本文已被:浏览 7次 下载 63次
Received:April 29, 2024 Revised:June 04, 2024
Received:April 29, 2024 Revised:June 04, 2024
中文摘要: 快速增长的安检需求推动了智能安检技术的发展, 由于X光图片的特殊性, 导致小目标违禁品检测难度大, 本文提出一种改进YOLOv8s的违禁品识别网络进行解决. 首先引入Focal L1 Loss函数改进CIoU, 优化预测框位置与长宽比, 以提高网络对于违禁品的标记能力. 将改进后的可变形卷积加入浅层主干网络中, 捕获不同方向上的违禁品特征信息. 在SPPF模块加入LSKA扩大网络感受野, 并使用Swin-CS模块捕获全局信息、补充维度交互, 最后使用3种注意力堆叠的注意力块进行处理, 提高了网络对小目标的敏感性. 改进后的网络在SIXray数据集上的平均精度均值达到96.1%, 相比原有的YOLOv8s提高5.4%, mAP50-95达到0.682, 提高4.5%. 实验结果表明, 提出的模型能够准确给出预测框, 应对复杂场景中的违禁品检测, 证明了算法的有效性.
Abstract:The rapid growth of security inspection demand drives the development of intelligent security inspection technology. Due to the unique characteristics of X-ray images, detecting small contraband items is challenging. This study proposes an improved YOLOv8s network for contraband recognition to address this issue. Firstly, the Focal L1 Loss function is introduced to enhance CIoU and optimize the position and aspect ratio of prediction boxes to improve the network’s ability to identify contraband items. Improved deformable convolution is added to the shallow backbone network to capture features of contraband items in different directions. LSKA is incorporated into the SPPF module to expand the network’s receptive field, while the Swin-CS module captures global information and supplements dimensional interaction. Finally, three stacked attention blocks are used for processing, enhancing the network’s sensitivity towards small targets. The improved network achieves an average precision mean of 96.1% on the SIXray dataset, a 5.4% improvement over YOLOv8s with mAP50-95 reaching 0.682, a 4.5% increase. Experimental results indicate that the proposed model can accurately generate prediction boxes, effectively handle contraband detection in complex scenarios, and validate algorithm effectiveness.
文章编号: 中图分类号: 文献标志码:
基金项目:山西省自然科学基金面上基金(20210302124192)
Author Name | Affiliation | |
CHEN Guan-Hao | School of Software, North University of China, Taiyuan 030051, China | |
PAN Guang-Zhen | School of Software, North University of China, Taiyuan 030051, China | 228390888@qq.com |
Author Name | Affiliation | |
CHEN Guan-Hao | School of Software, North University of China, Taiyuan 030051, China | |
PAN Guang-Zhen | School of Software, North University of China, Taiyuan 030051, China | 228390888@qq.com |
引用文本:
陈冠豪,潘广贞.基于YOLOv8s的X光违禁品识别.计算机系统应用,,():1-8
CHEN Guan-Hao,PAN Guang-Zhen.X-ray Contraband Identification Based on YOLOv8s.COMPUTER SYSTEMS APPLICATIONS,,():1-8
陈冠豪,潘广贞.基于YOLOv8s的X光违禁品识别.计算机系统应用,,():1-8
CHEN Guan-Hao,PAN Guang-Zhen.X-ray Contraband Identification Based on YOLOv8s.COMPUTER SYSTEMS APPLICATIONS,,():1-8