Contraband detection method in X-ray image based on improved CenterNet network

Abstract

Security inspection has been played a crucial role in ensuring the safety of railway passenger transportation. The detection of contraband in X-ray images is an important part of safety inspection work. Since the X-ray image of security inspection is a pseudo color image with a unique imaging style, and the restricted objects are mostly small targets, the accuracy of the object detection algorithm using visible light images directly is not high. This research will propose an improved CenterNet method, and design a 16 times down sampling rate backbone network, which is more suitable for detecting contraband in X-ray images. This article will introduce attention mechanisms to increase attention to effective and key areas in X-ray images, and reveal the mechanisms of spatial and channel attention in X-ray images. Furthermore, by designing an adaptive feature fusion mechanism, the drawback of the original CenterNet by using only the last layer of output features is compensated. Experiments have shown that on the SIXray dataset, mAP is improved by 3.3% compared to the original CenterNet method, and 5.5%, 2.4%, 3.6%, 10.1% compared to SSD, Yolo V3, FPN, DERT algorithms. The detection accuracy of restricted items in X-ray images is effectively improved.