Bibliometric analysis of the application of computer vision in intelligent driving: based on Web of Science core collection data

This article is based on the Web of Science core collection database of 8927 articles from 2015 to 2024, and uses bibliometric and knowledge graph analysis to explore the research progress and development of computer vision in the field of intelligent driving. Through the InCites platform and Citespace tool, analyze from dimensions such as publication trends, national/regional influence, institutional contributions, and research hotspots. Research shows that from 2015 to 2024, the number of published papers on computer vision in the field of intelligent driving worldwide has shown a significant growth trend, with China leading with 2993 papers. However, the number and proportion of international papers are relatively small, and international cooperation needs to be strengthened. The University of California system has the highest average citation frequency per article with 6554 citations. The hot research topics focus on environmental perception and object detection, multi-sensor fusion, and deep learning driven visual task models. The technological evolution presents a phased feature of "basic algorithms to multimodal fusion to lightweight and intelligent". Future research needs to strengthen low-power real-time computing, small sample learning, and collaborative perception to promote the maturity of intelligent driving technology and commercial applications.