A new region matching method for stereoscopic images

Ansari, Mohamed El; Masmoudi, Lhoussaine; Radouane, L.

doi:10.1016/s0167-8655(99)00158-0

Cited by 22 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The disparity range is provided to the dynamic programming algorithm which performs the matching between edge points of the same image line. The authors have developed different stereo matching [3,4] methods. However, it is difficult to adapt these methods to IV applications because of the features and segmentation they use in the matching process.…”

Section: Related Workmentioning

confidence: 99%

Temporal consistent real-time stereo for intelligent vehicles

Ansari

Mousset²,

Bensrhair³

2010

Pattern Recognition Letters

View full text Add to dashboard Cite

This paper presents a real-time stereo image sequences matching approach dedicated to intelligent vehicles applications. The main idea of the paper consists in integrating temporal information into the matching scheme. The estimation of the disparity map of an actual frame exploits the disparity map estimated for its preceding frame. An association between the two frames is searched, i.e. temporal integration. The disparity range is inferred for the actual frame based on both the association and the disparity map of the preceding frame. Dynamic programming technique is considered for matching the image features. As a similarity measure, a new cost function is defined. The proposed approach is tested on virtual and real stereo image sequences and the results are satisfactory. The method is fast and able to provide about 20 millions disparity maps per second on a HP Pavilion dv6700 2.1GHZ.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporal consistent real-time stereo for intelligent vehicles

Ansari

Mousset²,

Bensrhair³

2010

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…In vertical direction, the mean u(x,y+1) of neighbor pixel (x+1,y) can be described as follow: (8) This scheme allows for keeping complexity small and independent of the size of the matching window, since only two row or col elementary operations are needed to obtain the gray mean at each pixel. The Formula (7) and (8) makes use of a horizon or vertical recursion to obtain other neighbor pixels' mean.…”

Section: ∑ ∑mentioning

confidence: 99%

“…We would like to thank the authors of literature [8], The idea of the proposed algorithm is motivated by it, This work supported by the Doctor Fund of ZhengZhou University of Light Industry(2007BSJ005) and Key Technologies R&D Program(2006BAK01A38).…”

Section: Acknowledgmentmentioning

confidence: 99%

An Obstacle Segmentation Approach in ALV System

Xia

Jun

Min

et al. 2008

2008 Second International Symposium on Intelligent Information Technology Application

View full text Add to dashboard Cite

In ALV system, obstacle detection algorithm is one of the most important research fields and obstacle segmentation is a key factor in obstacle detection approaches. In this paper, a simple and fast segmentation approach is proposed for ALV system based on binocular stereo viison. Firstly, a simple method is applied to binarize the images by the defined binarization function; Secondly, in order to save the computation time of gray mean of pixels in squared window, the method of reduce the redundant computation is applied in our algorithm; Lastly, in order to avoid the affection of inner region of obstacle objects, the outer contour tracing algorithm is applied to get the outer contour of likely obstacle in binarized images, as a result, the likely obstacle objects are segmented. Several images captured from ALV system is used to test the proposed algorithm, the result indicate that the approach is valid and feasible.

show abstract

“…Considerable work has been done in feature correspondence, but the methods are very much image and application dependent. Methods for determining correspondence between point features [44][45][46], line segments [47,48], and regions [49,50] have been developed. Techniques for spatio-temporal alignment of image sequences have also been proposed [51].…”

Section: Role Of Image Registrationmentioning

confidence: 99%