文献类型：期刊文献

英文题名：ALODAD: An Anchor-Free Lightweight Object Detector for Autonomous Driving

作者：Liang, Tianjiao;Bao, Hong;Pan, Weiguo[1];Pan, Feng

第一作者：Liang, Tianjiao

通讯作者：Pan, WG[1]

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

第一机构：北京联合大学机器人学院|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.|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2022

卷号：10

起止页码：40701-40714

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20221611994142);Scopus(收录号：2-s2.0-85128324587);WOS:【SCI-EXPANDED(收录号:WOS:000787928400001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61802019, Grant 61932012, Grant 61871039, Grant 61906017, and Grant 62006020; in part by the Beijing Municipal Education Commission Science and Technology Program under Grant KM201911417003, Grant KM201911417009, and Grant KM201911417001; in part by the Beijing Union University Research and Innovation Projects for Postgraduates under Grant YZ2020K001 and Grant YZ2021K001; and in part by the Premium Funding Project for Academic Human Resources Development, Beijing Union University, under Grant BPHR2020DZ02

语种：英文

外文关键词：Feature extraction; Object detection; Convolution; Autonomous vehicles; Computational modeling; Location awareness; Neural networks; Autonomous driving; deep learning; lightweight; object detection

摘要：Vision-based object detection is an essential component of autonomous driving. Because vehicles typically have limited on-board computing resources, a small-sized detection model is required. Simultaneously, high object detection accuracy and real-time inference detection speeds are required to ensure safety while driving. In this paper, an anchor-free lightweight object detector for autonomous driving called ALODAD is proposed. ALODAD incorporates an attention scheme into the lightweight neural network GhostNet and builds an anchor-free detection framework to achieve lower computational costs and provide parameters with high detection accuracy. Specifically, the lightweight backbone neural network integrates a convolutional block attention model that analyzes the valuable features from traffic scene images to generate an accurate bounding box, and then constructs feature pyramids for multi-scale object detection. The proposed method adds an intersection over union (IoU) branch to the decoupled detector to rank the vast number of candidate detections accurately. To increase the data diversity, data augmentation was used during training. Extensive experiments based on benchmarks demonstrate that the proposed method offers improved performance compared to the baseline. The proposed method can achieve an increased detection accuracy while meeting the real-time requirements of autonomous driving. The proposed method was compared with the YOLOv5 and RetinaNet models and 98.7% and 94.5% were obtained for the average precision metrics AP50 and AP75, respectively, on the BCTSDB dataset.