A region-level motion-based graph representation and labeling for tracking a spatial image partition

Gelgon, Marc; Bouthémy, Patrick

doi:10.1016/s0031-3203(99)00083-7

Cited by 40 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work on object segmentation and tracking can be divided into region based approaches ( [4][5][6][7][8][9][10]) and boundarybased approaches ( [11,12]; [13,14], [15]). Among the regionbased approaches, some ( [6][7][8][9]) can be classified as layered approaches, with the latter two using models to describe image regions.…”

Section: Related Workmentioning

confidence: 99%

“…Both short-term (2-frame) and longer-term structure is represented and tracked. A model-less, layered approach is taken in [10], where the authors perform motion-based segmentation by computing motion parameters for fixed regions, then merging based on adjacency and similarity of motion parameters. Another model-less approach is found in [4,5], where a method for nonparametric flow estimation is given.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Integrating region and boundary information for spatiallycoherent object tracking

Chung¹,

MacLean²,

Dickinson³

2006

Image and Vision Computing

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Integrating region and boundary information for spatiallycoherent object tracking

Chung¹,

MacLean²,

Dickinson³

2006

Image and Vision Computing

View full text Add to dashboard Cite

“…None of these are feasible for on-IinG use, e.g. [3] reports 80 s processing time per frame. A recent extension to [3] by Cuccbiara er al.…”

Section: Related Workmentioning

confidence: 99%

Fast object segmentation from a moving camera

Arnell

2005

IEEE Proceedings. Intelligent Vehicles Symposium, 2005.

View full text Add to dashboard Cite

Segmentation of the scene is a fundamental component in computer vision to find regions of interest. Most systems that aspire to run in real-time use a fast segmentation stage that considers the whole image, and then a more costly stage for classification. In this paper we present a novel approach to segment moving objects from images taken with a moving camera. The segmentation algorithm is based on a special representation of optical flow, on which u-disparity is applied. The u-disparity is used to indirectly find and mask out the background flow in the image, by approximating it with a quadratic function. Robustness in the optical Row calculation is achieved by contrast content filtering.The algorithm successfully segments moving pedestrians from a moving vehicle with few false positive segments. Most false positive segments are due to poles and organic structures, such as trees. Such false positives are, however, easily rejected in a classification stage. The presented segmentation algorithm is intended to be used as a component in a detectiodclassification framework.

show abstract

“…The vectors are then clustered to segment objects with homogeneous motion. Finally, the approaches based on region merging with motion are hybrid approaches in which the objects are obtained with a segmentation based on visual features, and next merged on motion parameters computed on a region-level [4].…”

Section: Introductionmentioning

confidence: 99%

Fast Dynamic Mosaicing and Person Following

Prati

Seghedoni

Cucchiara

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

A system for video surveillance purposes in wide areas based on active cameras, also capable to follow a person in the scene by keeping him framed, is presented. The proposed approach is based on the so-called direction histograms to compute the ego-motion and on frame differencing for detecting moving objects. It exploits post-processing and active contours to extract precise shape of moving objects to be fed to a probabilistic algorithm to track moving people in the scene. Person following, instead, is based on simple heuristic rules that move the camera as soon as the selected person is close to the border of the field of view. Experimental results on a live active camera demonstrate the feasibility of real-time person following.

show abstract

A region-level motion-based graph representation and labeling for tracking a spatial image partition

Cited by 40 publications

References 25 publications

Integrating region and boundary information for spatiallycoherent object tracking

Integrating region and boundary information for spatiallycoherent object tracking

Fast object segmentation from a moving camera

Fast Dynamic Mosaicing and Person Following

Contact Info

Product

Resources

About