{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T00:49:44Z","timestamp":1701478184560},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643684444","type":"print"},{"value":"9781643684451","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,30]]},"abstract":"<jats:p>With the continuous growth of intelligent driving applications, the accuracy of vehicle target detection is of critical importance. The limitations of a single sensor cannot meet the stringent requirements for vehicle-level detection accuracy at present. Therefore, this research is committed to solving this problem, mainly through the following steps: first, a unified spatiotemporal fusion strategy is adopted, associating the detection results of multiple sensors, while deep preprocessing of point cloud data is performed to ensure high-quality data and improve processing efficiency. In addition, the YOLOv4 algorithm is optimized to improve vehicle detection accuracy in occluded environments. On this basis, this paper proposes a multi-sensor fusion strategy. By setting a lower visual confidence threshold, the omission rate of vehicle targets is reduced. During the correlation matching stage, LIDAR is used to \u201creview\u201d the visual detection results to further enhance the confidence of visual detection results. The fused results are output with a high confidence threshold, significantly improving the detection accuracy of target vehicles. To verify the performance of the target detection system designed in this paper, a real-vehicle verification was conducted in an outdoor road environment. The experimental results show that the detection accuracy of vehicle targets can be effectively improved by an average of about 4.5%.<\/jats:p>","DOI":"10.3233\/faia230886","type":"book-chapter","created":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T15:56:37Z","timestamp":1701446197000},"source":"Crossref","is-referenced-by-count":0,"title":["Vehicle Target Detection Based on LIDAR and Camera Information Fusion"],"prefix":"10.3233","author":[{"given":"Linwen","family":"Geng","sequence":"first","affiliation":[{"name":"Chongqing Research Institute of Changchun University of Science and Technology, Chongqing 400000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongchang","family":"Ding","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Changchun University of Science and Technology, Chongqing 400000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Advances in Artificial Intelligence, Big Data and Algorithms"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA230886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T15:56:40Z","timestamp":1701446200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA230886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"ISBN":["9781643684444","9781643684451"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia230886","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,30]]}}}