Filters








2,311 Hits in 5.2 sec

Object tracking with spatio-temporal blob

Catherine Achard, Ghilès Mostafaoui, Maurice Milgram
2005 IAPR International Workshop on Machine Vision Applications  
We propose to develop a tracking algorithm of objects or humans, based on kinematics, with a fix ed monochromatic camera, without any knowledge on the sequence: siz e, shape or number of objects are unknown  ...  For this purpose, we first make a motion detection, then, as we suppose that people move locally in a consistent way and thus draw a regular trajectory in the spatio-temporal space, we modeliz e locally  ...  All points are represented in the spatio-temporal space (x,y,t). Figure 2.  ... 
dblp:conf/mva/AchardMM05 fatcat:wdjfpfig2faqrmth6amrz3wuum

Object Detection by Spatio-Temporal Analysis and Tracking of the Detected Objects in a Video with Variable Background [article]

Kumar S. Ray, Vijayan K. Asari, Soma Chakraborty
2017 arXiv   pre-print
To detect actual moving object in this work, spatio-temporal blobs have been generated in each frame by spatio-temporal analysis of the image sequence using a three-dimensional Gabor filter.  ...  In this paper we propose a novel approach for detecting and tracking objects in videos with variable background i.e. videos captured by moving cameras without any additional sensor.  ...  Formation of moving object from discrete spatio-temporal blobs Discrete spatio-temporal blobs may be parts of same object or the whole moving object in a frame.  ... 
arXiv:1705.02949v1 fatcat:imteamprjnd7tniod3dtg3vp2m

Enhanced tracking and recognition of moving objects by reasoning about spatio-temporal continuity

Brandon Bennett, Derek R. Magee, Anthony G. Cohn, David C. Hogg
2008 Image and Vision Computing  
The reasoning engine deals with error, ambiguity and occlusion in a unified framework to produce a hypothesis that satisfies fundamental constraints on the spatio-temporal continuity of objects.  ...  The framework has been implemented and applied successfully to the analysis of team sports with a single camera.  ...  Our system is based on 'blob tracking' and object classification methods. Much prior work has been presented in these areas. 'Blob tracking' may be described as tracking with a weak object model.  ... 
doi:10.1016/j.imavis.2005.08.012 fatcat:pfyncp5iorgo5f3zujji77p7o4

Learning Spatio-Temporal Topology Of A Multi-Camera Network By Tracking Multiple People

Yunyoung Nam, Junghun Ryu, Yoo-Joo Choi, We-Duke Cho
2007 Zenodo  
This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs).  ...  In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs.  ...  spatio-temporal topology to 3-dimensional topology of the building with stairs and elevators.  ... 
doi:10.5281/zenodo.1334437 fatcat:d7syufv5cfcr3jog4nskxtawju

Persistent Objects Tracking Across Multiple Non Overlapping Cameras

Jinman Kang, Isaac Cohen, Gerard Medioni
2005 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1  
The proposed method tracks a large number of moving people with partial and total occlusions and provides automatic handoff of tracked objects.  ...  The novelty of our approach consists in defining a spatio-temporal Joint Probability Data Association Filter (JPDAF) for integrating multiple cues.  ...  The computational complexity of the spatio-temporal JPDAF depends on the number of tracked moving objects.  ... 
doi:10.1109/acvmot.2005.92 dblp:conf/wacv/KangCM05 fatcat:pgrx2d5vkzaf5oohaewyws4dsa

Determining Interacting Objects in Human-Centric Activities via Qualitative Spatio-Temporal Reasoning [chapter]

Hajar Sadeghi Sokeh, Stephen Gould, Jochen Renz
2015 Lecture Notes in Computer Science  
We use a comprehensive spatio-temporal representation that captures the joint movement between humans and each object.  ...  We take an activity-agnostic approach and rank every moving object in the scene with how likely it is to be involved in the activity.  ...  Therefore, by analysing the spatio-temporal relational changes between each blob and person, we can differentiate between the relevant and irrelevant blobs.  ... 
doi:10.1007/978-3-319-16814-2_36 fatcat:7lzvis4hhrctbe2ibhubni3wgu

Temporal spatio-velocity transform and its application to tracking and interaction

Koichi Sato, J.K. Aggarwal
2004 Computer Vision and Image Understanding  
recognition of human interactions in video sequences using the temporal spatio-velocity transform.  ...  I am also indebted to my friends who have helped me and participated in my experiments. v Preface This dissertation is based on research in the areas of automatic segmentation and tracking of objects and  ...  In the image sequences, a person or a vehicle is treated as one or more continuous blobs in the spatio-temporal image cube. I modeled the objects with slant cylinders.  ... 
doi:10.1016/j.cviu.2004.02.003 fatcat:ay426ffwn5f23nojksdtbqyvze

