Efficient use of geometric constraints for sliding-window object detection in video

P Sudowe, B Leibe - International Conference on Computer Vision …, 2011 - Springer
We systematically investigate how geometric constraints can be used for efficient sliding-
window object detection. Starting with a general characterization of the space of sliding …

Security and surveillance

S Gong, CC Loy, T Xiang - Visual analysis of humans: Looking at people, 2011 - Springer
Human eyes are highly efficient devices for scanning through a large quantity of low-level
visual sensory data and delivering selective information to one's brain for high-level …

Learning behavioural context

J Li, S Gong, T Xiang - International journal of computer vision, 2012 - Springer
We propose a novel framework for automatic discovering and learning of behavioural
context for video-based complex behaviour recognition and anomaly detection. Our work …

Crowd behaviour analysis using histograms of motion direction

HM Dee, A Caplier - 2010 IEEE International Conference on …, 2010 - ieeexplore.ieee.org
A practical system for the automated analysis of crowded scenes will have to deal with
multiple occlusions and tracking failures, in a context in which the cameras may move at any …

Scene modelling and classification using learned spatial relations

HM Dee, DC Hogg, AG Cohn - … Conference, COSIT 2009 Aber Wrac'h …, 2009 - Springer
This paper describes a method for building visual scene models from video data using
quantized descriptions of motion. This method enables us to make meaningful statements …

[PDF][PDF] 28nm 工艺基于T_Coil 结构的带ESD 防护器件的高速IO 设计

张博翰, 陈建军, 梁斌, 罗园, 黄俊… - 计算机与数字 …, 2019 - jsj.journal.cssc709.net
摘要高速串行接口芯片是通信领域的核心芯片, 也是云计算的核心互联芯片,
高速串行接口芯片的IO 在实现高速率的同时如何保证其军品ESD 指标是关键难点之一 …

Building semantic scene models from unconstrained video

HM Dee, AG Cohn, DC Hogg - Computer Vision and Image Understanding, 2012 - Elsevier
This paper describes a method for building semantic scene models from video data using
observed motion. We do this through unsupervised clustering of simple yet novel motion …

Learning multi‐planar scene models in multi‐camera videos

F Yin, SA Velastin, T Ellis, D Makris - IET Computer Vision, 2015 - Wiley Online Library
Many man‐made environments are constructed with multiple levels where people walk,
joined by stairs, ramps and overpasses. This study proposes a novel method to learn the …

[PDF][PDF] 一种基于非对称决策融合的行人检测方法

孙妍, 谭毅华, 李彦胜, 田金文 - 计算机与数字工程, 2019 - jsj.journal.cssc709.net
摘要行人检测一直是计算机视觉中的热门话题, 其重要应用包括视觉监视,
机器人技术和汽车驾驶等. 而当行人暂时保持静止时, 运动信息将消失, 运动特征与外观特征均不 …

Self-calibrating 3D context for retrieving people with luggage

J Schels, J Liebelt, R Lienhart - 2011 IEEE International …, 2011 - ieeexplore.ieee.org
We outline the retrieval of images from a network of security cameras by means of an
attribute-based query. Our approach is based on detectors for several object classes which …