Jinman Kang

Detecting motion regions in presence of strong parallax from a moving camera by multi-view geometric constraints (2008)

Chang Yuan, Gérard Medioni, Jinman Kang, Isaac Cohen

Abstract — We present a method for detecting motion regions in video sequences observed by a moving camera, in the presence of strong parallax due to static 3D structures. The proposed method...

Joint IEEE Workshop on Object Tracking and Classification Beyond the Visible Spectrum (OTCBVS’04) In conjunction with IEEE Computer Vision and Pattern Recognition Conference (CVPR’2004) Detection and Tracking of Moving Objects from Overlapping EO and IR S (2008)

Jinman Kang, Kalpitkumar Gajera, Isaac Cohen, Gérard Medioni

We present an approach for tracking moving objects observed by EO and IR sensors on a moving platform. Our approach detects and tracks the moving objects after accurately recovering the geometric...

Medioni “Persistent objects tracking across multiple non overlapping cameras (2008)

Jinman Kang, Isaac Cohen, Gérard Medioni

We present an approach for persistent tracking of moving objects observed by non-overlapping and moving cameras. Our approach robustly recovers the geometry of non-overlapping views using a moving...

IEEE International Workshop on Performance Evaluation of Tracking and Surveillance In conjunction with ECCV'04. Automatic Tracking and Labeling of Human Activities in a Video Sequence (2008)

Fengjun Lv, Jinman Kang, Ram Nevatia, Isaac Cohen, Gérard Medioni

This paper presents a novel approach for tracking multiple objects and a statistical learning approach for detection of human activities in a video sequence. For the tracking, a � rigid...

Asian Conference on Computer Vision (ACCV) January 2004, Jeju Island, Korea TRACKING PEOPLE IN CROWDED SCENES ACROSS MULTIPLE CAMERAS (2008)

Jinman Kang, Isaac Cohen, Gerard Medioni

We present a novel approach for continuous detection and tracking of moving objects observed by multiple stationary cameras. We address the tracking problem by simultaneously modeling motion and...

Part Based Human Tracking in A Multiple Cues Fusion Framework. ICPR (2006)

Qi Zhao, Jinman Kang, Hai Tao, Wei Hua

This paper presents a real time video surveillance system which is capable of tracking multiple humans simultaneously. To better deal with various challenging issues such as occlusions, sharp motion...

Detection and Tracking of Moving Objects from a Moving Platform in Presence of Strong Parallax (2005)

Jinman Kang, Isaac Cohen, Gerard Medioni, Chang Yuan

We present a novel approach to detect and track independently moving regions in a 3D scene observed by a moving camera in the presence of strong parallax. Detected moving pixels are classified into...

Detection and tracking of moving objects from a moving platform in presence of strong parallax (2005)

Jinman Kang, Isaac Cohen, Gérard Medioni, Chang Yuan

We present a novel approach to detect and track independently moving regions in a 3D scene observed by a moving camera in the presence of strong parallax. Detected moving pixels are classified into...

Persistent object detection and tracking within and across multiple cameras / (2004)

Kang, Jinman.

Thesis (Ph. D.)--University of Southern California, 2004.

Automatic Tracking and Labeling of Human Activities in a Video Sequence (2004)

Fengjun Lv, Jinman Kang, Ram Nevatia, Isaac Cohen, Gerard Medioni

This paper presents a novel approach for tracking multiple objects and a statistical learning approach for detection of human activities in a video sequence. For the tracking, a ## rigid...

Object reacquisition using invariant appearance model (2004)

Jinman Kang, Isaac Cohen, Gérard Medioni

We present an approach for reacquisition of detected moving objects. We address the tracking problem by modeling the appearance of the moving region using stochastic models. The appearance of the...

Multi-Views Tracking Within and Across Uncalibrated Camera Streams (2003)

Jinman Kang

This paper presents novel approaches for continuous detection and tracking of moving objects observed by multiple, stationary or moving cameras. Stationary video streams are registered using a ground...

Soccer Player Tracking across Uncalibrated Camera Streams (2003)

Jinman Kang, Isaac Cohen, Gerard Medioni

This paper presents a novel approach for continuous detection and tracking of moving objects observed by multiple stationary cameras. We address the tracking problem by simultaneously modeling motion...

Multi-Views Tracking Within and Across Uncalibrated Camera Streams (2003)

Jinman Kang

This paper presents novel approaches for continuous detection and tracking of moving objects observed by multiple, stationary or moving cameras. Stationary video streams are registered using a ground...

Soccer Player Tracking across Uncalibrated Camera Streams (2003)

Jinman Kang, Isaac Cohen, Gerard Medioni

This paper presents a novel approach for continuous detection and tracking of moving objects observed by multiple stationary cameras. We address the tracking problem by simultaneously modeling motion...

Continuous tracking within and across camera streams (2003)

Jinman Kang, Isaac Cohen, Gerard Medioni

This paper presents a new approach for continuous tracking of moving objects observed by multiple, heterogeneous cameras. Our approach simultaneously processes video streams from stationary and...

Continuous MultiViews Tracking using Tensor Voting (2002)

Jinman Kang, Isaac Cohen, Gerard Medioni

This paper presents a new approach for continuous tracking of moving objects observed by multiple fixed cameras. The continuous tracking of moving objects in each view is realized using a Tensor...