거리 기반 적응형 임계값을 활용한 강건한 3차원 물체 탐지
Robust 3D Object Detection through Distance based Adaptive Thresholding
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Ensuring robust 3D object detection is a core challenge for autonomous driving systems operating in urban environments. To tackle this issue, various 3D representation, including point cloud, voxels, and pillars, have been widely adopted, making use of LiDAR, Camera, and Radar sensors. These representations improved 3D object detection performance, but real-world urban scenarios with unexpected situations can still lead to numerous false positives, posing a challenge for robust 3D models. This paper presents a post-processing algorithm that dynamically adjusts object detection thresholds based on the distance from the ego-vehicle. While conventional perception algorithms typically employ a single threshold in post-processing, 3D models perform well in detecting nearby objects but may exhibit suboptimal performance for distant ones. The proposed algorithm tackles this issue by employing adaptive thresholds based on the distance from the ego-vehicle, minimizing false negatives and reducing false positives in the 3D model. The results show performance enhancements in the 3D model across a range of scenarios, encompassing not only typical urban road conditions but also scenarios involving adverse weather conditions.
Abstract
Ensuring robust 3D object detection is a core challenge for autonomous driving systems operating in urban environments. To tackle this issue, various 3D representation, including point cloud, voxels, and pillars, have been widely adopted, making use of LiDAR, Camera, and Radar sensors. These representations improved 3D object detection performance, but real-world urban scenarios with unexpected situations can still lead to numerous false positives, posing a challenge for robust 3D models. This paper presents a post-processing algorithm that dynamically adjusts object detection thresholds based on the distance from the ego-vehicle. While conventional perception algorithms typically employ a single threshold in post-processing, 3D models perform well in detecting nearby objects but may exhibit suboptimal performance for distant ones. The proposed algorithm tackles this issue by employing adaptive thresholds based on the distance from the ego-vehicle, minimizing false negatives and reducing false positives in the 3D model. The results show performance enhancements in the 3D model across a range of scenarios, encompassing not only typical urban road conditions but also scenarios involving adverse weather conditions.
참고문헌 (33)
- K. Zhang, "Moving object detection of assembly components based on improved background subtraction algorithm", IOP Conference Series : Materials Science and Engineering, 1009 (2021)
- S. F. Lin, "Moving object detection from a moving stereo camera via depth information and visual odometry", 2018 IEEE International Conference on Applied System Invention(ICASI), pp.437~440 (2018)
- Y. Zhou, "VoxelNet : End-to-End Learning for Point Cloud Based 3D Object Detection", 2018 IEEE, 2018, 4490~4499
- G. Ross, "Fast r-cnn", IEEE international conference on computer vision(ICCV), pp.1440~1448 (2015)
- Y. Yan, "Second : Sparsely embedded convolutional detection", Sensors, 18(10) (2018)[DOI]
- A. H. Lang, "PointPillars : Fast Encoders for Object Detection From Point Clouds", 2019 IEEE, 2019, 12689~12697
- S. Shi, "PointRCNN : 3D Object Proposal Generation and Detection From Point Cloud", 2019 IEEE, 2019, 770~779
- S. Shi, "PV-RCNN : Point-Voxel Feature Set Abstraction for 3D Object Detection", 2020 IEEE, 2020, 10526~10535
- K. Duan, "CenterNet : Keypoint Triplets for Object Detection", 2019IEEE, 2019, 6568~6577
- H. Kim, "Monocular Camera based Real-Time Object Detection and Distance Estimation Using Deep Learning", The Journal of Korea Robotics Society, 14(4), pp.357~362 (2019)[DOI]
- J. Redmon, "You Only Look Once : Unified, Real-Time Object Detection", 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.779~788 (2016)
- R. Girshick, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.580~587 (2014)
- D. Song, "Development of an Efficient 3D Object Recognition Algorithm for Robotic Grasping in Cluttered Environments", The Journal of Korea Robotics Society, 17(3), pp.255~263 (2022)[DOI]
- T. Wang, "FCOS3D : Fully Convolutional One-Stage Monocular 3D Object Detection", 2021 IEEE, 2021, 913~922
- Z. Tian, "FCOS : Fully Convolutional One-Stage Object Detection", 2019 IEEE, 2019, 9626~9635
- N. Carion, "End-to-end object detection with transformers", European conference on computer vision(ECCV), pp.213~229 (2020)
- Y. Wang, "DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries", 2021 Conference on Robot Learning (CoRL) (2021)
- Y. Liu, "Petr : Position embedding transformation for multi-view 3D object detection", European Conference on Computer Vision, pp.531~548 (2022)
- Z. Chen, "Graph-DETR3D : rethinking overlapping regions for multi-view 3D object detection", The 30th ACM International Conference on Multimedia, pp.5999~6008 (2022)
- X. Chen, "Multi-view 3D Object Detection Network for Autonomous Driving", 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.6526~6534 (2017)
- C. R. Qi, "Frustum PointNets for 3D Object Detection from RGB-D Data", 2018IEEE, 2018, 918~927
- Z. Wang, "Frustum ConvNet : Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection", 2019 IEEE, 2019, 1742~1749
- R. Nabati, "CenterFusion : Center-based Radar and Camera Fusion for 3D Object Detection", 2021 IEEE Winter Conference on Applications of Computer Vision(WACV), pp.1526~1535 (2021)
- X. Chen, "FUTR3D : A Unified Sensor Fusion Framework for 3D Detection", 2023IEEE, 2023, 172~181
- X. Bai, "TransFusion : Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers", 2022 IEEE, 2022, 1080~1089
- Z. Liu, "BEVFusion : Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation", 2023 IEEE International Conference on Robotics and Automation(ICRA), pp.2774~2781 (2023)
- Y. Li, "DeepFusion : Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection", 2022 IEEE, 2022, 17161~17170
- Y. Chen, "Focal Sparse Convolutional Networks for 3D Object Detection", 2022 IEEE, 2022, 5418~5427
- S. Xu, "Fusion Painting : Multimodal Fusion with Adaptive Attention for 3D Object Detection", 2021 IEEE International Intelligent Transportation Systems Conference(ITSC), pp.3047~3054 (2021)
- M. Liang, "Deep continuous fusion for multi-sensor 3D object detection", The European conference on computer vision(ECCV), pp.641~656 (2018)
- W. Liu, "SSD : Single Shot MultiBox Detector", Computer Vision–ECCV 2016 : 14th European Conference, pp.21~37 (2016)
- A. Geiger, "Are we ready for autonomous driving? The KITTI vision benchmark suite", 2012IEEE Conference on Computer Vision and Pattern Recognition, pp.3354~3361 (2012)