Video object segmentation by tracking regions

Brendel, William; Todorovic, Sinisa

doi:10.1109/iccv.2009.5459242

Cited by 142 publications

(147 citation statements)

References 18 publications

Supporting

Mentioning

145

Contrasting

Unclassified

Order By: Relevance

“…This was also outlined in the closely related video object segmentation framework of Brendel and Todorovic [3]. They therefore proposed a cyclic dynamic time warping (CDTW) method for obtaining the partial matches with quadratic complexity.…”

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

“…The performance gain of approximately 20% comes from the fact that in single image based segmentation often the upper body part, the face and the legs are split which are correctly merged by our proposed method. In Figure 3 we directly compare results to the two most related image sequence segmentation methods of [12,3] showing improved results due to our proposed graph matching verification. Further results and exemplary videos can be found at our homepage 1 .…”

Section: Object Trackingmentioning

confidence: 99%

“…We focused on single image methods because we are not aware of any publicly available approach for segmenting whole image sequences. Unfortunately, also for the two most related methods [3,12] no code is available. We selected five diverse image sequences for comparison: the well-known flower garden with a moving camera, a static camera news messenger sequence, a video from an action recognition data set, a dynamic texture example and a cartoon sequence.…”

Section: Evaluating Consistencymentioning

confidence: 99%

“…The most related work to ours is from Brendel and Todorovic [3] who recently proposed a video object segmentation method where the results of single frame segmentation were improved by also analyzing a partial match cost between segments. But there are some major differences to our work.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Highly Consistent Sequential Segmentation

et al. 2011

View full text Add to dashboard Cite

Abstract. This paper deals with segmentation of image sequences in an unsupervised manner with the goal of getting highly consistent segmentation results from frame-to-frame. We first introduce a segmentation method that uses results of the previous frame as initialization and significantly improves consistency in comparison to a single frame based approach. We also find correspondences between the segmented regions from one frame to the next to further increase consistency. This matching step is based on a modified version of an efficient partial shape matching method which allows identification of similar parts of regions despite topology changes like merges and splits. We use the identified matched parts to define a partial matching cost which is then used as input to pairwise graph matching. Experiments demonstrate that we can achieve highly consistent segmentations for diverse image sequences, even allowing to track manually initialized moving and static objects.

show abstract

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

Section: Object Trackingmentioning

confidence: 99%

Section: Evaluating Consistencymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Highly Consistent Sequential Segmentation

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Some of the other methods make use of the superpixels. They connect them spatially and temporally to generate temporally consistent object regions [15,4,19,11]. This approach is often used in an unsupervised setting, which usually leads to severe over-segmentation.…”

Section: Related Workmentioning

confidence: 99%

Hierarchy of Localized Random Forests for Video Annotation

Nagaraja

Ochs

Liu

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We address the problem of annotating a video sequence with partial supervision. Given the pixel-wise annotations in the first frame, we aim to propagate these labels ideally throughout the whole video. While some labels can be propagated using optical flow, disocclusion and unreliable flow in some areas require additional cues. To this end, we propose to train localized classifiers on the annotated frame. In contrast to a global classifier, localized classifiers allow to distinguish colors that appear in both the foreground and the background but at very different locations. We design a multi-scale hierarchy of localized random forests, which collectively takes a decision. Cues from optical flow and the classifier are combined in a variational framework. The approach can deal with multiple objects in a video. We present qualitative and quantitative results on the Berkeley Motion Segmentation Dataset.

show abstract

Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation

Huang

Schwing

2018

Computer Vision – ECCV 2018

101

View full text Add to dashboard Cite

Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. To address these challenges for unsupervised video segmentation, we develop a novel saliency estimation technique as well as a novel neighborhood graph, based on optical flow and edge cues. Our approach leads to significantly better initial foreground-background estimates and their robust as well as accurate diffusion across time. We evaluate our proposed algorithm on the challenging DAVIS, SegTrack v2 and FBMS-59 datasets. Despite the usage of only a standard edge detector trained on 200 images, our method achieves state-of-the-art results outperforming deep learning based methods in the unsupervised setting. We even demonstrate competitive results comparable to deep learning based methods in the semi-supervised setting on the DAVIS dataset.

show abstract

Video object segmentation by tracking regions

Abstract: Abstract

Cited by 142 publications

References 18 publications

Highly Consistent Sequential Segmentation

Highly Consistent Sequential Segmentation

Hierarchy of Localized Random Forests for Video Annotation

Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation

Contact Info

Product

Resources

About