Object Detection in Thermal Infrared Image Based on Improved YOLOX
Ruijie Gao, Zhanchuan Cai
Abstract
Infrared image has received much attention, but the weak features and multi noise in it bring difficulties to object detection. In this letter, an improved YOLOX called YOLOX-IRI is proposed to improve the detection accuracy on infrared images. First, an improved CBAM is proposed to make the network focus on the object area. This module enriches the feature information by mixing three kinds of pooling methods properly, which helps the network distinguish between background and object. Second, class-balanced loss is introduced to suppress adverse effects caused by unbalanced sample distribution problems. This loss function can balance the contribution of each class to the total loss by assigning weights, thereby improving the classification result. Experimental results indicate that our method is superior to other object detection algorithms.