TY - GEN
T1 - Robust collaborative discriminative learning for RGB-infrared tracking
AU - LAN, Xiangyuan
AU - Ye, Mang
AU - Zhang, Shengping
AU - YUEN, Pong Chi
N1 - Funding Information:
This work was supported in part by Hong Kong RGC General Research Fund HKBU12254316 and the National Natural Science Foundation of China under Grant 61672188. The authors would like to thank Dr. Chenglong Li and Dr. Xiao Wang for providing the videos and some results for comparison, and the anonymous reviewers for their suggestions on improving the paper quality.
PY - 2018
Y1 - 2018
N2 - Tracking target of interests is an important step for motion perception in intelligent video surveillance systems. While most recently developed tracking algorithms are grounded in RGB image sequences, it should be noted that information from RGB modality is not always reliable (e.g. in a dark environment with poor lighting condition), which urges the need to integrate information from infrared modality for effective tracking because of the insensitivity to illumination condition of infrared thermal camera. However, several issues encountered during the tracking process limit the fusing performance of these heterogeneous modalities: 1) the cross-modality discrepancy of visual and motion characteristics, 2) the uncertainty of degree of reliability in different modalities, and 3) large target appearance variations and background distractions within each modality. To address these issues, this paper proposes a novel and optimal discriminative learning framework for multi-modality tracking. In particular, the proposed discriminative learning framework is able to: 1) jointly eliminate outlier samples caused by large variations and learn discriminability-consistent features from heterogeneous modalities, and 2) collaboratively perform modality reliability measurement and target-background separation. Extensive experiments on RGB-infrared image sequences demonstrate the effectiveness of the proposed method.
AB - Tracking target of interests is an important step for motion perception in intelligent video surveillance systems. While most recently developed tracking algorithms are grounded in RGB image sequences, it should be noted that information from RGB modality is not always reliable (e.g. in a dark environment with poor lighting condition), which urges the need to integrate information from infrared modality for effective tracking because of the insensitivity to illumination condition of infrared thermal camera. However, several issues encountered during the tracking process limit the fusing performance of these heterogeneous modalities: 1) the cross-modality discrepancy of visual and motion characteristics, 2) the uncertainty of degree of reliability in different modalities, and 3) large target appearance variations and background distractions within each modality. To address these issues, this paper proposes a novel and optimal discriminative learning framework for multi-modality tracking. In particular, the proposed discriminative learning framework is able to: 1) jointly eliminate outlier samples caused by large variations and learn discriminability-consistent features from heterogeneous modalities, and 2) collaboratively perform modality reliability measurement and target-background separation. Extensive experiments on RGB-infrared image sequences demonstrate the effectiveness of the proposed method.
UR - http://www.scopus.com/inward/record.url?scp=85060354520&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85060354520
T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
SP - 7008
EP - 7015
BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PB - AAAI press
T2 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Y2 - 2 February 2018 through 7 February 2018
ER -