CenterNet-Elite: A Small Object Detection Model for Driving Scenario
With the rapid development of deep learning networks, the accuracy of generic object detection has consistently improved. Nonetheless, small object detection tasks still face a range of challenges. On one hand, the limited pixel size of small objects severely constrains their visual features in imag...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10849529/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576761975537664 |
|---|---|
| author | Lingling Wang Xiang Li Xiaoyan Chen Bin Zhou |
| author_facet | Lingling Wang Xiang Li Xiaoyan Chen Bin Zhou |
| author_sort | Lingling Wang |
| collection | DOAJ |
| description | With the rapid development of deep learning networks, the accuracy of generic object detection has consistently improved. Nonetheless, small object detection tasks still face a range of challenges. On one hand, the limited pixel size of small objects severely constrains their visual features in images, making them susceptible to distortion and difficult to distinguish from background noise. On the other hand, small objects often appear in complex scenarios with severe occlusion and dense arrangement, further increasing the complexity and difficulty of small object detection tasks. In this context, this study proposes a new model, CenterNet-Elite, to overcome these challenges. To address the issue of feature information loss resulting from multiple downsamplings during feature extraction for small objects, we introduce the spatial and channel reconstruction convolution (SCConv) into the bottleneck to reduce spatial and channel redundancy and enhance feature representation. In the meantime, we construct multiple short connections to integrate feature maps of the same scale during the downsampling and upsampling stages, thereby retaining critical shallow spatial information. We introduce a multi-scale pooling module, SPPCSPC, to address the challenge of significant variations in object scale. This module obtains receptive fields of different sizes through max-pooling layers of diverse sizes, adapting to changes in object scale on the feature maps. Furthermore, we introduce the content-aware reassembly of features (CARAFE) to replace deconvolution, refining the upsampling process to enhance the quality of feature maps. A series of comparative experiments and ablation studies demonstrate the effectiveness of our method in small object detection. The CenterNet-Elite achieves a 2.3% increase in the average precision on the large-scale small object detection dataset (SODA-D). |
| format | Article |
| id | doaj-art-6d2d644e1c874b1e834a1bf976a2f066 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6d2d644e1c874b1e834a1bf976a2f0662025-01-31T00:01:55ZengIEEEIEEE Access2169-35362025-01-0113178681787710.1109/ACCESS.2025.353278610849529CenterNet-Elite: A Small Object Detection Model for Driving ScenarioLingling Wang0Xiang Li1https://orcid.org/0000-0002-5555-0734Xiaoyan Chen2Bin Zhou3School of Artificial Intelligence, Hubei Science and Technology College, Wuhan, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaSchool of Artificial Intelligence, Hubei Science and Technology College, Wuhan, ChinaSchool of Artificial Intelligence, Hubei Science and Technology College, Wuhan, ChinaWith the rapid development of deep learning networks, the accuracy of generic object detection has consistently improved. Nonetheless, small object detection tasks still face a range of challenges. On one hand, the limited pixel size of small objects severely constrains their visual features in images, making them susceptible to distortion and difficult to distinguish from background noise. On the other hand, small objects often appear in complex scenarios with severe occlusion and dense arrangement, further increasing the complexity and difficulty of small object detection tasks. In this context, this study proposes a new model, CenterNet-Elite, to overcome these challenges. To address the issue of feature information loss resulting from multiple downsamplings during feature extraction for small objects, we introduce the spatial and channel reconstruction convolution (SCConv) into the bottleneck to reduce spatial and channel redundancy and enhance feature representation. In the meantime, we construct multiple short connections to integrate feature maps of the same scale during the downsampling and upsampling stages, thereby retaining critical shallow spatial information. We introduce a multi-scale pooling module, SPPCSPC, to address the challenge of significant variations in object scale. This module obtains receptive fields of different sizes through max-pooling layers of diverse sizes, adapting to changes in object scale on the feature maps. Furthermore, we introduce the content-aware reassembly of features (CARAFE) to replace deconvolution, refining the upsampling process to enhance the quality of feature maps. A series of comparative experiments and ablation studies demonstrate the effectiveness of our method in small object detection. The CenterNet-Elite achieves a 2.3% increase in the average precision on the large-scale small object detection dataset (SODA-D).https://ieeexplore.ieee.org/document/10849529/CARAFEobject detectionSCConvSPPCSPCSODA dataset |
| spellingShingle | Lingling Wang Xiang Li Xiaoyan Chen Bin Zhou CenterNet-Elite: A Small Object Detection Model for Driving Scenario IEEE Access CARAFE object detection SCConv SPPCSPC SODA dataset |
| title | CenterNet-Elite: A Small Object Detection Model for Driving Scenario |
| title_full | CenterNet-Elite: A Small Object Detection Model for Driving Scenario |
| title_fullStr | CenterNet-Elite: A Small Object Detection Model for Driving Scenario |
| title_full_unstemmed | CenterNet-Elite: A Small Object Detection Model for Driving Scenario |
| title_short | CenterNet-Elite: A Small Object Detection Model for Driving Scenario |
| title_sort | centernet elite a small object detection model for driving scenario |
| topic | CARAFE object detection SCConv SPPCSPC SODA dataset |
| url | https://ieeexplore.ieee.org/document/10849529/ |
| work_keys_str_mv | AT linglingwang centerneteliteasmallobjectdetectionmodelfordrivingscenario AT xiangli centerneteliteasmallobjectdetectionmodelfordrivingscenario AT xiaoyanchen centerneteliteasmallobjectdetectionmodelfordrivingscenario AT binzhou centerneteliteasmallobjectdetectionmodelfordrivingscenario |