Application Status and Prospect of Computer Vision in Real - time Traffic Conditions[J].Creativity and Innovation,2026,10(02):115-118. DOI： 10.47297/wspciWSP2516-252724.20261002.

摘要

Abstract

With the accelerating pace of urbanization and the sharp increase in the number of motor vehicles

traffic congestion and frequent accidents have become the key bottlenecks restricting urban development. Computer vision

a crucial core branch of artificial intelligence

is gradually evolving into a key technological means to solve the above - mentioned problems. This paper refers to the latest relevant academic research results from 2025 to 2026 and comprehensively summarizes the practical applications of computer vision in real - time traffic condition perception

understanding

and decision - making.This article deeply analyzes the technological development in the fields of environmental perception and scene understanding

and focuses on the adaptability of semantic segmentation technology and dynamic feature extraction technology in complex and changeable traffic scenarios under the background of deep learning. In terms of target detection and tracking

it details the relevant situation of lightweight network design and also mentions the important breakthroughs achieved by DeepSORT in improving detection accuracy and real - time performance. In addition

it also conducts corresponding analyses on some specific cases such as driving behavior monitoring.Research shows that the technology is developing towards the direction of "lightweight

high - precision

and multi - modal fusion". However

in complex natural environments

such as in rainy or foggy conditions or low - light situations

combined with the limited computing power of edge computing devices

the robustness and generalization ability of existing algorithms are facing many tests. In the future

with the gradual implementation of large - scale visual model distillation

the continuous maturation of the end - edge - cloud collaborative computing architecture

and the increasing popularization of the vehicle - road collaborative system

computer vision will promote the intelligent transportation system to develop towards a higher level in terms of automation and intelligence.

关键词

Keywords

references

Zhao, S. J., & Yuan, L. H. (2026). The application of computer vision in intelligent vehicle environment perception. Automotive Test Report , (1), 28-30.

Li, J. J. (2025). The application of computer vision in intelligent vehicle environment perception. Automotive Electrical Appliances , (6), 54-56.

Li, Y. S., & Li, S. J. (2026). Optimization of automatic driving environment perception algorithm based on computer vision. Automotive Electrical Appliances , (3), 79-81.

Ma, T. F. (2026). Optimization algorithm for computer vision target detection based on deep learning. Software , 47(1), 49-51.

Wu, M. Y. (2025). Discussion on automatic driving perception module based on computer vision. Automotive Electrical Appliances , (12), 66-68.

Sun, H. H. (2026). Research and application of automatic detection and control technology for driving behavior based on computer vision. Gold , 47(1), 42-46.

Liu, H. L. (2025). Research on automatic parking system of automobile based on computer vision. Automotive Electrical Appliances , (8), 65-67.

Zhao, S. T., & Zhang, Q. (2025). The application of computer vision in automobile collision warning system. Automotive Electrical Appliances , (6), 65-67.

Yang, F. F. (2025). Research on abnormal road surface detection method based on computer vision [Master's thesis]. Chongqing Jiaotong University.

Zhang, S. B. (2025). Research on driving safety protection method based on computer vision [Master's thesis]. Jiangnan University.

Xiang, Q., Zhao, S. J., Zhan, X. C., & Zhu, H. W. (2025). Vehicle collision warning system for meeting on sections with poor visibility based on computer vision. Journal of Southwest University of Science and Technology , 40(3), 108-114.

Li, K. R., Zhou, Y. Y., Sun, R., Chen, J. J., & Han, Y. K. (2025). Design of intelligent tracking vehicle system based on computer vision. Internet of Things Technology , 15(21), 18-21.

Tang, L., & Li, L. P. (2025). Research on environment percep tion and obstacle recognition algorithm of automatic driving vehicle based on computer vision. Volkswagen , (10), 28-30.