Detection and segmentation of moving objects in highly dynamic scenes

Bugeau, Aurélie; Pérez, Patrick

doi:10.1109/cvpr.2007.383244

Cited by 63 publications

(41 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method shows promise on realistic datasets, however computationally it is costly; the shape features require extensive training, and computing the prior takes several minutes per frame. Another notable example is the work by [9], on dynamic scenes with rapidly moving objects. Their method clusters pixels together based on multi-scale optical flow, combined with local illumination features in an MRF.…”

Section: Related Workmentioning

confidence: 99%

Online Learning for Fast Segmentation of Moving Objects

Ellis

Zografos

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. This work addresses the problem of fast, online segmentation of moving objects in video. We pose this as a discriminative online semi-supervised appearance learning task, where supervising labels are autonomously generated by a motion segmentation algorithm. The computational complexity of the approach is significantly reduced by performing learning and classification on oversegmented image regions (superpixels), rather than per pixel. In addition, we further exploit the sparse trajectories from the motion segmentation to obtain a simple model that encodes the spatial properties and location of objects at each frame. Fusing these complementary cues produces good object segmentations at very low computational cost. In contrast to previous work, the proposed approach (1) performs segmentation on-the-fly (allowing for applications where data arrives sequentially), (2) has no prior model of object types or 'objectness', and (3) operates at significantly reduced computational cost. The approach and its ability to learn, disambiguate and segment the moving objects in the scene is evaluated on a number of benchmark video sequences.

show abstract

Section: Related Workmentioning

confidence: 99%

Online Learning for Fast Segmentation of Moving Objects

Ellis

Zografos

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

“… The motion based techniques (Optical Flow technique) usually compare relative or absolute motion between moving and stationary objects. Even though these two methods remain most popular, another type of technique which has gained a lot of interest in recent times is based on artificial intelligence [7].…”

Section: Introductionmentioning

confidence: 99%

Review paper on moving object detection using angle change method

2017

IJLTET

View full text Add to dashboard Cite

“…A drawback of the bottom-up approaches which are based on clustering flow vectors is that, due to the clustering procedure and the nature of the optical flow data, they cannot maintain correct identities of the targets after full occlusion even if the targets are of different colors. Bugeau and Pérez [21] approach this problem by also accounting for the color information in the clustering stage and apply graph cuts to improve segmentation.…”

Section: Introductionmentioning

confidence: 99%

A local-motion-based probabilistic model for visual tracking

Kristan

Perš

Kovačič

et al. 2009

Pattern Recognition

View full text Add to dashboard Cite

Color-based tracking is prone to failure in situations where visually similar targets are moving in a close proximity or occlude each other. To deal with the ambiguities in the visual information, we propose an additional color-independent visual model based on the target's local motion. This model is calculated from the optical flow induced by the target in consecutive images. By modifying a color-based particle filter to account for the target's local motion, the combined color/local-motion-based tracker is constructed. We compare the combined tracker to a purely color-based tracker on a challenging dataset from hand tracking, surveillance and sports. The experiments show that the proposed local-motion model largely resolves situations when the target is occluded by, or moves in front of, a visually similar object.

show abstract

Detection and segmentation of moving objects in highly dynamic scenes

Abstract: Abstract

Cited by 63 publications

References 22 publications

Online Learning for Fast Segmentation of Moving Objects

Online Learning for Fast Segmentation of Moving Objects

Review paper on moving object detection using angle change method

A local-motion-based probabilistic model for visual tracking

Contact Info

Product

Resources

About