IEEE Proceedings. Intelligent Vehicles Symposium, 2005. 2005
DOI: 10.1109/ivs.2005.1505117
|View full text |Cite
|
Sign up to set email alerts
|

Detection of close cut-in and overtaking vehicles for driver assistance based on planar parallax

Abstract: Image processing is widely considered an essential part of future driver assistance systems. This paper presents a motionbased vision approach to initial detection of static and moving objects observed by a monocular camera attached ,to a moving observer. The underlylng principle is based on parallax flow induced by all non-planar static or moving object of a 3D scene that is determined from optical Row measurements. Initial object hypotheses are crested in regions containing significant parallax flow. The sig… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
21
0

Year Published

2007
2007
2019
2019

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 31 publications
(21 citation statements)
references
References 14 publications
0
21
0
Order By: Relevance
“…In the older studies, e.g. [2], [3] , as well as in many recent ones, e.g. [4], [5] , authors refer to monocular vision or stereo-vision based techniques.…”
Section: Related Workmentioning
confidence: 99%
“…In the older studies, e.g. [2], [3] , as well as in many recent ones, e.g. [4], [5] , authors refer to monocular vision or stereo-vision based techniques.…”
Section: Related Workmentioning
confidence: 99%
“…A common approach when dealing with motion based method is to compute the movement of the car and predict future optical movement. This predicted movement is compared with the real one found to detect unpredicted moving objects in the image [4][5] [6]. Finally in [7] Wang et al propose to model the background into dynamic and quasi-static regions to perform this comparison.…”
Section: State Of the Artmentioning
confidence: 99%
“…Rather than directly utilizing the observed intrinsic flow field, camera ego-motion is canceled out (estimated from inertial sensors) by computing the parallax flow field [1]. Parallax flow is the difference between the intrinsic optical flow field and estimated ground-plane flow.…”
Section: Motion-based Pedestrian Modelmentioning
confidence: 99%
“…This allows for real-time flow computation (25 Hz). Parallax flow is obtained by canceling out camera ego-motion, estimated from inertial sensors [1].…”
Section: System Integrationmentioning
confidence: 99%