DATE 

 

 

 

 

 

摘要:
We present two our recent work for multi-target tracking, which are
published in CVPR 2010 and ECCV 2010 respectively. We propose an
approach for online learning of discriminative appearance models for
robust multi-target tracking in a crowded scene from a single camera.
Although much progress has been made in developing methods for optimal
data association, there has been comparatively less work on the
appearance models, which are key elements for good performance. Many
previous methods either use simple features such as color histograms, or
focus on the discriminability between a target and the background which
does not resolve ambiguities between the different targets. We propose
an algorithm for learning a discriminative appearance model for
different targets. Training samples are collected online from tracklets
within a time sliding window based on some spatial-temporal constraints;
this allows the models to adapt to target instances. Learning uses an
AdaBoost algorithm that combines effective image descriptors and their
corresponding similarity measurements. We term the learned models as
OLDAMs. Our evaluations indicate that OLDAMs have significantly higher
discrimination between different targets than conventional holistic
color histograms, and when integrated into a hierarchical association
framework, they help improve the tracking accuracy, particularly
reducing the false alarms and identity switches.

Furthermore, we extend our approach to multiple non-overlapping cameras.
Given the multi-target tracking results in each camera, we propose a
framework to associate those tracks. Collecting reliable training
samples is a major challenge in on-line learning since supervised
correspondence is not available at runtime. To alleviate the inevitable
ambiguities in these samples, Multiple Instance Learning (MIL) is
applied to learn an appearance affinity model which effectively combines
three complementary image descriptors and their corresponding similarity
measurements. Based on the spatial-temporal information and the proposed
appearance affinity model, we present an improved inter-camera track
association framework to solve the “target handover” problem across
cameras. Our evaluations indicate that our method have higher
discrimination between different targets than previous methods.

演講者簡介:
Cheng-Hao Kuo was born in Taipei, Taiwan. He received the BS degree in
electrical engineering from National Taiwan University in 2002, and the
MS degree in electrical and computer engineering from Carnegie Mellon
University in 2005. He is currently a PhD candidate in the Computer
Vision Lab at University of Southern California. His research interests
include computer vision and machine learning, especially for
multi-target tracking and object detection.