Interacting Object Tracking in Human Inhabited Environments
Date Issued
2007
Date
2007
Author(s)
Lo, Tzu-Chien
DOI
en-US
Abstract
Tracking in human inhabited environment is a daunting task. High crowdedness causes challenging data association problems. Different motion patterns from a wide variety of moving objects make motion modeling difficult. Accompanying
with traditional motion modeling techniques, this paper introduces a scene interaction model and a neighboring object interaction model to respectively take long-term and short-term interactions between the tracked objects and its surroundings into account. With the use of the interaction models, anomalous activity recognition is accomplished easily. In addition, move-stop hypothesis tracking is applied to deal with move-stop-move maneuvers. The proposed approaches have been demonstrated using data from a laser scanner mounted on the PAL1 robot. Interacting pedestrians, bicycles, motorcycles, cars and trucks are successfully tracked in difficult situations with occlusion.
Subjects
移動物體
追蹤
互動
moving object
tracking
interaction
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-96-R94922079-1.pdf
Size
23.31 KB
Format
Adobe PDF
Checksum
(MD5):0dbeaaa17b43fa4e4b93c17078f84e08