Object detection is becoming increasingly significant for autonomous-driving system. However, poor accuracy or low inference performance limits current object detectors in applying to autonomous driving. In this work, a fast and accurate object detector termed as SA-YOLOv3, is proposed by introducing dilated convolution and self-attention module (SAM) into the architecture of YOLOv3. Furthermore, loss function based on GIoU and focal loss is reconstructed to further optimize detection performance. With an input size of $512\times 512$ , our proposed SA-YOLOv3 improves YOLOv3 by 2.58 mAP and 2.63 mAP on KITTI and BDD100K benchmarks, with real-time inference (more than 40 FPS). When compared with other state-of-the-art detectors, it reports better trade-off in terms of detection accuracy and speed, indicating the suitability for autonomous-driving application. To our best knowledge, it is the first method that incorporates YOLOv3 with attention mechanism, and we expect this work would guide for autonomous-driving research in the future.
SA-YOLOv3: An Efficient and Accurate Object Detector Using Self-Attention Mechanism for Autonomous Driving
IEEE Transactions on Intelligent Transportation Systems ; 23 , 5 ; 4099-4110
2022-05-01
5072605 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
A STUDY ON AUTONOMOUS DRIVING ADAPTIVE SIMULATION SYSTEM USING DEEP LEARNING MODEL YOLOV3
BASE | 2021
|A STUDY ON AUTONOMOUS DRIVING ADAPTIVE SIMULATION SYSTEM USING DEEP LEARNING MODEL YOLOV3
BASE | 2021
|Traffic Object Detection and Distance Estimation Using YOLOv3
British Library Conference Proceedings | 2022
|Traffic Object Detection and Distance Estimation Using YOLOv3
SAE Technical Papers | 2022
|Multiple object tracking using a dual-attention network for autonomous driving
IET | 2020
|