379,200 Hits in 4.1 sec

Tracking multiple humans in complex situations

Tao Zhao, R. Nevatia
2004 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Tracking multiple humans in complex situations is challenging. The difficulties are tackled with appropriate knowledge in the form of various models in our approach.  ...  In the first part, we show how multiple human objects are segmented and their global motions are tracked in 3D using ellipsoid human shape models.  ...  ACKNOWLEDGMENTS This work was done in USC/IRIS. This research was supported, in part, by the Advanced Research and Development Activity of the US Government under contract No. MDA-908-00-C-0036.  ... 
doi:10.1109/tpami.2004.73 pmid:15742895 fatcat:qogyeijabnhhhd3vgmadvyhnni


W. Nakanishi, T. Fuse
2012 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Despite the importance of understanding pedestrian behavior in public space with regard to achieving more sophisticated space design and flow control, automatic human tracking in complex situation is still  ...  A new method of multiple human tracking is proposed. The key concept is that to assume a tracking process as a data assimilation process.  ...  In this paper, we propose a new method of multiple human tracking under the complex situations.  ... 
doi:10.5194/isprsarchives-xxxix-b3-409-2012 fatcat:6g2ptrzl6jgp3cquscagostfam

A System for Dissecting the Video for Tracing Multiple Humans in Multifaceted Situation

M. Hemalatha, V. Vinodhini, B. Sivaranjani
2013 International Journal of Computer Applications  
Segmenting and tracking multiple humans is a challenging problem in complex situations in which extended occlusion, shadow and/or reflection exists.  ...  Experiments show that our approach works robustly in very challenging Sequences. General Terms Human Tracking, Segmentation, Kalman Filter, Motion Template.  ...  Conclusion and future work Here the work is described on segmentation and tracking of multiple human in complex situations.  ... 
doi:10.5120/13390-1030 fatcat:z7aebldiovalbfkhknqvfuh35a

Multiple Human Tracking Based on Multi-view Upper-Body Detection and Discriminative Learning

Junliang Xing, Haizhou Ai, Shihong Lao
2010 2010 20th International Conference on Pattern Recognition  
This paper focuses on the problem of tracking multiple humans in dense environments which is very challenging due to recurring occlusions between different humans.  ...  The offline and online observation models are neatly integrated into the particle filter framework to robustly track multiple highly interactive humans.  ...  ACKNOWLEDGMENT This work is supported in part by National Basic Research Program of China (2006CB303102), Beijing Educational Committee Program (YB20081000303), and it is also supported by a grant from  ... 
doi:10.1109/icpr.2010.420 dblp:conf/icpr/XingAL10 fatcat:4rkp4xkimjbtbfnuwz2pr6jffa

Online Multi-object Tracking Based on Hierarchical Association Framework

Jaeyong Ju, Daehun Kim, Bonhwa Ku, Hanseok Ko, David K. Han
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, the problem of online multi-object tracking in complex scenes from a single, static, un-calibrated camera is addressed.  ...  In complex scenes, it is still challenging due to frequent and prolonged occlusions, abrupt motion change of objects, unreliable detections, and so on.  ...  Fig. 7 shows our tracking results in complex situation where the pedestrian pointed by an arrow is occluded by multiple pedestrians for a long-term.  ... 
doi:10.1109/cvprw.2016.161 dblp:conf/cvpr/JuKKKH16 fatcat:7or3de4nffbs7lumumx7tktadm

A Multiobject Tracking Framework for Interactive Multimedia Applications

M. Yeasin, E. Polat, R. Sharma
2004 IEEE transactions on multimedia  
Such systems include robots operating in a dynamic and uncertain environment, biomedical systems, and advanced human computer interfaces.  ...  His chief interest is in the role of computational vision in achieving robust behavior by autonomous systems.  ...  In order to perform collaborative human computer interaction or surveillance, the framework must be able to accommodate more than one user situated in a complex real world environment and be able to deal  ... 
doi:10.1109/tmm.2004.827514 fatcat:hifsikzj3fbnbey5xshuwpurhe

Reasoning and Object-Oriented Data Processing for Multisensor Data Fusion

2002 Information & Security An International Journal  
Despite considerable accomplishments in the field, the explosive growth of environmental complexity and uncertainty raise demands for higher degree of automation and more "embedded intelligence."  ...  Alerting peacekeepers in a timely manner, modern sensor systems are the main source of information for adequate situation and treat assessment and for rapid deployment of force.  ...  Theoretically, the most powerful approach for tracking multiple targets is known to be Multiple Hypothesis Tracking (MHT) approach.  ... 
doi:10.11610/isij.0900 fatcat:l5xjeulnkramdhqwudw4allpna

Real-time Multiple Head Shape Detection and Tracking System with Decentralized Trackers

