Higher order motion models and spectral clustering

Ochs, Peter; Brox, Thomas

doi:10.1109/cvpr.2012.6247728

Cited by 155 publications

(191 citation statements)

References 15 publications

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…The power of our consensus voting comes from the non-locality of the region reoccurrence, both in space and in time -enabling fast propagation of diverse and rich information across the entire video sequence. This enables the correction of large errors in the initial fg/bg votes.In contrast to trajectory-based methods [1,2,3,4,7,8,10, 11], we do not try to explicitly estimate long-term correspondences via flow estimation or tracking, but rather obtain long-term "probabilistic" correspondences using re-occurring regions across distant frames. This avoids the inherent uncertainties of explicit optical flow estimation, whose errors tend to accumulate over time.…”

mentioning

confidence: 99%

Video Object Segmentation by Non-Local Consensus voting

Faktor¹,

Irani²

2014

Proceedings of the British Machine Vision Conference 2014

210

262

View full text Add to dashboard Cite

Figure 1: A unified approach to foreground/background video segmentation in unconstrained videos. Our algorithm can handle in a single framework video sequences which contain highly non-rigid foreground and background motions, complex 3D parallax as well as simple 2D motions and severe motion blur.We address the problem of Foreground/Background (fg/bg) segmentation of "unconstrained" video. By "unconstrained" we mean that the moving objects and the background scene may be highly non-rigid (e.g., waves in the sea); the camera may undergo a complex motion with 3D parallax; moving objects may suffer from motion blur, large scale and illumination changes, etc. Fig. 1 shows a few such examples. Most existing segmentation methods fail on such unconstrained videos, especially in the presence of highly non-rigid motion and low resolution. Unconstrained video has thus become the focus of most recent video segmentation methods [5,6,9,13].In this paper, we suggest a simple yet general algorithm for performing fg/bg video segmentation, which handles complex unconstrained videos. We cast the video segmentation problem as a voting scheme on the graph of similar ("re-occurring") regions in the video sequence. 'Reoccurring' regions can be quite far both in space and in time, but are constrained to be close in the appearance feature space. We start from crude saliency votes at each pixel, and iteratively correct those votes by "consensus voting" of re-occurring regions across the video sequence. The power of our consensus voting comes from the non-locality of the region reoccurrence, both in space and in time -enabling fast propagation of diverse and rich information across the entire video sequence. This enables the correction of large errors in the initial fg/bg votes.In contrast to trajectory-based methods [1,2,3,4,7,8,10, 11], we do not try to explicitly estimate long-term correspondences via flow estimation or tracking, but rather obtain long-term "probabilistic" correspondences using re-occurring regions across distant frames. This avoids the inherent uncertainties of explicit optical flow estimation, whose errors tend to accumulate over time. Similarly, MRF-based video segmentation methods [5,6,9,13] tend to propagate information only locally in spacetime. Their temporal links are based on optical-flow, whose rapidly accumulated errors induce weak (often zero) weights between related parts in faraway frames. The segmentation performance of video-MRF methods thus strongly depends on the quality of their initial fg/bg data term. However, fg/bg initializations tend to be very noisy, whether based on mining moving object proposals [5,6,13], or based on motion saliency maps [9] (especially in unconstrained low-quality videos). Therefore, current video segmentation methods encounter difficulties in such challenging videos. In contrast, our non-local consensus voting allows us to start with very 'noisy' fg/bg votes, and clean them rapidly according to 'consensus voting' of distant re-occurring regions.Qualitative and quantitati...

show abstract

mentioning

confidence: 99%

Video Object Segmentation by Non-Local Consensus voting

Faktor¹,

Irani²

2014

Proceedings of the British Machine Vision Conference 2014

210

262

View full text Add to dashboard Cite

show abstract

“…Although (Ochs and Brox, 2012) approach is able to segment the hand clearly, the wheel segmentation is not perfect. Fig.…”

Section: The Proposed Approachmentioning

confidence: 99%

“…This is the reason that interests us to group the entire 5DMFV space into 3 clusters. (Ochs and Brox, 2012). We have presented the results of our proposed approach with just optical flow vector as feature vector in the column-4 while column-5 shows results obtained using 5DMFV.…”

Section: The Proposed Approachmentioning

confidence: 99%

“…This approach takes into consideration the 3D position of object and its direction of motion while segmenting the object. Another notable work on motion segmentation is given by Ochs and Brox (Ochs and Brox, 2012). Their paper presents an efficient approach of separating the moving objects from a video using spectral clustering.…”

Section: Related Workmentioning

confidence: 99%

“…Also we consider the railway scene with constant locomotive motion and irregular tree movement due to the emitted smoke. In the fountain scene, the work by (Ochs and Brox, 2012) seems to perform better with less erroneous regions in the trajectory clustering image when compared to We apply our algorithm to a set of five consecutive frames of the wheel scene. In Fig.…”

Section: The Proposed Approachmentioning

confidence: 99%

See 2 more Smart Citations

Motion Characterization of a Dynamic Scene

Vasudevan

Muralidharan

Chintapalli

et al. 2014

Proceedings of the 9th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Given a video, there are many algorithms to separate static and dynamic objects present in the scene. The proposed work is focused on classifying the dynamic objects further as having either repetitive or non-repetitive motion. In this work, we propose a novel approach to achieve this challenging task by processing the optical flow fields corresponding to the video frames of a dynamic natural scene. We design an unsupervised learning algorithm which uses functions of the flow vectors to design the feature vector. The proposed algorithm is shown to be effective in classifying a scene into static, repetitive, and non-repetitive regions. The proposed approach finds significance in various vision and computational photography tasks such as video editing, video synopsis, and motion magnification.

show abstract

Transparent object segmentation from casually captured videos

Liao

Yan

et al. 2020

Computer Animation & Virtual

View full text Add to dashboard Cite

Segmentation of transparent objects from sequences can be very useful in computer vision applications. However, without additional auxiliary information it can be hard work for traditional segmentation methods, as light in the transparent area captured by RGB cameras mostly derive from the background and the appearance of transparent objects changes with surroundings. In this article, we present a from-coarse-to-fine transparent object segmentation method, which utilizes trajectory clustering to roughly distinguish the transparent from the background and refine the segmentation based on combination information of color and distortion. We further incorporate the transparency saliency with color and trajectory smoothness throughout the video to acquire a spatiotemporal segmentation based on graph-cut. We conduct our method on various datasets. The results demonstrate that our method can successfully segment transparent objects from the background.

show abstract

Higher order motion models and spectral clustering

Cited by 155 publications

References 15 publications

Video Object Segmentation by Non-Local Consensus voting

Video Object Segmentation by Non-Local Consensus voting

Motion Characterization of a Dynamic Scene

Transparent object segmentation from casually captured videos

Contact Info

Product

Resources

About