FA-YOLO: An Improved YOLO Model for Infrared Occlusion Object Detection under Confusing Background

Shuangjiang Du,Hong Xue,Pin Zhang,Baofu Zhang,Peng Xiang,Yin Zhang

doi:10.1155/2021/1896029

Shuangjiang Du, Hong Xue + Show 4 more

Open Access

https://doi.org/10.1155/2021/1896029

Copy DOI

Abstract

Infrared target detection is a popular applied field in object detection as well as a challenge. This paper proposes the focus and attention mechanism-based YOLO (FA-YOLO), which is an improved method to detect the infrared occluded vehicles in the complex background of remote sensing images. Firstly, we use GAN to create infrared images from the visible datasets to make sufficient datasets for training as well as using transfer learning. Then, to mitigate the impact of the useless and complex background information, we propose the negative sample focusing mechanism to focus on the confusing negative sample training to depress the false positives and increase the detection precision. Finally, to enhance the features of the infrared small targets, we add the dilated convolutional block attention module (dilated CBAM) to the CSPdarknet53 in the YOLOv4 backbone. To verify the superiority of our model, we carefully select 318 infrared occluded vehicle images from the VIVID-infrared dataset for testing. The detection accuracy-mAP improves from 79.24% to 92.95%, and the F1 score improves from 77.92% to 88.13%, which demonstrates a significant improvement in infrared small occluded vehicle detection.

Highlights

Infrared target detection is a hot topic in object detection due to its specific characteristics and special demands
When using a transfer learning strategy, the mAP50 improves by 11.1% and the F1 score improves by 9.58%; when using the negative sample focusing mechanism, the mAP50 improves by 12.68% and the F1 score increases by 10.06%
When adding the dilated CBAM to the YOLOv4, the mAP50 improves by 13.71% to 92.95% and the F1 score improves by 10.21% to Figure 7 shows the part of the detected images on the testing set of focus and attention mechanism-based YOLO (FA-YOLO), from which we draw the conclusion that the attention module could detect the small, weak, and occluded targets well

Summary

Introduction

Infrared target detection is a hot topic in object detection due to its specific characteristics and special demands. The current papers focus more on the infrared small, dim targets without too much confusing background information, while the infrared object detection under the confusing background is not being sufficiently studied. (1) Use GAN to increase the amount of the infrared images and transfer learning to promote the training process (2) Add a negative sample focusing mechanism to the YOLOv4 model, let it focus more on the negative sample training to reduce the impact of the confusing background, and improve the detection accuracy of the model (3) Fix the dilated convolutional block attention module (dilated CBAM) into the CSPDarknet to enhance the features of small targets.

Related Works

The Proposed Method

Experiment

Conclusion