Prohibited Items Detection in Baggage Security Based on Improved YOLOv5

Wang, Zuoshuai; Zhang, Hongyi; Lin, Zhibin; Tan, Xiangqiong; Zhou, Ben

doi:10.1109/seai55746.2022.9832407

Cited by 13 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work by Miao [9] represents the SOTA method in the field of foreground-background separation techniques. Sim- ilarly, the method proposed in [34] stands as the SOTA method among single-stage approaches, while Wang's method [8] is recognized as the SOTA method among twostage approaches. Zhang et al's technique [18] has demonstrated noteworthy performance in prohibited item detection tasks.…”

Section: Comparison Experiments Between Our Methods and Other Mainstr...mentioning

confidence: 99%

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

ZHANG,

BAO,

et al. 2024

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

Automatic detection of prohibited items is vital in helping security staff be more efficient while improving the public safety index. However, prohibited item detection within X-ray security inspection images is limited by various factors, including the imbalance distribution of categories, diversity of prohibited item scales, and overlap between items. In this paper, we propose to leverage the Poisson blending algorithm with the Canny edge operator to alleviate the imbalance distribution of categories maximally in the X-ray images dataset. Based on this, we improve the cascade network to deal with the other two difficulties. To address the prohibited scale diversity problem, we propose the Re-BiFPN feature fusion method, which includes a coordinate attention atrous spatial pyramid pooling (CA-ASPP) module and a recursive connection. The CA-ASPP module can implicitly extract direction-aware and position-aware information from the feature map. The recursive connection feeds the CA-ASPP module processed multi-scale feature map to the bottom-up backbone layer for further multi-scale feature extraction. In addition, a Rep-CIoU loss function is designed to address the overlapping problem in X-ray images. Extensive experimental results demonstrate that our method can successfully identify ten types of prohibited items, such as Knives, Scissors, Pressure, etc. and achieves 83.4% of mAP, which is 3.8% superior to the original cascade network. Moreover, our method outperforms other mainstream methods by a significant margin.

show abstract

Section: Comparison Experiments Between Our Methods and Other Mainstr...mentioning

confidence: 99%

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

ZHANG,

BAO,

et al. 2024

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

show abstract

“…The validity of the model is verified on several datasets. Based on YOLOv5-S, Wang et al [14] replaced the high-level layer of the backbone network with Transformer. They incorporated ASFF (Adaptively Spatial Feature Fusion) into FPN, and GAM (Global Attention Mechanism) into the detection head respectively, to enhance the feature representation capability of network.…”

Section: X-ray Prohibited Object Detectionmentioning

confidence: 99%

“…Recently, some attention mechanisms have been proposed for the prohibited object detection tasks in X-ray images and improved the detection performance significantly [12][13][14], including SA(Spatial Attention), MCIA(Material-aware Cross-channel Interaction Attention) and GAM(Global Attention Mechanism). However，these mechanisms are channel-wise or pixel-wise, which cannot suppress the features of background regions well.…”

Section: Introductionmentioning

confidence: 99%

CTA-FPN: Channel-Target Attention Feature Pyramid Network for Prohibited Object Detection in X-ray Images

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Fast and accurate prohibited object detection in X-ray images is great challenging. Based on YOLOv6 object detection framework, in this paper, Channel-Target Attention Feature Pyramid Network (CTA-FPN) is proposed for prohibited object detection in X-ray images. It includes two key components: TAAM (Target Aware Attention Module) and CAM (Channel Attention Module). TAAM is to generate the target attention map to enhance the features of prohibited object regions and suppress those of the background regions, so as to solve the problems of object occlusion and cluttered background in X-ray images. CAM is to highlight the feature channels important to the detection tasks, and suppress the irrelevant ones. The target-wise and channel-wise feature enhancement can effectively strengthen the feature representation capability of the network. The proposed CTA-FPN is incorporated into S, M and L models of YOLOv6 respectively, obtaining three X-ray prohibited object detection models. The experimental results on two publicly available benchmark datasets of SIXray and CLCXray show that, CTA-FPN can effectively improve the detection performance of YOLOv6. Especially, YOLOv6-CTA-FPN-L can achieve the state-of-the-arts detection accuracy.

show abstract

“…This involves refining both the loss function and the DCGAN structure to generate defects of superior quality. Another improvement is presented by [34] who proposes an enhanced version of the original YOLO v5 method specifically designed for detecting forbidden objects in baggage security. Moreover, [35] refines the YOLO v5 model to detect both regular and irregular cracks in tunnels.…”

Section: Introductionmentioning

confidence: 99%

Fishery Detection and Counting Model uing Fish Images

TALL,

NGOM,

SADIO

et al. 2024

Preprint

View full text Add to dashboard Cite

Fishing in Senegal is threatened by overfishing, compounded by a lack of fisheries management. Stock replenishment and fish classification are generally done manually, and catches are not always declared. In addition, the collection of fishing data suffers from a lack of tools for monitoring and counting the fish caught at the wharves. Although researchers have carried out studies on the fishery in Senegal, data collection is virtually non-existent, and there is no local database dedicated to the fishery or automatic detection and counting algorithm. In this article, a model for automatic detection and counting of fished species is proposed, using a semantic segmentation algorithm. The data used to form the adapted local database are collected from fish images taken at the Soumbédioune fishing wharf in Senegal. This database is supplemented by the Fishbase. This collected data is then segmented to form the appropriate local database. This database is used in conjunction with YOLO v8, an essential element in the detection of images with bounding boxes, to train the model. The results obtained are very promising for the proposed automatic fish detection and counting model. For example, the recall-confidence scores reflect the performance of bounding boxes, with scores ranging from 0.01 to 0.75, thus confirming the effectiveness of the model with bounding boxes. These results are of great importance for improving fisheries policies in Senegal.

show abstract

Prohibited Items Detection in Baggage Security Based on Improved YOLOv5

Cited by 13 publications

References 12 publications

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

CTA-FPN: Channel-Target Attention Feature Pyramid Network for Prohibited Object Detection in X-ray Images

Fishery Detection and Counting Model uing Fish Images

Contact Info

Product

Resources

About