QQ客服 官方微博 反馈留言

浏览/检索结果: 共5条，第1-5条 帮助 已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 某市城市道路交通视频监控系统的设计与实现 学位论文 2016, 2016 戴宇平 收藏  |  浏览/下载：8/0  |  提交时间：2017/06/20 智能交通  综合治理  视频图像监控  Intelligent Transportation  Comprehensive Governance  Video Image Monitoring System   Driving posture recognition by convolutional neural networks 期刊论文 IET COMPUTER VISION, 2016, 卷号: 10, 期号: [db:dc_citation_issue], 页码: 103-114 作者:  Yan, Chao;  Coenen, Frans;  Zhang, Bailing 收藏  |  浏览/下载：12/0  |  提交时间：2019/12/02 road conditions  driver information systems  unsupervised learning  effectiveness performance  sparse filtering  feature extraction  cell phone call  feedforward neural nets  image classification  traffic accidents  road traffic  video clips  road accidents  pose estimation  normal driving  intelligent driver assistance system development  poor illuminations  eating  driver fatigue  unsupervised feature learning method  smoking  image descriptors  embedded functionality  convolutional neural networks  driver hand position monitoring  automatic discriminative feature learning  object recognition  driving posture recognition  driver inattention  video signal processing  Southeast University driving posture dataset  image filtering  generalisation performance  driver vigilance monitoring   Dual DSP-based embedded visual feedback control system for mobile welding robots 期刊论文 2010, 2010 Huang Cao; Sun Zhenguo; Chen Qiang; Liu Pengfei 收藏  |  浏览/下载：10/0 Production monitoring image processing based on foveated vision 期刊论文 2010, 2010 Zheng Yong; Liu Dacheng 收藏  |  浏览/下载：4/0 Adaptive resolution storage system based on LOG-POLAR transform for multi-target trackers (EI CONFERENCE) 会议论文 2010 International Conference on Computer Application and System Modeling, ICCASM 2010, October 22, 2010 - October 24, 2010, Shanxi, Taiyuan, China Zhang Y. 收藏  |  浏览/下载：14/0  |  提交时间：2013/03/25 The main constrained problem of the video monitoring and storage system is the contradiction between large field of view and storage space limitations. Not all of the video information introduced by the image sensors need to be recorded especially for some tracking system which has appointed functions to track specifically kinds of targets. For instance  the system not only works for single target  if the monitor is appointed for human face tracking  but also can work for multi-targets. High reconstruction resolution in the fovea region enables the successive application of recognition modules without sacrificing their performance  the best system appears to be concentrating on human face only and all the others considered being background  the low reconstruction resolution in the periphery helps to reduce the video data. 2010 IEEE.  the background regions needn't to be recorded in detail. For this purpose  this letter presents a real-time foveate storage system  which efficiently represents the video image in log-polar coordinates  with the foveate point centered on the target