Multi-Object Detection in Security Screening Scene Based on Convolutional Neural Network

Abstract

The technique for target detection based on a convolutional neural network has been widely implemented in the industry. However, the detection accuracy of X-ray images in security screening scenarios still requires improvement. This paper proposes a coupled multi-scale feature extraction and multi-scale attention architecture. We integrate this architecture into the Single Shot MultiBox Detector (SSD) algorithm and find that it can significantly improve the effectiveness of target detection. Firstly, ResNet is used as the backbone network to replace the original VGG network to improve the feature extraction capability of the convolutional neural network for images. Secondly, a multi-scale feature extraction (MSE) structure is designed to enrich the information contained in the multi-stage prediction feature layer. Finally, the multi-scale attention architecture (MSA) is fused onto the prediction feature layer to eliminate the redundant features’ interference and extract effective contextual information. In addition, a combination of Adaptive-NMS and Soft-NMS is used to output the final prediction anchor boxes when performing non-maximum suppression. The results of the experiments show that the improved method improves the mean average precision (mAP) value by 7.4% compared to the original approach. New modules make detection much more accurate while keeping the detection speed the same.

Lightweight Detection Method for X-ray Security Inspection with Occlusion

“…Zhang et al [13] improved the SSD (single-shot multibox detector) network by adding small convolutional asymmetric modules and multiscale feature map fusion modules to enhance the detection performance for small targets. Sun et al [14] proposed an algorithm based on SSD, which integrates MSA (multi-scale attention architecture) and MSE (multi-scale feature extraction) structures to eliminate redundant features and enrich the contextual information; the algorithm achieved a 7.4% mAP improvement on X-ray security images compared to original approach. Zhu et al [15] proposed an attention-based multi-scale object detection network AMOD-Net for X-ray baggage security inspection; they designed a channel selection attention module to solve the problems of stacking and occlusion that were extant in the X-ray baggage image; they achieved 86.7%, 88.3%, and 66.9% mAP values for the Easy, Hard, and Hidden test sets of the PIDray [16] datasets, respectively.…”