Robust background subtraction method based on 3D model projections with likelihood

Suzuki, Hiroshi; Ishikawa, Akio; Naito, Seiji; Sakazawa, Shigeyuki

doi:10.1109/mmsp.2010.5662014

Cited by 6 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first experiment, our proposed method was applied to two kinds of video sequences captured in an environment in which the background texture was complicated and similar to the foreground texture, and the luminance varied according to the time changes. Then, the segmentation accuracy was compared using three conventional methods: the foreground segmentation method [6] using only single image information (Single-view method), our conventional method [10] based on the information from multi-view images (multi-view method), and a depth-based approach (Kinect), which were all evaluated for comparison. In order to compare the accuracy with a depth camera, the scene was captured with three Kinect devices arranged at 50-cm and 30-degree angle intervals and 80-cm distances from the object as shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…8. Finally, three values of Recall, Precision, and F-measure were calculated based on the pixel number of true positives, false positives, and false negatives by equation (12), (13), and (14) for each frame as in the case of our conventional work [10]. Fig.…”

Section: A Experiments 1: Comparisons Of Segmentation Accuracymentioning

confidence: 99%

“…On the other hand, some research studies exist using multiview cameras for robust foreground segmentation [9] [10]. In a previous work, we proposed a background subtraction method using multi-view images, instead of using only a single camera image [10].…”

Section: Introductionmentioning

confidence: 99%

“…In a previous work, we proposed a background subtraction method using multi-view images, instead of using only a single camera image [10]. The previous method targeted a shooting environment as in a studio where the background is simple, and the luminance change is controlled.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust foreground segmentation from sparsely arranged multi-view cameras

Suzuki

Sugano

Naito

2013

2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

In this paper, we propose robust segmentation of foreground objects, such as human regions from sparsely arranged multi-view cameras. This work is intended for an immersive telepresence system. The system can be realized by segmenting a conferee (i.e. the foreground) from captured video at each conference site and then synthesizing life-sized textures with the background of another space. However, segmentation is a very challenging problem where the background has a similar texture to the foreground or the illumination varies according to time changes. Actually, segmentation accuracies of conventional methods are not sufficient to realize the telepresence system. The proposed method achieves sufficient segmentation quality to realize the system by directly estimating the foreground regions in a three-dimensional space based on the object existence probability for an individual camera and the color similarity among multiple cameras. Experimental results showed the effectiveness of the proposed method regarding foreground segmentation accuracy. Furthermore, confirmation was made that the experience of motion parallax for head movement could be naturally realized. I. INTRODUCTIONOur motivation for this study is to realize a telepresence system [1] without dedicated equipment based on sparsely arranged multi-view cameras. In the system, the region of an attendee in each conference site is extracted accurately from multi-view video sequences. Then, the segmented texture from respective camera is naturally synthesized to the background of another site as illustrated in Fig. 1.The European FP7 3DPresence project aimed to build a multi-view and multi-user 3D videoconferencing system. In the project, some research activities that cut out the attendees from the real scene and virtually synthesized them into the background of another 3D space were reported [2]. The major challenge of these activities was the generation of high quality depth maps or reconstruction of accurate 3D models of human regions. The main approach of depth map generation is disparity estimation techniques based on stereo block matching [3], while the main approach by 3D model reconstruction is volumetric reconstruction techniques based on the shape from silhouette algorithms [4]. For the stereo block matching method, the depth estimation quality fully depends on camera intervals, and long camera intervals would introduce artifacts. On the other hand, the shape from silhouettes algorithms could stably reconstruct high quality 3D models using multiple cameras with long intervals.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: A Experiments 1: Comparisons Of Segmentation Accuracymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust foreground segmentation from sparsely arranged multi-view cameras

Suzuki

Sugano

Naito

2013

2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authoring application utilizes the method proposed in [5]- [7] to perform texture extraction in order to reconstruct the billboard models. The texture extraction method comprises several steps, in which the most important parts are: projection of borders of the soccer field to determine precise positions of the objects and the area of the field; background segmentation to segment the objects from the field and acquire only the region of the objects; and object tracking to approximate the location and recognize the movement of the objects during the sequence.…”

Section: Introductionmentioning

confidence: 99%

Automatic Soccer Player Tracking in Single Camera with Robust Occlusion Handling Using Attribute Matching

Sabirin

Suzuki

Naito

2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper presents an automatic method to track soccer players in soccer video recorded from a single camera where the occurrence of pan-tilt-zoom can take place. The automatic object tracking is intended to support texture extraction in a free viewpoint video authoring application for soccer video. To ensure that the identity of the tracked object can be correctly obtained, background segmentation is performed and automatically removes commercial billboards whenever it overlaps with the soccer player. Next, object tracking is performed by an attribute matching algorithm for all objects in the temporal domain to find and maintain the correlation of the detected objects. The attribute matching process finds the best match between two objects in different frames according to their pre-determined attributes: position, size, dominant color and motion information. Utilizing these attributes, the experimental results show that the tracking process can handle occlusion problems such as occlusion involving more than three objects and occluded objects with similar color and moving direction, as well as correctly identify objects in the presence of camera movements. key words: free viewpoint, attribute matching, automatic object tracking, soccer video

show abstract

FTV standardization in MPEG

Tanimoto

2014

2014 3dtv-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3dtv-Con)

View full text Add to dashboard Cite

Robust background subtraction method based on 3D model projections with likelihood

Cited by 6 publications

References 11 publications

Robust foreground segmentation from sparsely arranged multi-view cameras

Robust foreground segmentation from sparsely arranged multi-view cameras

Automatic Soccer Player Tracking in Single Camera with Robust Occlusion Handling Using Attribute Matching

FTV standardization in MPEG

Contact Info

Product

Resources

About