Video Object Segmentation by Salient Segment Chain Composition

Banica, Dan; Agape, Alexandru; Ion, Adrian; Sminchisescu, Cristian

doi:10.1109/iccvw.2013.45

Cited by 36 publications

(27 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to quantitatively compare our results with other methods, we compute the average pixel error rate per frame as done in [17], [24], [9], [29], [3], [20]. As it can be observed in Table 1, our method outperforms the results of these methods in three out of six sequences of the SegTrack database (cheetah, parachute and penguin), in two sequences it is ranked the fourth (birdfall and monkeydog) and in one sequence it is ranked the seventh (girl).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Region-Based Particle Filter for Video Object Segmentation

Varas

Marqués

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We present a video object segmentation approach that extends the particle filter to a region-based image representation. Image partition is considered part of the particle filter measurement, which enriches the available information and leads to a re-formulation of the particle filter. The prediction step uses a co-clustering between the previous image object partition and a partition of the current one, which allows us to tackle the evolution of non-rigid structures. Particles are defined as unions of regions in the current image partition and their propagation is computed through a single co-clustering. The proposed technique is assessed on the SegTrack dataset, leading to satisfactory perceptual results and obtaining very competitive pixel error rates compared with the state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…However, further work is required to deal with occlusions caused by other objects and to improve the detection of self-disocclusions. A similar approach is used in [3] to identify static and moving objects in the scene.…”

Section: Related Workmentioning

confidence: 99%

Region-Based Particle Filter for Video Object Segmentation

Varas

Marqués

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Some approaches utilize tracked feature points [5,6,14,29,34]. Approaches that track a pool of image segment proposals are most related to our approach [3,31], however, these algorithms are unable to handle complete occlusions, and some have restrictions on where segment tracks may start.…”

Section: Related Workmentioning

confidence: 99%

“…There have been some previous frameworks for creating video segmentation proposals, e.g., [3,28,31,45]. However, they all have different restrictions, such as objects have to be moving independently [28], or segments have to start from the first frame [31].…”

Section: Introductionmentioning

confidence: 99%

“…Video segmentation has been defined by different researchers as separating foreground from background [4,28,37,45], identifying moving objects [12,29,34], creating segmentation proposals [3,28,31,45], computing hierarchical sets of coarse-tofine video segments [19,24,36,42], or generating motion segmentations [24,35]. Each of these definitions has its own merits and applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust video segment proposals with painless occlusion handling

Sukthankar

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a robust algorithm to generate video segment proposals. The proposals generated by our method can start from any frame in the video and are robust to complete occlusions. Our method does not assume specific motion models and even has a limited capability to generalize across videos. We build on our previous least squares tracking framework, where image segment proposals are generated and tracked using learned appearance models. The innovation in our new method lies in the use of two efficient moves, the merge move and free addition, to efficiently start segments from any frame and track them through complete occlusions, without much additional computation. Segment size interpolation is used for effectively detecting occlusions. We propose a new metric for evaluating video segment proposals on the challenging VSB-100 benchmark and present state-of-the-art results. Preliminary results are also shown for the potential use of our framework to track segments across different videos.

show abstract

Moving Object 3D Detection and Segmentation Using Optical Flow Clustering

Zhuravlev

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Video Object Segmentation by Salient Segment Chain Composition

Cited by 36 publications

References 17 publications

Region-Based Particle Filter for Video Object Segmentation

Region-Based Particle Filter for Video Object Segmentation

Robust video segment proposals with painless occlusion handling

Moving Object 3D Detection and Segmentation Using Optical Flow Clustering

Contact Info

Product

Resources

About