A two-stage hybrid approach to the correspondence problem via forward-searching and backward-correcting

Cheng, Changsheng; Aggarwal, J. K.

doi:10.1109/icpr.1990.118084

Cited by 9 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rangarajan and Shah [3] have proposed a noniterative polynomial time approximation algorithm by minimizing a proximal uniformity cost function. Cheng and Aggarwal [4] propose a two stage hybrid approach to the trajectory finding problem. The first stage extends the trajectories and the second one attempts to correct any errors.…”

Section: Introductionmentioning

confidence: 99%

Pixel matching and motion segmentation in image sequences

Ahuja

Charan

1996

Recent Developments in Computer Vision

View full text Add to dashboard Cite

Abstract. This paper presents a coarse-to-fine algorithm to obtain pinel trajectories in a long image sequence and to segment it into subsets corresponding to distinctly moving objects. Much of the previous related work has addressed the computation of optical flow over two frames or sparse feature trajectories in sequences. The features used are often small in number and restrictive assumptions are made about them such as the visibility of features in all the frames. The algorithm described here uses a coarse scale point feature detector to form a 3-D dot pattern in the spatiotemporal space. The trajectories are extracted as 3-D curves formed by the points using perceptual grouping. Increasingly dense correspondences are obtained iteratively from the sparse feature trajectories. At the finest level, which is the focus of this paper, all pixels are matched and the finest boundaries of the moving objects are obtained. Keywords: Motion Segmentation, Perceptual Grouping, Pixel Matching, Triangulation, Feature Matching, Optical Flow. IntroductionThis paper describes a component of our work aimed at interpretation of image sequences. Given an image sequence containing an arbitrary number of rigid objects in motion, the objectives of the overall work are to identify feature points in the scene, obtain spatially dense trajectories of those points, segment moving objects, compute image flow at each pixel, and derive a qualitative description of the scene structure and dynamics from the image sequence. Such qualitative interpretation of the image sequence is useful for a variety of applications such as traffic scene analysis, biological image analysis and aerial image understanding. The focus of this paper is on the detection of pixel flow trajectories. Next section reviews some related previous work. Section 3 summarizes the steps of coarseto-fine detection of sparse feature trajectories. Section 4 then gives the details of the algorithm for finding pixel flow trajectories which is the objective of this paper. Section 5 presents experimental results and Section 6 presents concluding remarks.

show abstract

Section: Introductionmentioning

confidence: 99%

Pixel matching and motion segmentation in image sequences

Ahuja

Charan

1996

Recent Developments in Computer Vision

View full text Add to dashboard Cite

show abstract

“…First of all, it is important to choose a good feature so that the feature correspondence can be made as effortlessly as possible. Typically used features are points [3][4][5][6], line segments or edges [7][8][9][10], or deformable regions [11]. For the low-level feature extraction problem to be practically solvable, we use moving light displays (MLD) [12].…”

mentioning

confidence: 99%

“…Then, iteratively, they tried to gain the trajectories' total smoothness by exchanging intermediate points until it was impossible to gain any further smoothness. Cheng and Aggarwal suggested a two-stage hybrid approach to the problem [3]; a sequential forward-searching algorithm (FSA), which extends all the surviving trajectories, and a batch-type, rulebased, backward-correcting algorithm (BCA). However, certain assumptions upon which their approaches are based are untrue in realistic situations.…”

mentioning

confidence: 99%

Tracking and Motion Estimation of the Articulated Object: a Hierarchical Kalman Filter Approach

Jung

Wohn

1997

Real-Time Imaging

View full text Add to dashboard Cite

Section: P R E V I O U S Workmentioning

confidence: 99%

“…Next section summarizes some related previous work. Section [3][4][5] give details of our algorithm. Section 6 presents experimental results and section 7 presents concluding remarks.…”

Section: Introductionmentioning

confidence: 99%

Feature guided pixel matching and segmentation in motion image sequences

Charan¹,

Ahuja²

Proceedings of International Symposium on Computer Vision - ISCV

View full text Add to dashboard Cite

The problem of feature correspondences and trajectory finding for a long image sequence has received considerable attention. Most attempts involve small numbers of features and make restrictive assumptions such as the visibility of features in all the frames. In this paper, a coarse-to-fine algorithm is described to obtain pixel trajectories through the sequence and to segment into subsets corresponding to distinctly moving objects. The algorithm uses a coarse scale point feature detector to form a 3-D dot pattern in the spatiotemporal space. The trajectories are extracted as 3-D curves formed by the points using perceptual grouping. Increasingly dense correspondences are obtained iteratively from the sparse feature trajectories. At the finest level, matching of all pixels is done using intensity correlation and the finest boundaries of the moving objects are obtained.

show abstract

A two-stage hybrid approach to the correspondence problem via forward-searching and backward-correcting

Cited by 9 publications

References 15 publications

Pixel matching and motion segmentation in image sequences

Pixel matching and motion segmentation in image sequences

Tracking and Motion Estimation of the Articulated Object: a Hierarchical Kalman Filter Approach

Feature guided pixel matching and segmentation in motion image sequences

Contact Info

Product

Resources

About