F. Moscheni, "Spatio-temporal segmentation and object tracking: An application to second generation video coding," Ph.D. dissertation, Ecole Polytechnique Fdrale de Lausanne, Lausanne, France, 1997. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Unsupervised Segmentation Using Modified Pyramidal Linking Approach - Ziliani (1998) (2 citations) (Correct)
....homogeneous. A higher level interpretation of the scene is necessary in order to define the common characteristics between these heterogeneous regions and thus to merge them together. This higher level interpretation may be the result of user interaction, an object tracking procedure[1], or ever a specific processing. In this paper we propose a segmentation technique that might be considered as a pre processing for a subsequent higher level interpretation of the scene. The main goal of the proposed unsupervised segmentation technique is to obtain regions that belong to the ....
F. Moscheni,"Spatio-Temporal segmentation and object tracking: an application to second generation video coding",Ph.D. thesis at EPFL,Lausanne, CH, 1997.
Image Analysis for Video Surveillance Based on Spatial.. - Francesco Ziliani And (1999) (Correct)
....at the same time, the motion information. In this case detected objects have not precise edges. 2 To overcome these problems an approach based on a statistical decision rule is adopted. The method we apply was proposed by Aach [1] and has already found several applications in Computer Vision [9]. Instead of thresholding the difference image, this approach compares through a significance test, the statistical behaviour of a small neighborhood, N , of each pixel position in the difference image with a model of the noise that could affect the difference image. The noise model is defined ....
F. Moscheni. Spatio-Temporal segmentation and object tracking: an application to second generation video coding. PhD thesis, Swiss Federal Institute of Technology, Lausanne, CH, February 1997.
Focus of Attention: An Image Segmentation procedure based on. . . - Ziliani (1998) (Correct)
....the motion information. In order to obtain a much more flexible procedure, we apply a method that is able to dynamically change the threshold according to the image content. The technique we have chosen has been proposed by Aach [2] It has already found several applications in Computer Vision [3, 4]. This procedure models the camera noise and determine a threshold for each pixel of the image. This is done by taking into account the statistical behavior of each pixel s neighborhood. In order to discriminate the changes that are due to noise from those that are caused by a moving object it is ....
....object. Both shadows and transparencies effects do not appear in comparing the current and the previous frame of the sequence. Thus it could be of interest to combine reference frame, previous frame and current frame in order to obtain more robust results. By analyzing the results shown in Figures [3,4,5,6], we can observe the following: ffl The proposed method is successful in detecting changes in the video sequence. This is true despite the presence of noise as shown in Figure 1. ffl The algorithm performs well for different sequences without the need for a fine tuning of the few parameters it ....
F. Moscheni. Spatio-Temporal segmentation and object tracking: an application to second generation video coding. PhD thesis, Swiss Federal Institute of Technology, Lausanne, CH, February 1997.
Kalman Filtering Motion Prediction For Recursive.. - Ziliani, Moscheni Self-citation (Moscheni) (Correct)
....video coding. 1 RECURSIVE SPATIO TEMPORAL SEGMENTATION AND OBJECT TRACKING In this paper, objects are seen as entities which are both temporally and spatially coherent over multiple frames throughout the sequence [1, 2, 3] In order to find these objects, we use the algorithm proposed by Moscheni [4, 5]. This is an unsupervised technique, that robustly segments a video sequence in terms of multiple moving objects and tracks them through time. The algorithm is composed of two parts, namely, a recursive spatio temporal segmentation method and an object tracking method. These two parts interact and ....
....is characterized through spatial, temporal and spatiotemporal features. With regard to the temporal features, they are naturally taken to be the parameters of the affine motion model. This model is chosen because it describes the object motion with a good compromise between accuracy and complexity [5]. The spatial features have been chosen to be moment based affine invariant parameters [6, 7] This choice is motivated by the fact that the spatial features of the object must be invariant although the object is moving. Finally, the spatio temporal features of the object are related to its ....
[Article contains additional citation context not shown here]
F. Moscheni. Spatio-Temporal segmentation and object tracking: an application to second generation video coding. PhD thesis, Swiss Federal Institute of Technology, Lausanne, CH, February 1997.
Video Object Segmentation Using Bayes-Based Temporal .. - Mezaris.. (2004) (Correct)
No context found.
F. Moscheni, "Spatio-temporal segmentation and object tracking: An application to second generation video coding," Ph.D. dissertation, Ecole Polytechnique Fdrale de Lausanne, Lausanne, France, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC