###
计算机系统应用英文版:2024,33(11):101-110
本文二维码信息
码上扫一扫!
基于变形卷积和多重注意力的零售商品检测
(1.宁夏大学 信息工程学院, 银川 750021;2.宁夏“东数西算”人工智能与信息安全重点实验室, 银川 750021)
Retail Commodity Detection Based on Deformable Convolution and Multiple Attention
(1.School of Information Engineering, Ningxia University, Yinchuan 750021, China;2.Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West, Yinchuan 750021, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 16次   下载 553
Received:April 25, 2024    Revised:June 17, 2024
中文摘要: 针对零售商品旋转和变形导致难以准确提取全局特征及无关特征干扰的问题, 提出一种基于改进YOLOv8s的零售商品检测算法. 首先, 利用归一化可变形卷积替代部分标准卷积, 通过充分捕获长距离依赖关系以及突出通道关键特征, 增强对全局特征的提取能力; 其次, 使用改进的动态检测头, 使用基于空间感知、尺度感知和任务感知的多重注意力机制来捕获更具区分性的商品局部特征, 以抑制无关特征干扰; 最后, 采用InnerEIoU损失函数替换CIoU, 以降低商品漏检率. 实验结果表明, 所提算法在RPC零售商品数据集上的mAP@0.5:0.95达到93.3%, 较原始算法提升了1.5%, 并优于其他主流检测算法; 同时模型参数量和计算量分别下降了10.0%和6.5%, 能够在存储和计算资源受限的实际场景中, 准确地进行零售商品检测.
Abstract:A retail commodity detection algorithm based on improved YOLOv8s is proposed in response to the difficulty in accurately extracting global features and irrelevant feature interference caused by retail commodity rotation and deformation. Firstly, using normalized deformable convolutions to replace some standard convolutions enhances the ability to extract global features by fully capturing long-range dependencies and highlighting key channel features. Secondly, using an improved dynamic detection head and a multi-attention mechanism based on spatial perception, scale perception, and task perception captures more discriminative local features of goods to suppress irrelevant feature interference. Finally, the InnerEIoU loss function is used to replace CIoU to reduce the missed detection rate of goods. Experimental results show that the proposed algorithm achieves an mAP@0.5:0.95 of 93.3% on the RPC retail commodity dataset, which is 1.5% higher than the original algorithm and better than other mainstream detection algorithms. At the same time, the number of model parameters and the amount of computation decrease by 10.0% and 6.5% respectively, enabling accurate retail commodity detection in practical scenarios with limited storage and computing resources.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(62262053); 宁夏科技创新领军人才计划(2022GKLRLX03)
引用文本:
王添,刘立波.基于变形卷积和多重注意力的零售商品检测.计算机系统应用,2024,33(11):101-110
WANG Tian,LIU Li-Bo.Retail Commodity Detection Based on Deformable Convolution and Multiple Attention.COMPUTER SYSTEMS APPLICATIONS,2024,33(11):101-110