文献类型：期刊文献

英文题名：AspectNet: Aspect-Aware Anchor-Free Detector for Autonomous Driving

作者：Liang, Tianjiao[1,2];Bao, Hong[1,2];Pan, Weiguo[1,2];Fan, Xinyue[1,2];Li, Han[1,2]

第一作者：Liang, Tianjiao

通讯作者：Pan, WG[1];Pan, WG[2]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]corresponding author), Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2022

卷号：12

期号：12

外文期刊名：APPLIED SCIENCES-BASEL

收录：;Scopus(收录号：2-s2.0-85132309559);WOS:【SCI-EXPANDED(收录号:WOS:000817447400001)】；

基金：This research was funded by the National Natural Science Foundation of China (Nos. 61802019, 61932012, 61871039) and the Beijing Municipal Education Commission Science and Technology Program (Nos. KM201911417003, KM201911417009, KM201911417001). Beijing Union University Research and Innovation Projects for Postgraduates (No. YZ2020K001). By the Premium Funding Project for Academic Human Resources Development in Beijing Union University under Grant BPHR2020DZ02.

语种：英文

外文关键词：anchor free; autonomous driving; deep learning; object detection

摘要：The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in this paper to address this problem. Specifically, it adds an aspect prediction head at the end of the detector, which can learn different distributions of aspect ratios between other objects. The sample definition method is improved to alleviate the problem of positive and negative sample imbalance. A loss function is designed to strengthen the learning weight of the center point of the network. The validation results show that the AP50 and AP75 of the proposed method are 97.3% and 93.4% on BCTSDB, and the average accuracies of the car, pedestrian, and cyclist are 92.7%, 77.4%, and 78.2% on KITTI, respectively. The comparison results demonstrate that the proposed algorithm is better than existing anchor-free methods.