Jacky C. Yuk, Kwan-yee Wong, Ronald Y. Chung, F. L. Chin, K. Chow
2006 Sixth International Conference on Intelligent Systems Design and Applications  
This paper presents a robust human tracking system which incorporates automatic detection of head shape objects with decentralized tracking approach.  ...  This approach simplifies the competition of targets between trackers, and is more efficient than the centralized approach whose time complexity is greatly depends on the number of tracked objects.  ...  Their approach can successfully track multiple human objects in a crowded situation, however, not in real-time.  ... 
doi:10.1109/isda.2006.253867 dblp:conf/isda/YukWCCC06 fatcat:enwik7nafjazrdyjln7lqjbkom

A relaxation algorithm for real-time multiple view 3D-tracking

Yi Li, Adrian Hilton, John Illingworth
2002 Image and Vision Computing  
In this paper we address the problem of reliable real-time 3D-tracking of multiple objects which are observed in multiple wide-baseline camera views.  ...  Abstract In this paper we address the problem of reliable real-time 3D-tracking of multiple objects which are observed in multiple wide-baseline camera views.  ...  In this paper we apply the multiple view 3D-tracking framework to address the issue of computational efficiency in the reliable capture of human movement by simultaneous tracking a person in multiple views  ... 
doi:10.1016/s0262-8856(02)00094-x fatcat:wmbhvd2ovvgolh4zsj5xfgitia

Robust 3D multi-camera tracking from 2D mono-camera tracks by Bayesian association

Raul Mohedano, Narciso Garcia
2010 2010 Digest of Technical Papers International Conference on Consumer Electronics (ICCE)  
In this paper, we present a light but automatic and robust 3D tracking method using multiple calibrated cameras.  ...  The proposed system shows excellent results even in challenging situations, proving itself able to automatically boost and recover from possible errors.  ...  Although monocular systems have been largely studied in the literature [1] and they are useful in a number of situations, they prove themselves insufficient in complex scenarios, also providing limited  ... 
doi:10.1109/icce.2010.5418780 fatcat:vsc3ooosljc7fk3navl5nffsf4

Information Security and Multisensor Data Processing

1999 Information & Security An International Journal  
It performs better than the known solutions, and provides an opportunity to rise the public safety in the complex airport area situations.  ...  Multiple hypothesis tracking using Hough transform track detector is proposed and evaluated in the next paper.  ... 
doi:10.11610/isij.0200 fatcat:dj5l4qkwz5h2lnzhziim5aby2u

Online Learning With Novelty Detection in Human-Guided Road Tracking

Jun Zhou, Li Cheng, Walter F. Bischof
2007 IEEE Transactions on Geoscience and Remote Sensing  
When novel situations are encountered, control is returned back to the human expert to initialize a new training and tracking iteration.  ...  For this reason, we need to develop image interpretation systems that rely on human guidance. In this paper, we tackle the problem of semiautomatic road tracking in aerial photos.  ...  Due to the complexity of the road, intensive human input is required.  ... 
doi:10.1109/tgrs.2007.900697 fatcat:crq5vwimufbcdedothch2fmc64

Tracking multiple people using laser and vision

Jinshi Cui, Hongbin Zha, Huijing Zhao, R. Shibasaki
2005 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We present a novel system that aims at reliably detecting and tracking multiple people in an open area. Multiple single-row laser scanners and one video camera are utilized.  ...  Feet trajectory tracking based on registration of distance information from multiple laser scanners and visual body region tracking based on color histogram are combined in a Bayesian formulation.  ...  In situation 2, we test a much more complex situation, two people walk too close, and there are tracking errors with laser module. In situation 3, we test simultaneous tracking of multiple people.  ... 
doi:10.1109/iros.2005.1545159 dblp:conf/iros/CuiZZS05 fatcat:55s332l5kbfkdlb6ldijaqpmke

Intelligent visual surveillance — A survey

In Su Kim, Hong Seok Choi, Kwang Moo Yi, Jin Young Choi, Seong G. Kong
2010 International Journal of Control, Automation and Systems  
In wide area surveillance control task, multiple cameras or agents are controlled in a cooperative manner to monitor tagged objects in motion.  ...  Detection, tracking, and understanding of moving objects of interest in dynamic scenes have been active research areas in computer vision over the past decades.  ...  Also, robust tracking is possible for occlusion situations because of the shape model. Contour tracking is generally better than kernel tracking when tracking objects with complex shape changes.  ... 
doi:10.1007/s12555-010-0501-4 fatcat:pdv6jpfqfnfiraqe4ngxzvywvu

Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning [chapter]

Xuan Song, Jinshi Cui, Hongbin Zha, Huijing Zhao
2008 Lecture Notes in Computer Science  
Various evaluations have demonstrated that this method performs better than previous methods when the interactions occur, and can maintain the correct tracking under various complex tracking situations  ...  This paper presents an on-line supervised learning based method for tracking multiple interacting targets.  ...  With the help of the classifiers, our method is able to deal with various complex situations in the tracking.  ... 
doi:10.1007/978-3-540-88690-7_48 fatcat:lrjwayrau5d3phlecgz2dhvmem
« Previous Showing results 1 — 15 out of 379,200 results