面向超市场景的人体关键点检测算法研究
首发时间:2020-06-30
摘要:近年来,随着计算机科学和人工智能技术的快速发展,以智能零售、无人超市为代表的新零售行业越来越多地走进了人们的生活。与传统零售行业相比,新零售行业更加依赖智能化的解决方案获取顾客的选择和喜好,这离不开对超市场景中的大规模监控数据进行统计和分析。人体关键点检测算法不仅可以从图像中检测到顾客,还可以输出顾客的头部、肢体等关键点位置信息,为顾客行为分析提供重要的辅助。现有的人体关键点检测算法在准确率与实时性等指标方面不能满足实际场景的需求,本论文提出了一种基于深度学习的人体关键点检测算法以提高算法性能。
关键词: 计算机应用 深度学习 卷积神经网络 人体关键点检测
For information in English, please click here
Research on human keypoint detection algorithm for supermarket scene
Abstract:In recent years, with the rapid development of computer science and artificial intelligence technology, new retail industries represented by smart retail and unmanned supermarkets have increasingly entered people\'s lives. Compared with the traditional retail industry, the new retail industry relies more on intelligent solutions to obtain customers\' choices and preferences, which is inseparable from the statistics and analysis of large-scale monitoring data in supermarket scenarios. The human key point detection algorithm can not only detect customers from the image, but also output the position information of key points such as the customer\'s head and limbs, providing important assistance for customer behavior analysis. Existing human key point detection algorithms cannot meet the needs of actual scenarios in terms of accuracy and real-time performance. This paper proposes a human key point detection algorithm based on deep learning to improve algorithm performance.
Keywords: Computer application technology Deep learning Convolutional neural network Human keypoint detection
基金:
引用
No.****
同行评议
勘误表
面向超市场景的人体关键点检测算法研究
评论
全部评论0/1000