Video partitioning and camera motion characterization for content-based video indexing

Bouthémy, Patrick; Ganansia, F.

doi:10.1109/icip.1996.559646

Cited by 15 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The short term temporal link provided by our algorithm can be efficiently exploited to build long term object trajectories, even in the presence of long occultation [12]. Background motion estimates can be exploited to compute mosaic or key frames [9] as well as to identify and to characterize different shots of a video sequence [5]. The use of motion and trajectory of objects, along with the detection of dynamic events (e.g.…”

Section: Resultsmentioning

confidence: 99%

Direct incremental model-based image motion segmentation for video analysis

Odobez

Bouthémy

1998

Signal Processing

View full text Add to dashboard Cite

Dynamic analysis of image sequences is an important task in object-oriented video applications. It often relies on the segmentation of each image of the sequence into region entities of apparent homogeneous motion. In this paper, we present an original motion segmentation algorithm based on 2D polynomial motion models, a multiresolution robust estimator to compute these motion models, and appropriate local observations supplying both motion relevant information and their reliability.Motion segmentation is formulated as a contextual statistical labeling problem exploiting multiscale Markov Random Field (MRF) models. One of its main features is that it avoids time consuming alternate iterations between motion model estimation and spatial support identification. An original detection step allows us to estimate and to update the number of required motion models, and thus to handle the appearance of new objects. Numerous experiments performed with real indoor and outdoor image sequences demonstrate the efficiency of the method.

show abstract

Section: Resultsmentioning

confidence: 99%

Direct incremental model-based image motion segmentation for video analysis

Odobez

Bouthémy

1998

Signal Processing

View full text Add to dashboard Cite

show abstract

“…Algorithms that are based on optical flow [2,21] (computed from a pair of raw images) or on motion vectors [13] or macroblock data rates [12] (computed in the compressed domain) explicitly incorporate or compensate the image difference caused by smooth camera movements. The fact that the total change of image intensity, both in space and in time, is modeled should result in enhanced performance of these algorithms.…”

Section: Related Workmentioning

confidence: 99%

Scene-Based Shot Change Detection and Comparative Evaluation

Cheong

2000

Computer Vision and Image Understanding

View full text Add to dashboard Cite

A key step for managing a large video database is to partition the video sequences into shots. Past approaches to this problem tend to confuse gradual shot changes with changes caused by smooth camera motions. This is in part due to the fact that camera motion has not been dealt with in a more fundamental way. We propose an approach that is based on a physical constraint used in optical flow analysis, namely, the total brightness of a scene point across two frames should remain constant if the change across two frames is a result of smooth camera motion. Since the brightness constraint would be violated across a shot change, the detection can be based on detecting the violation of this constraint. It is robust because it uses only the qualitative aspect of the brightness constraint-detecting a scene change rather than estimating the scene itself. Moreover, by tapping on the significant know-how in using this constraint, the algorithm's robustness is further enhanced. Experimental results are presented to demonstrate the performance of various algorithms. It is shown that our algorithm is less likely to interpret gradual camera motions as shot changes, resulting in a better precision performance than most other algorithms. However, its performance deteriorates under large camera or object motions. A twin-threshold scheme is proposed to improve its robustness.

show abstract

“…The Video-shot segmentation segments the sequence into temporal slices. In our system we have implemented the method of [1] which is based on the detection of the dominant motion in the successive images. The Object acquisition task is done by detecting and tracking moving objects through the frames of a single shot.…”

Section: Description Of the Frameworkmentioning

confidence: 99%

“…(1) The nature of video is dynamic: rotations, occasional occlusions, variable illuminations, etc. Therefore recognition with classical methods [3] gives poor results.…”

Section: Introductionmentioning

confidence: 99%

“…To enable high level searching, browsing and navigation, this implicit structure needs to be made explicit [6]. For this purpose, cut detection [1] and object acquisition [4] are performed first. A classification strategy of these objects into homogeneous classes will create links in the video stream, allowing for instance to jump to the next shot where the same person appears.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation