Interactive video cutout

Wang, Jue; Bhat, P. N.; Colburn, Alex; Agrawala, Maneesh; Cohen, Michael F.

doi:10.1145/1073204.1073233

Cited by 285 publications

(237 citation statements)

References 21 publications

Supporting

Mentioning

234

Contrasting

Unclassified

Order By: Relevance

“…This work is motivated by recent advances in single image alpha matting where it has been shown that sparse information in the form of user brush strokes can be sufficient for figure-ground segmentation in many situations [30]. These results have been extended to video sequences, but to date have required considerable user interaction [32]. We show in this paper that sparse local information in the form of spatiotemporal T-junctions can remove the requirement for user interaction in many cases.…”

Section: Introductionmentioning

confidence: 94%

Automatic video segmentation using spatiotemporal T-junctions

Apostoloff¹,

Fitzgibbon²

2006

Procedings of the British Machine Vision Conference 2006

View full text Add to dashboard Cite

The problem of figure-ground segmentation is of great importance in both video editing and visual perception tasks. Classical video segmentation algorithms approach the problem from one of two perspectives. At one extreme, global approaches constrain the camera motion to simplify the image structure. At the other extreme, local approaches estimate motion in small image regions over a small number of frames and tend to produce noisy signals that are difficult to segment. With recent advances in image segmentation showing that sparse information is often sufficient for figureground segmentation it seems surprising then that with the extra temporal information of video, an unconstrained automatic figure-ground segmentation algorithm still eludes the research community. In this paper we present an automatic video segmentation algorithm that is intermediate between these two extremes and uses spatiotemporal features to regularize the segmentation. Detecting spatiotemporal T-junctions that indicate occlusion edges, we learn an occlusion edge model that is used within a colour contrast sensitive MRF to segment individual frames of a video sequence. T-junctions are learnt and classified using a support vector machine and a Gaussian mixture model is fitted to the (foreground, background) pixel pairs sampled from the detected T-junctions. Graph cut is then used to segment each frame of the video showing that sparse occlusion edge information can automatically initialize the video segmentation problem.

show abstract

Section: Introductionmentioning

confidence: 94%

Automatic video segmentation using spatiotemporal T-junctions

Apostoloff¹,

Fitzgibbon²

2006

Procedings of the British Machine Vision Conference 2006

View full text Add to dashboard Cite

show abstract

“…Interactive video object segmentation systems have been proposed in recent years. Various directions have been investigated such as tracking region boundaries over time [2,54], extending 2D segmentation to 3D video volumes [43,66,3,4], applying graph cut segmentation on successive frames driven by motion flow [6,5,70,68]. Our algorithm propagates the foreground mask forward which initializes the segmentation on the new frame and provides a shape prior taking account of the inherent error in optical flow.…”

Section: Related Workmentioning

confidence: 99%

TouchCut: Fast image and video segmentation using single-touch interaction

Wang

Han

Collomosse

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Global color models. Some modern interactive video cutout systems use global color models, such as the popular choice of global Gaussian mixtures (GMM), to represent the appearance of the dynamic objects, e.g., [2][3][4]. Global color models do not consider the spatial arrangements of color components, thus are robust to object motion.…”

Section: Related Workmentioning

confidence: 99%

“…Similar to the foreground modeling, the DCF model is applied to the reconstructed clean plate, except that σ i is fixed for every background pixel. Typically for static background σ i is set to [2,4] to compensate for small alignment errors. Progressive Background Completion.…”

Section: The Background Layermentioning

confidence: 99%

Dynamic Color Flow: A Motion-Adaptive Color Model for Object Segmentation in Video

Bai

Wang

Sapiro

2010

Computer Vision – ECCV 2010

Self Cite

View full text Add to dashboard Cite

Abstract. Accurately modeling object colors, and features in general, plays a critical role in video segmentation and analysis. Commonly used color models, such as global Gaussian mixtures, localized Gaussian mixtures, and pixel-wise adaptive ones, often fail to accurately represent the object appearance in complicated scenes, thereby leading to segmentation errors. We introduce a new color model, Dynamic Color Flow, which unlike previous approaches, incorporates motion estimation into color modeling in a probabilistic framework, and adaptively changes model parameters to match the local properties of the motion. The proposed model accurately and reliably describes changes in the scene's appearance caused by motion across frames. We show how to apply this color model to both foreground and background layers in a balanced way for efficient object segmentation in video. Experimental results show that when compared with previous approaches, our model provides more accurate foreground and background estimations, leading to more efficient video object cutout systems. 3

show abstract

Interactive video cutout

Cited by 285 publications

References 21 publications

Automatic video segmentation using spatiotemporal T-junctions

Automatic video segmentation using spatiotemporal T-junctions

TouchCut: Fast image and video segmentation using single-touch interaction

Dynamic Color Flow: A Motion-Adaptive Color Model for Object Segmentation in Video

Contact Info

Product

Resources

About