국내 주행환경을 고려한 자율주행 라이다 데이터 셋 구축 및 효과적인 3D 객체 검출 모델 설계
Construction of LiDAR Dataset for Autonomous Driving Considering Domestic Environments and Design of Effective 3D Object Detection Model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Recently, with the growing interest in the field of autonomous driving, many researchers have been focusing on developing autonomous driving software platforms. In particular, we have concentrated on developing 3D object detection models that can improve real-time performance. In this paper, we introduce a self-constructed 3D LiDAR dataset specific to domestic environments and propose a VariFocal-based CenterPoint for the 3D object detection model, with improved performance over the previous models. Furthermore, we present experimental results comparing the performance of the 3D object detection modules using our self-built and public dataset. As the results show, our model, which was trained on a large amount of self-constructed dataset, successfully solves the issue of failing to detect large vehicles and small objects such as motorcycles and pedestrians, which the previous models had difficulty detecting. Consequently, the proposed model shows a performance improvement of about 1.0 mAP over the previous model.
Abstract
Recently, with the growing interest in the field of autonomous driving, many researchers have been focusing on developing autonomous driving software platforms. In particular, we have concentrated on developing 3D object detection models that can improve real-time performance. In this paper, we introduce a self-constructed 3D LiDAR dataset specific to domestic environments and propose a VariFocal-based CenterPoint for the 3D object detection model, with improved performance over the previous models. Furthermore, we present experimental results comparing the performance of the 3D object detection modules using our self-built and public dataset. As the results show, our model, which was trained on a large amount of self-constructed dataset, successfully solves the issue of failing to detect large vehicles and small objects such as motorcycles and pedestrians, which the previous models had difficulty detecting. Consequently, the proposed model shows a performance improvement of about 1.0 mAP over the previous model.
참고문헌 (16)
- 이진희, "국내 도로 환경에 특화된 자율주행을 위한 멀티카메라 데이터 셋 구축 및 유효성 검증", 대한임베디드공학회논문지, 17(5), pp.273~280 (2022), 대한임베디드공학회[DOI]
- T. Y. Lin, "Focal Loss for Dense Object Detection", International Conference on Computer Vision (ICCV), pp.2980~2988 (2017)
- Z. Zheng, "Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression", 34nd AAAI Conference on Artificial Intelligence, 34(07) (2020)
- T. Yin, "Center-based 3D Object Detection and Tracking", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.11784~11793 (2021)
- S. Wu, "IoU-aware Single-stage Object Detector for Accurate Localization", Image and Vision Computing, 97, pp.103911~ (2020)
- P. Sun, "Scalability in Perception for Autonomous Driving: Waymo Open Dataset", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2446~2454 (2020)
- A. Patil, "The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes", International Conference on Robotics and Automation (ICRA), pp.9552~9557 (2019)
- Y. Ma, "TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents", 33nd AAAI Conference on Artificial Intelligence, pp.6120~6127 (2019)
- "A3D: Korean Autonomous Driving Dataset"[URL]
- Y. Zhou, "VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4490~4499 (2018)
- W. Zheng, "CIA-SSD:Confident IoU-Aware Single-Stage Object Detector From Point Cloud", 35nd AAAI Conference on Artificial Intelligence, 35(4), pp.3555~3562 (2021)
- Y. Hu, "AFDetV2:Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds", 36nd AAAI Conference on Artificial Intelligence (2022)
- A. H. Lang, "PointPillars: Fast Encoders for Object Detection From Point Clouds", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.12697~12705 (2019)
- G. Shi, "PillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection", European Conference on Computer Vision (ECCV), pp.35~52 (2022)
- X. Zhou, "Objects as Points", ~ (2019)
- H. Zhang, "VarifocalNet: An IoU-aware Dense Object Detector", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.8514~8523 (2021)