Structured Kalman Filter for Tracking Partially Occluded Moving Objects

Jang, Daesik; Jang, Seok-Woo; Choi, Hyung-Il

doi:10.1007/3-540-45482-9_24

Cited by 4 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A boundary template generated by S-ACES in the first frame is used for the matching. An advantage of the present method compared to the Kalman [11] and those present in [8,24] is the higher speed. Another advantage is that the geometric information extracted from the objects in a frame is useful to determine the semantic of the scene.…”

Section: Resultsmentioning

confidence: 97%

“…This stage predicts the position of the mass center in F t+1 using the information from frames F t , F t−1 , and F t−2 [11,13]. In Equation (4.1), V t and a t denote the velocity and acceleration of the target.…”

Section: Prediction Stagementioning

confidence: 99%

“…In the original Kalman Filter [11,13], E Zt is calculated through the covariance matrix, whereas our measurement error calculation is simpler and less time consuming as shown in Equation in (4.4). But its accuracy is lower compared to the original one.…”

Section: Estimation Stagementioning

confidence: 99%

“…A number of tracking algorithms are available in the literature [1,6,8,11,13,14,20,24]. Generally, tracking systems face two basic obstacles: motion detection, and matching.…”

Section: Introductionmentioning

confidence: 99%

“…A number of occlusion-handling methods have been proposed in the literature. The Structural Kalman Filter [11] utilizes the relational information among the sub-regions of a moving object to handle occlusion. The relational information and actual measurements are used to obtain a priori estimate of the next state of the sub-regions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Tracking partially occluded objects with centripetal active contour

Sirakov¹,

Kandhare²,

Arslan³

2014

Math. Appl.

View full text Add to dashboard Cite

Abstract. This study develops a new approach for tracking single object through a video in case of partial occlusion. The approach uses an active contour (AC) to determine the mass center of the target in the present frame. The mass center is utilized by a Modified Kalman Filter which estimates its position, in the next frame, as the center of the area, the target is most likely to appear in. This area is bounded by the AC, which evolves toward the target. If multiple objects are enveloped, a shell algorithm splits the AC to multiple contours utilizing the mass center position estimated in the previous frame. Every shell is constructed by a part of the AC which envelops the visible, from the contour, parts of objects and ends at the mass center of the AC. In every shell, an AC extracts the object's boundary and generates a finite numerical sequence as a signature for this boundary. A sequence alignment approach matches the signature of every object, in the present frame, with the signature of the target. To validate the method, experiments are performed on 14 videos. The paper ends with discussion on the results and the contributions comparing them with contemporary works.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Prediction Stagementioning

confidence: 99%

Section: Estimation Stagementioning

confidence: 99%

“…A number of tracking algorithms are available in the literature [1,6,8,11,13,14,20,24]. Generally, tracking systems face two basic obstacles: motion detection, and matching.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Tracking partially occluded objects with centripetal active contour

Sirakov¹,

Kandhare²,

Arslan³

2014

Math. Appl.

View full text Add to dashboard Cite

show abstract

Moving Objects Segmentation Based on Automatic Foreground / Background Identification of Static Elements

Isenegger

Salgado

García

2005

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

A Dynamic Adaptive Update System of Tracking Moving Objects Based on Contour Feature

Wang

Zhu

Qin

et al. 2006

2006 IEEE International Conference on Information Acquisition

View full text Add to dashboard Cite

This paper proposes a real-time moving proposed. It gives attention to a good real-time quality and objects detecting algorithm based on computer vision. requirements for illumination. On the other hand, Practice Contour feature is firstly extracted from the initial frame results indicate that the algorithm has dependability and as the feature to describe object, and then the moving robustness to the noise and variable shape of object. object in the latter frame could be tracked and located by marking the location of this feature, at the same time, the II. METHOD OF DETECTING OBJECT feature is dynamically adaptively updated and optimized online. The slight computation burden and robustness to A. ExtractingeFeature of Moving object To extract the feature of moving objects, firstly, the initial the noise and illumination disturbance make the algorithm position of the object should be determined. In actual have a good real-time quality and reliability. Experimental application of monitoring system, there are many moving results indicate that the system reaches the designing objects in video. However, maybe only one of them is requirements.interested, so, the initial position of the object can be

show abstract

Structured Kalman Filter for Tracking Partially Occluded Moving Objects

Cited by 4 publications

References 6 publications

Tracking partially occluded objects with centripetal active contour

Tracking partially occluded objects with centripetal active contour

Moving Objects Segmentation Based on Automatic Foreground / Background Identification of Static Elements

A Dynamic Adaptive Update System of Tracking Moving Objects Based on Contour Feature

Contact Info

Product

Resources

About