Focusing 3D Small Objects with Object Matching Set Abstraction
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/8/4121 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849712309529739264 |
|---|---|
| author | Lei Guo Ningdong Song Jindong Hu Huiyan Han Xie Han Fengguang Xiong |
| author_facet | Lei Guo Ningdong Song Jindong Hu Huiyan Han Xie Han Fengguang Xiong |
| author_sort | Lei Guo |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-c620c333a5dc45b5b2caca2c85a527fa |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-c620c333a5dc45b5b2caca2c85a527fa2025-08-20T03:14:19ZengMDPI AGApplied Sciences2076-34172025-04-01158412110.3390/app15084121Focusing 3D Small Objects with Object Matching Set AbstractionLei Guo0Ningdong Song1Jindong Hu2Huiyan Han3Xie Han4Fengguang Xiong5Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaCurrently, 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.https://www.mdpi.com/2076-3417/15/8/41213D object detectionset abstractionsmall object detectionpoint clouds |
| spellingShingle | Lei Guo Ningdong Song Jindong Hu Huiyan Han Xie Han Fengguang Xiong Focusing 3D Small Objects with Object Matching Set Abstraction Applied Sciences 3D object detection set abstraction small object detection point clouds |
| title | Focusing 3D Small Objects with Object Matching Set Abstraction |
| title_full | Focusing 3D Small Objects with Object Matching Set Abstraction |
| title_fullStr | Focusing 3D Small Objects with Object Matching Set Abstraction |
| title_full_unstemmed | Focusing 3D Small Objects with Object Matching Set Abstraction |
| title_short | Focusing 3D Small Objects with Object Matching Set Abstraction |
| title_sort | focusing 3d small objects with object matching set abstraction |
| topic | 3D object detection set abstraction small object detection point clouds |
| url | https://www.mdpi.com/2076-3417/15/8/4121 |
| work_keys_str_mv | AT leiguo focusing3dsmallobjectswithobjectmatchingsetabstraction AT ningdongsong focusing3dsmallobjectswithobjectmatchingsetabstraction AT jindonghu focusing3dsmallobjectswithobjectmatchingsetabstraction AT huiyanhan focusing3dsmallobjectswithobjectmatchingsetabstraction AT xiehan focusing3dsmallobjectswithobjectmatchingsetabstraction AT fengguangxiong focusing3dsmallobjectswithobjectmatchingsetabstraction |