Human Activity Recognition - A Grand Challenge

J.K. Aggarwal
2007 2007 International Symposium on Signals, Circuits and Systems  
For blob level analysis, we use a modified Hough transform called the Temporal Spatio-Velocity transform to isolate pixels with similar velocity profiles.  ...  Aggarwal's interest in motion started with the study of motion of rigid planar objects and it gradually progressed to the study of human motion.  ...  For blob level analysis, we use a modified Hough transform called the Temporal Spatio-Velocity transform to isolate pixels with similar velocity profiles.  ... 
doi:10.1109/isscs.2007.4292724 fatcat:auxxtp2otvc3zn6i2zxny53rui

Multiple Image Objects Detection, Tracking, and Classification using Human Articulated Visual Perception Capability [chapter]

HeungKyu Lee
2008 Brain, Vision and AI  
From this fact, the spatio-temporal mechanism is derived in order to detect and track multiple objects in consecutive image sequences.  ...  From this fact, the spatio-temporal mechanism is derived in order to detect and track multiple objects in consecutive video frame sequences.  ...  Multiple Image Objects Detection, Tracking, and Classification using Human Articulated Visual Perception Capability, Brain, Vision and AI, Cesare Rossi (Ed.), ISBN: 978-953-7619-04-6, InTech, Available  ... 
doi:10.5772/6040 fatcat:xmuljcpyzbbzvomxqsqfoc2jju

Semantic event representation and recognition using syntactic attribute graph grammar

Liang Lin, Haifeng Gong, Li Li, Liang Wang
2009 Pattern Recognition Letters  
This grammar models the variability of semantic events by a set of meaningful "event components" with the spatio-temporal constraints.  ...  A dictionary of temporal and spatial relations are defined to constrain the event primitives.  ...  Spatio-temporal relations The spatio-temporal constraints of events is critical to understanding to hence representing compositional events, and here we define 6 explicit temporal relations with prior  ... 
doi:10.1016/j.patrec.2008.02.023 fatcat:g6ptjmczhffrbkuaodgicj6voy

Tracking Humans Based on Interest Point over Span-Space in Multifarious Situations

Mohammad Alamgir Hossain, Goutam Sanyal
2016 International Journal of Software Engineering and Its Applications  
We assumed that human may carry something with him or her. However, to apply our method everything is considered as object in our proposed model.  ...  However, based on the tracked object we tried to establish the performance of matching and recognition of human object methods (HOM).  ...  Video Analysis over Activity We demonstrate series of video with respect to spatio-temporal based on POI that can be used to interpret video frames.  ... 
doi:10.14257/ijseia.2016.10.9.15 fatcat:zjmzlqg2yzadhe5xqeyprvo7qi

Where is your dive buddy: tracking humans underwater using spatio-temporal features

Junaed Sattar, Gregory Dudek
2007 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We present results of our algorithm on open-ocean video footage of swimming divers, and also discuss possible extensions and enhancements of the proposed approach for tracking other objects that exhibit  ...  Periodic motion is typically associated with propulsion underwater and specifically with the kicking of human swimmers.  ...  Niyogi and Adelson have utilized spatio-temporal patterns in tracking human beings on land [3] .  ... 
doi:10.1109/iros.2007.4399527 dblp:conf/iros/SattarD07 fatcat:vi5lzhhrxvhglao5xcmpronndm

A Probabilistic Framework for Spatio-Temporal Video Representation & Indexing [chapter]

Hayit Greenspan, Jacob Goldberger, Arnaldo Mayer
2002 Lecture Notes in Computer Science  
Video representation schemes are needed to enable segmenting a video stream into meaningful video-objects, useful for later indexing and retrieval applications.  ...  by temporal tracking of information across frames.  ...  Video has both spatial and temporal dimensions and hence a good video index should capture the spatio-temporal contents of the scene.  ... 
doi:10.1007/3-540-47979-1_31 fatcat:kq6h2ttgdvfmfp5bhbrfuhurgu

Trajectory parsing by cluster sampling in spatio-temporal graph

Xiaobai Liu, Liang Lin, Song-Chun Zhu, Hai Jin
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
We present a spatio-temporal graph (ST-Graph) representation and a cluster sampling algorithm via deferred inference.  ...  pursuit and a tracking process.  ...  each frame, (ii) temporal matching/tracking, and (iii) object recognition.  ... 
doi:10.1109/cvpr.2009.5206688 dblp:conf/cvpr/LiuLZJ09 fatcat:inkuy6tqxfds7kx6j42swqcj7e

Trajectory parsing by cluster sampling in spatio-temporal graph

Xiaobai Liu, Liang Lin, Song-Chun Zhu, Hai Jin
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
We present a spatio-temporal graph (ST-Graph) representation and a cluster sampling algorithm via deferred inference.  ...  pursuit and a tracking process.  ...  each frame, (ii) temporal matching/tracking, and (iii) object recognition.  ... 
doi:10.1109/cvprw.2009.5206688 fatcat:mrj2ls6tarh4bplhexao5u62vu
« Previous Showing results 1 — 15 out of 2,311 results