Paper Info
Title
Online Detection of Moving Object in Video.
Abstract
Moving car discovery is one of the most essential problems in image processing. It is a very challenging problem that attracts many attentions recently. Major part of previous moving car discovery methods engages radar signals. Nevertheless, those face some troubles in special cases, for example they have difficulty in detection of moving cars in zigzag movements. Machine learning methods can be utilized to conquer these inefficiencies. For online moving car discovery, we propose to employ hierarchical partitioning over the features extracted from image. Each moving car is corresponds to a partition. Unlike the traditional partitioning algorithms, the threshold distance in the proposed method is not fixed. This threshold value is tuned by a Gaussian distribution. Harris features are applied to capture the corner features. Experimentations show the proposed method outperforms other competent methods.
Year
DOI
Venue
2015
10.1007/978-3-319-26181-2_26
Lecture Notes in Artificial Intelligence
Keywords
Field
DocType
Object recognition,Video processing,Moving car discovery
Computer vision,Video processing,Radar signals,Computer science,Image processing,Gaussian,Artificial intelligence,Zigzag,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
Citations 
9426
0302-9743
0
PageRank 
References 
Authors
0.34
3
3
Name
Order
Citations
PageRank
Maryam Azimifar100.34
Farhad Rad223.40
Hamid Parvin326341.94