检索结果:
返回 49 结果。
排序:
- 作者: 穆晓芳,李毫,刘嘉骥,刘振宇,李越 ( 太原师范学院计算机科学与技术学院;山西能源学院;天津工业大学电子信息工程学院 )
- 出处: 917 2025 第1期
- 关键词: 多目标跟踪 YOLO 计算机视觉 深度学习
- 摘要: 【目的】针对监控视频跨域环境下的多目标跟踪画面中,频繁遮挡、轨迹开始终止时刻未知、目标太小、目标间交互、表观相似以及摄像头视角变化等问题,提出一种改进的多目标跟踪算法。【方法】 该算法最大化利用低分检测对象,将未匹配的低分对象进行二次匹配,目标跨域后,依据摄像头拓扑排序规则,以及相邻摄像头的未匹配跟
-
点击量:2
- 作者: MU Xiaofang,LI Hao,LIU Jiaji,LIU Zhenyu,LI Yue ( 1College of Computer Science and Technology, Taiyuan Normal University, Jinzhong, Shanxi, China;2School of Electronics and Information Engineering, Tiangong University, Tianjin, China )
- 出处: 4309 2025 Vol.56 No.1 P165-173
- 关键词: multi-target tracking yolo computer vision deep learning
- 摘要: [Purposes] Multi-target tracking in the cross-domain environment of surveillance video is a very important and challenging task in intelligent securit
- 作者: Zhenghan Zhou,Kebin Liu,Yantong Xie,Hangxu Jin,Shi Liu,Ruiqing Wang,Haitian Zhao,Borong Lin,Xiaofang Mu,Hui Qi ( Global Innovation Exchange, Tsinghua University Global Innovation Exchange, Tsinghua University","Fuzhou Fuyao Institute for Advanced Study School of Architecture, Carnegie Mellon University School of Architecture, Tsinghua University College of Computer Science and Technology, Taiyuan Normal University","Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology )
- 出处: 4269 2024
- 关键词: Wireless communication Wireless sensor networks Three-dimensional displays Buildings Psychology Data visualization Cognitive load Real-time systems Space heating Meteorology Climate change Global warming Environmental factors Immersive learning
- 摘要: Amidst global warming and escalating extreme weather events, indoor environmental quality’s impact on human health and public hygiene gains prominence
- 作者: Xiaofang Mu,Yiming Wu,Hong Shi,Mingxing Hou,Bing Guo ( School of Computer Science and Technology, Taiyuan Normal University, Taiyuan, China )
- 出处: 4267 2024
- 关键词: Head Accuracy Attention mechanisms Shape Convolution Interference Feature extraction Safety Neck Context modeling
- 摘要: In response to the challenge of low helmet detection accuracy in actual construction site scenarios due to factors such as worker occlusion and backgr
- 作者: Xiaofang Mu,Shuxian Guo,Hong Shi,Mingxing Hou,Minghui Song,Yiming Wu,Zijian Wang ( College of Computer Science and Technology, Taiyuan Normal University, Taiyuan, China )
- 出处: 4268 2024
- 关键词: Performance evaluation Training Visualization Accuracy Convolution Computational modeling Pose estimation Predictive models Feature extraction Data mining
- 摘要: Lightweight human pose estimation networks are designed to operate on mobile devices with limited resources and computing power. However, reducing mod
会议论文
- 作者: Jinliang Yuan,Qing Li,Fan Dang,Xiaofang Mu,Hui Qi,Mengwei Xu,Shangguang Wang ( Department of Automation, Tsinghua University, China State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China Global Innovation Exchange (GIX), Tsinghua University, China College of Computer Science and Technology, Taiyuan Normal University, China","Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology, China )
- 出处: 4269 2024
- 关键词: Wide area networks Training Wireless communication Protocols Costs Accuracy Federated learning Bandwidth Topology Local area networks
- 摘要: Federated learning has been widely adopted as a privacy-preserving model training paradigm. However, traditional FL protocol heavily relies on data t
- 作者: 穆晓芳,张祎昕,石泓,侯明星 ( 太原师范学院计算机科学与技术学院 )
- 出处: 224 2024 第23卷 第4期 P41-48
- 关键词: 人体姿态估计 轻量级网络 多维协作注意力 DySample
- 摘要: 目前人体姿态估计算法在提高准确率同时,会增加模型的参数量与计算量.本文提出改进的HigherHRNet:一种轻量化的人体姿态估计网络模型.在特征提取阶段采用金字塔分割注意力与幻影卷积,获得比传统3×3卷积更低的参数量;为保证提取精度,引入多维协作注意力模块,提高通道间特征信息的捕获能力.融合动态上采
- 作者: 王俊丽,穆晓芳,温瑞萍 ( 1太原师范学院数学与统计学院;2太原师范学院计算机科学与技术学院 )
- 出处: 224 2023 第22卷 第2期 P13-18
- 关键词: 压缩感知 图像重构 ?-α?最小化 约束等距性 误差估计
- 摘要: 压缩感知主要是考虑从较少的采样数据中以高概率精确地重构原高维稀疏信号.基于■最小化模型,大多数文献研究信号的重构问题,而对于图像重构方面很少研究,尤其对于高斯噪声和?-有界噪声下的图像重构.根据测量矩阵的约束等距性得到这两种噪声下图像重构的误差估计.
-
点击量:1
- 作者: 王俊丽,穆晓芳,温瑞萍 ( 太原师范学院数学与统计学院;太原师范学院计算机科学与技术学院 )
- 出处: 224 2023 第2期 P13-18
- 摘要: 压缩感知主要是考虑从较少的采样数据中以高概率精确地重构原高维稀疏信号.基于l-αl(0-有界噪声下的图像重构.根据测量矩阵的约束等距性得到这两种噪声下图像重构的误差估计.
期刊
- 作者: Jiaji Liu,Xiaofang Mu,Zhenyu Liu,Hao Li ( 1College of Computer Science and Technology, Taiyuan Normal University, 030000, Taiyuan, China )
- 出处: 3822 2023 Vol.34 No.3
- 关键词: Spatiotemporal semantics Multi-object detection Human key points Behavior recognition
- 摘要: Multi-object pose estimation in surveillance scenes is challenging and inaccurate due to object motion blur and pose occlusion in video data. Targetin
-
点击量:1