CDANet: a small object detection model for unmanned aerial vehicle images based on cross-layer guidance and skip dilated fusion
- 1 November 2024
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (06) , 063011-22
Abstract
Detecting small objects in unmanned aerial vehicle (UAV) pictures is a vital but demanding task in the field of computer vision due to factors such as object size, image degradation, and computational resource limitations. Most existing algorithms improve object detection accuracy by improving feature fusion structures and incorporating single-layer attention modules. However, the weight of single-layer attention is computed only based on the original input, which leads to insufficient exploration of correlations among cross-layer features. To remedy the above issues, we design a novel multi-scale UAV image object detection model called CDANet. First, to fully utilize the scattered detail features in the shallow layers, a cross-layer attention module named the enhanced guided attention module is designed. Second, a simplified depth-wise separable dilated spatial pyramid pooling-fast module is built to overcome the shortcomings of max-pooling operation during feature fusion. Third, an efficient coordinate guidance module is designed as the basic module for guiding the inter-channel information interaction. Fourth, a cross-spatial learning encoder module is designed to encode cross-channel information with an efficient multi-scale attention module. Last, to optimize the learning process by dynamically regulating the attention toward diverse objects, an advanced loss function Wise-IoU v3 is introduced. The results show that, on the VisDrone2021-DET dataset, the average precision and mean average precision of the proposed method are superior to YOLOv8, which are respectively improved by 3.9% and 4.9%.Keywords
This publication has 40 references indexed in Scilit:
- Soft-edge-guided significant coordinate attention network for scene text image super-resolutionThe Visual Computer, 2023
- DMA-YOLO: multi-scale object detection method with attention mechanism for aerial imagesThe Visual Computer, 2023
- Research on target recognition and tracking in mobile augmented reality assisted maintenanceComputer Animation and Virtual Worlds, 2022
- DCR‐Net: Dilated convolutional residual network for fashion image retrievalComputer Animation and Virtual Worlds, 2022
- MFANet: Multi-scale feature fusion network with attention mechanismThe Visual Computer, 2022
- SOD‐YOLO: A Small Target Defect Detection Algorithm for Wind Turbine Blades Based on Improved YOLOv5Advanced Theory and Simulations, 2022
- Accurate landslide detection leveraging UAV‐based aerial remote sensingIET Communications, 2020
- Multi-Attention Object Detection Model in Remote Sensing Images Based on Multi-ScaleIEEE Access, 2019
- Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learningRemote Sensing of Environment, 2018
- Deep Residual Learning for Image Recognition2016