Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions

Ochs, Peter; Brox, Thomas

doi:10.1109/iccv.2011.6126418

Cited by 201 publications

(179 citation statements)

References 23 publications

Supporting

Mentioning

179

Contrasting

Order By: Relevance

“…Super-pixels are labeled and merged using the motion segmentation tracks and a multi-level variational approach. The results presented in [12] are very good and can easily deal with multiple objects. Due to the very costly components, this method is strictly an off-line approach.…”

Section: Related Workmentioning

confidence: 87%

“…First, we compare the computational complexity (in terms of run time on a 64bit, 2.83 GHz Quad Core CPU with 4GB RAM machine) of the key processes in our method with that of a state-of-the-art method [12]. Table 1 shows both the runtime, and the result of the three main processes: (1) Segmented Trajectories (includes interest point tracking and clustering trajectories over a 10 frame window), (2) oversegmentation/superpixel computation, (3) object segmentation (for both methods, this includes all processes not carried out in process (1) or (2)).…”

Section: Methodsmentioning

confidence: 99%

“…This step serves a similar purpose to the superpixel step used in [12], however, as is illustrated in Table 1, the segmented regions correspond much less strongly to object boundaries than the superpixels computed in [12]. However, the computational complexity of computing the oversegmentation is considerably lower than for the superpixel computation in [12]. The median of the shape-location KDE within each superpixel is also computed, producing a multi-scale boundary sensitive shape-location confidence, as illustrated in the bottom image of Fig.…”

Section: Multi-scale Oversegmentationmentioning

confidence: 99%

“…The object segmentation method in [12] builds on previous research from [10]. They use semi-dense motion segmentation to generate a good initial labeling of the moving objects in the scene.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

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: 87%

Section: Methodsmentioning

confidence: 99%

Section: Multi-scale Oversegmentationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Online Learning for Fast Segmentation of Moving Objects

Ellis

Zografos

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

“…Finally, they produce a sparse segmentation and therefore requires further post-processing to segment the image. [3,11] computes distances de ned over long term trajectories followed by spectral clustering to group trajectories by object. This is followed by applying a hierarchical variational approach to segment regions belonging to di erent objects.…”

Section: Introductionmentioning

confidence: 99%

Online Moving Camera Background Subtraction

Elqursh

Elgammal

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. Recently several methods for background subtraction from moving camera were proposed. They use bottom up cues to segment video frames into foreground and background regions. Due to this lack of explicit models, they can easily fail to detect a foreground object when such cues are ambiguous in certain parts of the video. This becomes even more challenging when videos need to be processed online. We present a method that enables learning of pixel-based models for foreground and background regions and, in addition, segments each frame in an online framework. The method uses long term trajectories along with a Bayesian ltering framework to estimate motion and appearance models. We compare our method to previous approaches and show results on challenging video sequences. IntroductionOne may argue that the ultimate goal of computer vision is to learn and perceive the environment in the same way children learn. Without access to presegmented visual input, infants learn how to segment objects from background using low level cues. Inspired by this evidence, signi cant e ort in the computer vision community has focused on bottom up segmentation of images and videos. This has become ever more important with the proliferation of videos captured by moving cameras. Our goal is to develop an algorithm for foreground/background segmentation from freely moving camera in a online framework that is able to deal with arbitrary long sequences. Traditional video segmentation comes in di erent avors depending on the application, but falls short of achieving this goal. In background subtraction, moving foreground objects are segmented by learning a model of the background with the assumption of a static scene and camera. Motion segmentation methods attempt to segment sparse point trajectories based on coherency of motion. However, they lack a model of the appearance of foreground or background. Video object segmentation attempts to segment an object of interest from the video with no model of the scene background. On the other hand, there are several segmentation techniques that attempt to extend traditional image segmentation to the temporal domain. Such techniques are typically limited to segmenting a short window of time.It is frequently the case that low-level cues may be ambiguous if one only considers a short window of frames. Existing approaches either ignore this problem or resort to processing the whole video o ine. O ine methods can typically 2 Ali Elqursh, and Ahmed Elgmmal produce good results on short sequences but the complexity increases rapidly as more frames need to be processed. The key to solving this problem is to recognize that to handle long sequences in an online way one has to learn and maintain models for the background and foreground regions. Such models serve the purpose of compactly accumulating the evidence over a large number frames and are essential for high level vision tasks.The contribution of this paper is a novel online method that learns appearance and motion models of the scene (backgroun...

show abstract

Sequential Clique Optimization for Video Object Segmentation

Koh¹,

Lee

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions

Cited by 201 publications

References 23 publications

Online Learning for Fast Segmentation of Moving Objects

Online Learning for Fast Segmentation of Moving Objects

Online Moving Camera Background Subtraction

Sequential Clique Optimization for Video Object Segmentation

Contact Info

Product

Resources

About