Focusing 3D Small Objects with Object Matching Set Abstraction
Open Access
- 9 April 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4121
Abstract
Currently, 3D object detection methods fail to detect small objects due to the fewer effective points of small objects. It is a significant challenge to reduce the loss of information of points in representation learning. To this end, we propose an effective 3D detection method with object matching set abstraction (OMSA). We observe that key points are lost during feature learning with multiple set abstraction layers, especially for downsampling and queries. Therefore, we present a novel sampling module named focus-based sampling, which raises the sampling probability of small objects. In addition, we design a multi-scale cube query to match the small objects with a close geometric alignment. Our comprehensive experimental evaluations on the KITTI 3D benchmark demonstrate significant performance improvements in 3D object detection. Notably, the proposed framework exhibits competitive detection accuracy for small objects (pedestrians and cyclists). Through an ablation study, we verify that each module contributes to the performance enhancement and demonstrate the robustness of the method against the balance factor.Keywords
Funding Information
- Natural Science Foundation of Shanxi Province (202203021212138, 202303021211153, 447-110103)
- Foundation of Shanxi Key Laboratory of Machine Vision and Virtual Reality (202203021212138, 202303021211153, 447-110103)
This publication has 40 references indexed in Scilit:
- HIC-YOLOv5: Improved YOLOv5 For Small Object Detection2024
- WS-SSD: Achieving faster 3D object detection for autonomous driving via weighted point cloud samplingExpert Systems with Applications, 2024
- DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defectsExpert Systems with Applications, 2023
- Survey and systematization of 3D object detection models and methodsThe Visual Computer, 2023
- 3D Object Detection for Autonomous Driving: A Comprehensive SurveyInternational Journal of Computer Vision, 2023
- PSA-Det3D: Pillar set abstraction for 3D object detectionPattern Recognition Letters, 2023
- Boosting R-CNN: Reweighting R-CNN samples by RPN’s error for underwater object detectionNeurocomputing, 2023
- PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object DetectionInternational Journal of Computer Vision, 2022
- A full data augmentation pipeline for small object detection based on generative adversarial networksPattern Recognition, 2022
- ASCNet: 3D object detection from point cloud based on adaptive spatial context featuresNeurocomputing, 2022