A Robust Learning-Based Detection and Tracking Algorithm - Technologies and Applications of Artificial Intelligence - page 283

A Robust Learning-Based Detection
and Tracking Algorithm
Dini Nuzulia Rahmah, Wen-Huang Cheng, Yung-Yao Chen, and Kai-Lung Hua
National Taiwan University of Science and Technology, Taipei, Taiwan
[e-mail]
Abstract. Object tracking in video is a challenging problem in sev-
eral applications such as video surveillance, video compression, video
retrieval, and video editing. Tracking an object in a video is not easy
due to loss of information caused by illumination changing in a scene,
occlusions with other objects, similar target appearances, and inaccurate
tracker responses. In this paper, we present a novel object detection and
tracking algorithm via structured output prediction classifier. Given an
initial bounding box with its position, we first divide it into sub-blocks
with a predefined size. Next, we extract the features from each sub-
blocks with Haar-like features method. And then we learn those features
with a structured output prediction classifier. We treat the sub-blocks
obtained from the initial bounding box as positive samples and then
randomly choose negative samples from search windows defined by the
specific area around the bounding box. After that, we obtain prediction
scores for each sub-blocks both from positive and negative samples. We
construct a region-graph with sub-blocks as nodes and classifier's score
as weight to detect the target object in each frame. Our experimental re-
sults show that the proposed method outperforms state-of-the-art object
tracking algorithms.
Keywords: Object Detection, Object Tracking, Support Vector Ma-
chine.
1 Introduction
Object tracking in video is one of the highly challenging problems in various
applications, such as video editing, video surveillance, video compression, video
retrieval and etc. Some of the challenges that may happen during video tracking
are occlusions with other objects, similar target appearances and inaccurate
tracker responses. When the target object is known for some cases in video
sequences, it is possible to collect the information to be used in the tracker.
While for the other applications, the tracked object might be an arbitrary object
that only can be specified in real time. In these cases, the object may change
caused by object motion, illumination changing and occlusion with other objects.
Hence, in this problem, the tracker must be able to build the appearance of the
object in real time.