We proposed a new modeling method to promote the performance of prohibited items recognition via X-ray image. We analyzed the characteristics of prohibited items and X-ray images. We found the fact that the scales of some items are too small to be recognized which encumber the model performance. Then we adopted a set of data augmentation and modified the model to adapt the field of prohibited items recognition. The Convolutional Block Attention Module(CBAM) and rescoring mechanism has been assembled into the model. By the modification, our model achieved a mAP of 89.9% on SIXray10, mAP of 74.8%.
Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark
State Key Laboratory of Computer Science, ISCAS(中国科学院软件研究所计算机科学国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Hangzhou Institute for Advanced Study, UCAS(中国科学院大学杭州高等研究院);JD Finance America Corporation(京东金融美国公司);Beihang University(北京航空航天大学)
Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling
Department of Computing, The Hong Kong Polytechnic University(计算系,香港理工大学);Research Institute of Multiple Agents and Embodied Intelligence(多智能体与具身智能研究院);Pengcheng Laboratory(鹏城实验室)
Towards Real-world X-ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection
State Key Laboratory of Software Development Environment, Beihang University(北京航空航天大学软件开发环境国家重点实验室);iFLYTEK Research(科大讯飞研究院);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所)
Over-sampling De-occlusion Attention Network for Prohibited Items Detection in Noisy X-ray Images
Beihang University(北京航空航天大学);Shen Yuan Honors College, Beihang University(北航沈元荣誉学院);Beijing Advanced Innovation Center for Big Data-Based Precision Medicine(北京大数据精准医学高精尖创新中心)
Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module
State Key Lab of Software Development Environment, Beihang University(北京航空航天大学软件开发环境国家重点实验室);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University(北京航空航天大学大数据精准医疗北京高精尖创新中心)
BGM: Background Mixup for X-ray Prohibited Items Detection
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学学院);Faculty of Data Science, City University of Macau(澳门城市大学数据科学学院);Nuctech Company Limited(核tech公司)
针对 X 射线安检检测忽视背景信息的问题,提出基于透射成像与材料伪彩色特性的 Background Mixup 背景增强,可兼容前景增强并在多个基准上稳定提升性能。
Taming Generative Synthetic Data for X-ray Prohibited Item Detection
Institute of Information Science, Beijing Jiaotong University(信息科学学院,北京交通大学);Faculty of Data Science, City University of Macau(数据科学学院,澳门城市大学);Nuctech Company Limited(NuTech公司)
AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection
College of Information Science and Engineering, Northeastern University(东北大学信息科学与工程学院);Foshan Graduate School of Innovation, Northeastern University(东北大学佛山创新研究生院)
The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery
College of Information Science and Engineering, Northeastern University(信息科学与工程学院,东北大学);State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University(过程工业综合自动化国家重点实验室,东北大学)
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection
Beihang University(北京航空航天大学);Zhongguancun Laboratory(中关村实验室);Chinese Academy of Sciences(中国科学院);University of Science and Technology of China(中国科学技术大学);iFLYTEK(科大讯飞);JD Explore Academy(京东探索研究院);Hefei Comprehensive National Science Center(合肥综合性国家科学中心)
Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学学院);State Key Laboratory of Complex & Critical Software Environment, Beihang University(北航复杂与关键软件环境国家重点实验室)
Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP
College of Information Science and Engineering, Northeastern University(东北大学信息科学与工程学院);Foshan Graduate School of Innovation, Northeastern University(东北大学佛山创新研究院)
针对 X 射线安检中新增违禁品类别识别难题,本文提出带瓶颈适配器的 OVXD 模型,通过微调 CLIP 对齐 X 射线图像与文本,并在 PIXray、PIDray 上显著提升新类别检测性能。
College of Information Science and Engineering, Northeastern University, Shenyang, 110819, China(信息科学与工程学院,东北大学,沈阳,110819,中国);State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, 110819, China(过程工业综合自动化国家重点实验室,东北大学,沈阳,110819,中国);Lee Kong Chian School of Medicine, Nanyang Technological University, 639798, Singapore(李光前医学院,南洋理工大学,639798,新加坡)
RAFA-Net: Region Attention Network For Food Items And Agricultural Stress Recognition
Birla Institute of Technology and Science, Pilani(比拉理工与科学学院皮拉尼分校);University of Hradec Kralove(赫拉德茨-克拉洛韦大学);Skoda Auto University(斯柯达汽车大学);Malaysia Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia(马来西亚理工大学马来西亚日本国际理工学院);Jadavpur University(贾达普大学)
Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from X-ray Scans
Khalifa University(哈利法大学);Durham University(杜伦大学);COSMONiO AI;The University of Western Australia(西澳大学);Inception Institute of Artificial Intelligence(人工智能研究院)
Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting
University of Glasgow(格拉斯哥大学);University of Birmingham(伯明翰大学)
本文提出了一种从2.5D特征中识别服装类别的单次方法。我们提出了两个视觉特征,BSP(B样条补丁)和TSD(拓扑空间距离)的这项任务。该方法采用LLC(Locality-constrained Linear Coding)对BSP局部特征进行编码,并与三种不同的全局特征进行融合。我们的视觉功能是强大的可变形的形状,我们的方法是能够识别类别的未知服装在无约束和随机配置。我们将类别识别流水线与立体视觉系统、服装实例检测和双臂机械手相集成,以实现自主分拣系统。为了验证我们提出的方法的性能,我们构建了一个高分辨率的RGBD服装数据集,其中包含以随机配置采样的5个类别的50件服装(总共2,100个服装样本)。实验结果表明,该方法对训练过程中未发现的服装分类正确率达到83.2%.这比以前的最先进水平提高了36.2%。最后,我们评估所提出的方法在一个自主的机器人分拣系统,其中的机器人认识到一个服装项目从一个不受约束的桩,抓住它,并将其分类到一个盒子根据其类别。我们提出的分拣系统实现了合理的分拣成功率与单发感知。
Tensor Pooling Driven Instance Segmentation Framework for Baggage Threat Recognition
Khalifa University(哈利法大学);Durham University(杜伦大学);The University of Western Australia(西澳大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from Multi-Vendor X-ray Scans
Center for Cyber-Physical Systems (C2PS)(网络物理系统中心(C2PS));Inception Institute of Artificial Intelligence(inception人工智能研究所);Abu Dhabi University(阿布扎比大学);Department of Computer Science, Durham University(杜伦大学计算机科学系)
Southeast University(东南大学);Advanced Ocean Institute of Southeast University(东南大学先进海洋研究院);Northwestern Polytechnical University(西北工业大学);Binjiang Institute of Artificial Intelligence, ZJUT(浙江工业大学滨江人工智能研究院);Alibaba Group(阿里巴巴集团)
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学);MThreads, Inc.(MThreads公司);Nanyang Technological University(南洋理工大学)
Unsupervised Anomaly Instance Segmentation for Baggage Threat Recognition
Khalifa University(哈利法大学);Durham University(杜伦大学);The University of Western Australia(西澳大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)