Object-oriented motion estimation and segmentation in image sequences

Diehl, Norbert

doi:10.1016/0923-5965(91)90028-z

Cited by 147 publications

(59 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in [1,9,10,13,14,16], but the proposed algorithm enables a more efficient implementation than the earlier techniques. Background for this success is that both over-and under-segmentation can be afforded because of the robust way the image segmentation is used in the OME algorithm.…”

Section: Introductionmentioning

confidence: 99%

Efficient image segmentation and its application to motion estimation

Wittebrood

Haan

2003

SPIE Proceedings

View full text Add to dashboard Cite

In this paper, a new concept is introduced for economy image segmentation applicable in an earlier designed object based motion estimation algorithm. The image segmentation is based on simple features, like average grayscale within a segment, and uses spatial-temporal predictions in order to economize the segmentation procedure. Focus is on the segmentation process and the robust application of a non-perfect segmentation mask in the object based motion estimator. In this application, the new image segmentation method helps to improve the motion segmentation, while reducing the operations count. The paper describes both the object-based motion estimation and the block-based image segmentation. Experimental results are described in order to proof the validity of the concept.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient image segmentation and its application to motion estimation

Wittebrood

Haan

2003

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…We now replace the estimates O and B, given by expressions (3,4), in the cost function (2), obtaining an expression for the ML cost function C in terms of a single unknown-the moving object silhouette T, C(T). This is an huge difference from the approach in [13,14], where only the estimate O is replaced in (2), leading to an expression for the ML cost function C in terms of B and T, i.e., C(B, T).…”

Section: Maximum Likelihood Estimation: Greedy Algorithmmentioning

confidence: 99%

“…Regions undergoing different movements are then compensated in different ways, according to their motion, see for example [2] for a review on very low bit rate video coding. The majority of these approaches are based on a single pair of consecutive frames and try to capture the moving object by detecting the regions that changed between the two co-registered images, see for example [3]. Since these methods were developed for image coding rather than for inferring high level representations, they often lead to inaccurate segmentation results.…”

Section: Introductionmentioning

confidence: 99%

Occlusion-Based Accurate Silhouettes from Video Streams

Aguiar

Miranda

Castro

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.We address the problem of segmenting out moving objects from video. The majority of current approaches use only the image motion between two consecutive frames and fail to capture regions with low spatial gradient, i.e., low textured regions. To overcome this limitation, we model explicitly: i) the occlusion of the background by the moving object and ii) the rigidity of the moving object across a set of frames. The segmentation of the moving object is accomplished by computing the Maximum Likelihood (ML) estimate of its silhouette from the set of video frames. To minimize the ML cost function, we developed a greedy algorithm that updates the object silhouette, converging in few iterations. Our experiments with synthetic and real videos illustrate the accuracy of our segmentation algorithm.

show abstract

“…Two consecutive frames of a traffic road video clip are shown in the left side of Figure 1. In the right side of Figure 1, the template of the moving car was found by excluding from the regions that changed between the two co-registered frames the ones that correspond to uncovered background areas, see reference [8]. The small regions that due to the noise are misclassified as belonging to the car template can be discarded by an adequate morphological post-processing.…”

Section: Introductionmentioning

confidence: 99%

“…Since their focus is on compression and not in developing a high level representation, these efforts have not considered low textured scenes, and regions with no texture are considered unchanged. As an example, we applied the algorithm of reference [8] to segmenting a low textured moving object. Two consecutive frames of a traffic road video clip are shown in the left side of Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Maximum Likelihood Estimation of the Template of a Rigid Moving Object

Aguiar¹,

Moura

2001

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Motion segmentation methods often fail to detect the motions of low textured regions. We develop an algorithm for segmentation of low textured moving objects. While usually current motion segmentation methods use only two or three consecutive images our method refines the shape of the moving object by processing successively the new frames as they become available. We formulate the segmentation as a parameter estimation problem. The images in the sequence are modeled taking into account the rigidity of the moving object and the occlusion of the background by the moving object. The segmentation algorithm is derived as a computationally simple approximation to the Maximum Likelihood estimate of the parameters involved in the image sequence model: the motions, the template of the moving object, its intensity levels, and the intensity levels of the background pixels. We describe experiments that demonstrate the good performance of our algorithm.

show abstract

Object-oriented motion estimation and segmentation in image sequences

Cited by 147 publications

References 20 publications

Efficient image segmentation and its application to motion estimation

Efficient image segmentation and its application to motion estimation

Occlusion-Based Accurate Silhouettes from Video Streams

Maximum Likelihood Estimation of the Template of a Rigid Moving Object

Contact Info

Product

Resources

About