Small Object Detection Model with Spatial Laplacian Pyramid Attention and Multi-Scale Features Enhancement in Aerial Images

TL;DR

This paper introduces a novel small object detection method for aerial images that combines a Spatial Laplacian Pyramid Attention module, multi-scale feature enhancement, and deformable convolutions, resulting in improved detection accuracy.

Contribution

The paper proposes a new small object detection algorithm integrating SLPA, MSFEM, and deformable convolutions to enhance feature representation and detection performance.

Findings

Outperforms baseline models on VisDrone and DOTA datasets.

Improves small object detection accuracy in aerial images.

Enhances feature alignment and semantic understanding.

Abstract

Detecting objects in aerial images confronts some significant challenges, including small size, dense and non-uniform distribution of objects over high-resolution images, which makes detection inefficient. Thus, in this paper, we proposed a small object detection algorithm based on a Spatial Laplacian Pyramid Attention and Multi-Scale Feature Enhancement in aerial images. Firstly, in order to improve the feature representation of ResNet-50 on small objects, we presented a novel Spatial Laplacian Pyramid Attention (SLPA) module, which is integrated after each stage of ResNet-50 to identify and emphasize important local regions. Secondly, to enhance the model's semantic understanding and features representation, we designed a Multi-Scale Feature Enhancement Module (MSFEM), which is incorporated into the lateral connections of C5 layer for building Feature Pyramid Network (FPN). Finally, the features representation quality of traditional feature pyramid network will be affected because the features are not aligned when the upper and lower layers are fused. In order to handle it, we utilized deformable convolutions to align the features in the fusion processing of the upper and lower levels of the Feature Pyramid Network, which can help enhance the model's ability to detect and recognize small objects. The extensive experimental results on two benchmark datasets: VisDrone and DOTA demonstrate that our improved model performs better for small object detection in aerial images compared to the original algorithm.