{"title":"AO-DETR:用于 X 射线违禁品检测的反重叠 DETR。","authors":"Mingyuan Li, Tong Jia, Hao Wang, Bowen Ma, Hui Lu, Shuyang Lin, Da Cai, Dongyue Chen","doi":"10.1109/TNNLS.2024.3487833","DOIUrl":null,"url":null,"abstract":"<p><p>Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2000,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection.\",\"authors\":\"Mingyuan Li, Tong Jia, Hao Wang, Bowen Ma, Hui Lu, Shuyang Lin, Da Cai, Dongyue Chen\",\"doi\":\"10.1109/TNNLS.2024.3487833\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.</p>\",\"PeriodicalId\":13303,\"journal\":{\"name\":\"IEEE transactions on neural networks and learning systems\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":10.2000,\"publicationDate\":\"2024-11-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on neural networks and learning systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/TNNLS.2024.3487833\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3487833","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
摘要
X 射线图像中的违禁物品检测是广泛应用于各种安检场景中最基本、最有效的方法之一。考虑到 X 射线违禁物品图像中存在严重的重叠现象,我们在最先进的(SOTA)通用对象检测器之一 DETR 的基础上提出了一种反重叠检测变换器(AO-DETR),并改进了去噪锚框 (DINO)。具体来说,为了解决重叠现象造成的特征耦合问题,我们引入了特定类别一对一赋值(CSA)策略,在预测固定类别的违禁物品时对特定类别的对象查询进行约束,从而提高其从重叠的前景-背景特征中提取特定类别违禁物品的特定特征的能力。针对重叠现象导致的边缘模糊问题,我们提出了密集前瞻(LFD)方案,该方案提高了中高层解码器层中参考盒的定位精度,增强了对最终层模糊边缘的定位能力。与 DINO 类似,我们的 AO-DETR 也提供了两个具有不同骨干网的不同版本,以满足不同的应用要求。在 PIXray、OPIXray 和 HIXray 数据集上进行的大量实验表明,所提出的方法超越了 SOTA 物体检测器,这表明它在违禁物品检测领域具有潜在的应用价值。源代码可在以下网址获取:https://github.com/Limingyuan001/AO-DETR。
AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection.
Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.
期刊介绍:
The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.