2011 IEEE Workshop on Applications of Computer Vision (WACV) 2011
DOI: 10.1109/wacv.2011.5711560
|View full text |Cite
|
Sign up to set email alerts
|

Classification of traffic video based on a spatiotemporal orientation analysis

Abstract: This paper describes a system for classifying traffic congestion videos based on their observed visual dynamics. Central to the proposed system is treating traffic flow identification as an instance of dynamic texture classification. More specifically, a recent discriminative model of dynamic textures is adapted for the special case of traffic flows. This approach avoids the need for segmentation, tracking and motion estimation that typify extant approaches. Classification is based on matching distributions (o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0
3

Year Published

2012
2012
2023
2023

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(23 citation statements)
references
References 37 publications
0
20
0
3
Order By: Relevance
“…Optical snow arises in many natural situations where the imaged scene elements are restricted to a single direction of motion but vary in speed (e.g., camera translating across a static scene containing a range of depths and vehicular traffic scenes [45], where the speeds may vary but the direction of motion is generally uniform). In the frequency domain, the energy approximately corresponds to a "bow tie" signature formed by the superposition of planes.…”
Section: Orientation In Visual Spacetimementioning
confidence: 99%
“…Optical snow arises in many natural situations where the imaged scene elements are restricted to a single direction of motion but vary in speed (e.g., camera translating across a static scene containing a range of depths and vehicular traffic scenes [45], where the speeds may vary but the direction of motion is generally uniform). In the frequency domain, the energy approximately corresponds to a "bow tie" signature formed by the superposition of planes.…”
Section: Orientation In Visual Spacetimementioning
confidence: 99%
“…As the focus of this paper is surveillance applications, the tracker is evaluated on several surveillance datasets with stationary cameras including CAVIAR 4 , PETS2007 5 , i-LIDS 6 and York dataset 7 . In the following text, we refer to our proposed tracker as IMSOE, as it works based on 'Intensity' and 'MSOE' features.…”
Section: Methodsmentioning
confidence: 99%
“…The SOE feature set is an integrated and modern framework, proposed for analysis of dynamic patterns based on their constituent space-time orientation structure in the video. This framework has been successfully applied in various computer vision applications such as 'Dynamic Texture Recognition and Scene Understanding', 'Action Recognition' and 'Visual Tracking', to name a few [5][6][7][8][9][10][11].…”
Section: Introductionmentioning
confidence: 99%
“…Henceforth they demonstrated the strength of their framework in various computer vision applications [9,7]. We refer to this framework as 'Marginalised SOE' (MSOE) in this paper, which will be discussed in detail.…”
Section: Introductionmentioning
confidence: 99%