Boundary and Position Information Mining for Aerial Small Object Detection
This work addresses the problem of small object detection in UAV applications, which is crucial for aerial photography and recognition tasks, but it appears incremental as it builds on existing methods like Yolov5-P2 with specific enhancements.
The paper tackles the challenge of detecting small objects in aerial images by proposing a Boundary and Position Information Mining (BPIM) framework, which integrates boundary, position, and scale information using attention mechanisms and cross-scale feature fusion, resulting in improved performance on datasets like VisDrone2021, DOTA1.0, and WiderPerson compared to baseline methods.
Unmanned Aerial Vehicle (UAV) applications have become increasingly prevalent in aerial photography and object recognition. However, there are major challenges to accurately capturing small targets in object detection due to the imbalanced scale and the blurred edges. To address these issues, boundary and position information mining (BPIM) framework is proposed for capturing object edge and location cues. The proposed BPIM includes position information guidance (PIG) module for obtaining location information, boundary information guidance (BIG) module for extracting object edge, cross scale fusion (CSF) module for gradually assembling the shallow layer image feature, three feature fusion (TFF) module for progressively combining position and boundary information, and adaptive weight fusion (AWF) module for flexibly merging the deep layer semantic feature. Therefore, BPIM can integrate boundary, position, and scale information in image for small object detection using attention mechanisms and cross-scale feature fusion strategies. Furthermore, BPIM not only improves the discrimination of the contextual feature by adaptive weight fusion with boundary, but also enhances small object perceptions by cross-scale position fusion. On the VisDrone2021, DOTA1.0, and WiderPerson datasets, experimental results show the better performances of BPIM compared to the baseline Yolov5-P2, and obtains the promising performance in the state-of-the-art methods with comparable computation load.