Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00101 - Corpus ID: 230511842
@article{Shi2020XDOGAI, title={X-DOG: An Intelligent X-ray-based Dangerous Goods Detection and Automatic Alarm System}, author={Yu Shi and Yige Xu and Lai Wei and Haoran Gao and Xiaolong Xu}, journal={2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)}, year={2020}, pages={576-582}, url={https://api.semanticscholar.org/CorpusID:230511842}}
- Yu Shi, Yige Xu, Xiaolong Xu
- Published in International Conferences on… 1 November 2020
- Computer Science, Engineering
- 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)
An X-ray-based dangerous goods detection scheme named SSD-X, an improved SSD (Single Shot Multi-Box Detector) object detection algorithm, and a portable detecting system X-DOG, which can run on mobile platform are proposed.
1 Citation
1
Figures and Tables from this paper
- figure 1
- figure 10
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
- figure 8
- figure 9
- table I
- table III
- table V
Topics
Object Detection Algorithm (opens in a new tab)Focal Loss (opens in a new tab)X-ray (opens in a new tab)Soft-NMS (opens in a new tab)Deep Learning (opens in a new tab)Solid-state Disks (opens in a new tab)
One Citation
- Xiaoyu YuWenjun YuanAili Wang
- 2023
Engineering, Computer Science
Electronics
Soft-NMS was used to improve the non-maximum suppression of YOLOv4, effectively solving the problem of the high overlap rate of hazardous materials in the X-ray security-inspection dataset and improving accuracy.
22 References
- Yuanxi WeiXiaoping Liu
- 2019
Computer Science, Engineering
Neural Computing and Applications
The research in this paper focuses on adding additional convolutional layers in the SSD network to re-learn the knowledge of the model learned from the source domain, and shows that compared with the traditional method of fine-tuning, this method has better transfer learning ability on SSD network.
- 23
- Tsung-Yi LinPriya GoyalRoss B. GirshickKaiming HePiotr Dollár
- 2017
Computer Science
2017 IEEE International Conference on Computer…
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
- 18,791
- PDF
- Abhinav ShrivastavaA. GuptaRoss B. Girshick
- 2016
Computer Science
2016 IEEE Conference on Computer Vision and…
OHEM is a simple and intuitive algorithm that eliminates several heuristics and hyperparameters in common use that leads to consistent and significant boosts in detection performance on benchmarks like PASCAL VOC 2007 and 2012.
- 2,189 [PDF]
- Jisoo JeongHyojin ParkNojun Kwak
- 2017
Computer Science
BMVC
The proposed network is suitable for sharing the weights in the classifier networks, by which property, the training can be faster with better generalization power, and shows state-of-the-art mAP, which is better than those of the conventional SSD, YOLO, Faster-RCNN and RFCN.
- 278 [PDF]
- Navaneeth BodlaBharat SinghR. ChellappaL. Davis
- 2017
Computer Science
2017 IEEE International Conference on Computer…
Soft-NMS is proposed, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M and improves state-of-the-art in object detection from 39.8% to 40.9% with a single model.
- 1,479 [PDF]
- W. LiuDragomir Anguelov A. Berg
- 2016
Computer Science
ECCV
The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
- 24,707
- Highly Influential[PDF]
- Shaoqing RenKaiming HeRoss B. GirshickJian Sun
- 2015
Computer Science
IEEE Transactions on Pattern Analysis and Machine…
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
- 51,502 [PDF]
- Hu ZhuJieke ZhangGuoxia XuLizhen Deng
- 2020
Engineering, Computer Science
IEEE Transactions on Aerospace and Electronic…
An adaptive structural element based on a guided filter kernel is proposed for capturing the local features in infrared images for background suppression and a balanced ring shape is used for two structural elements of top-hat transformation, which can utilize the contrast information between the target and background for target enhancement.
- 23
- Joseph RedmonAli Farhadi
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work.
- 13,181 [PDF]
- Cheng-Yang FuW. LiuA. RangaA. TyagiA. Berg
- 2017
Computer Science
ArXiv
This paper combines a state-of-the-art classifier with a fast detection framework and augments SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects.
- 1,757 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers