Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark
This work addresses the challenge of automated security inspection for real-world applications, though it is incremental as it builds on existing detection methods with a new dataset and network improvements.
The authors tackled the problem of detecting prohibited items in real-world X-ray security scans by introducing a large-scale dataset (PIDray) with 47,677 images and 12 categories, and proposed a selective dense attention network (SDANet) that outperforms state-of-the-art methods, particularly for hidden items.
Automatic security inspection using computer vision technology is a challenging task in real-world scenarios due to various factors, including intra-class variance, class imbalance, and occlusion. Most of the previous methods rarely solve the cases that the prohibited items are deliberately hidden in messy objects due to the lack of large-scale datasets, restricted their applications in real-world scenarios. Towards real-world prohibited item detection, we collect a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. With an intensive amount of effort, our dataset contains $12$ categories of prohibited items in $47,677$ X-ray images with high-quality annotated segmentation masks and bounding boxes. To the best of our knowledge, it is the largest prohibited items detection dataset to date. Meanwhile, we design the selective dense attention network (SDANet) to construct a strong baseline, which consists of the dense attention module and the dependency refinement module. The dense attention module formed by the spatial and channel-wise dense attentions, is designed to learn the discriminative features to boost the performance. The dependency refinement module is used to exploit the dependencies of multi-scale features. Extensive experiments conducted on the collected PIDray dataset demonstrate that the proposed method performs favorably against the state-of-the-art methods, especially for detecting the deliberately hidden items.