A New Approach to Track Moving Target with Improved Mean Shift Algorithm and Kalman Filter

Mu, Chengpo; Yuan, Zhijie; Song, Jia; Chen, Yuanqian

doi:10.1109/ihmsc.2012.96

Cited by 10 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In state space tracking and specifically Kalman Filter, object tracking divides to two steps [6]: prediction and correction. First the object location is predicted and then in the next frame using measurement formulas the predicted location will be corrected and a better estimation of the object location will be obtained.…”

Section: Kalman Filtermentioning

confidence: 99%

Real time occlusion handling using Kalman Filter and mean-shift

Panahi

Gholampour

Jamzad

2013

2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)

View full text Add to dashboard Cite

Tracking objects using Mean Shift algorithm fails when there is a full/partial occlusion or when the background color and the desired object are close. In this paper we proposed a method using Kalman Filter and Mean Shift for handling these situations. Using similarity measure of Mean Shift algorithm we are able to detect an occlusion. Kalman Filter comes into the play for occlusion handling in a Buffer-Mode Process. We implemented this algorithm both on PC and DSP 64x+ Texas Instrument and the results are both tabulated. The results reveal the ability of our method to locate the object soon after occlusion disappearance.

show abstract

Section: Kalman Filtermentioning

confidence: 99%

Real time occlusion handling using Kalman Filter and mean-shift

Panahi

Gholampour

Jamzad

2013

2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)

View full text Add to dashboard Cite

show abstract

“…By taking the Taylor expansion around the target candidate probability values [4], [5], [6] the estimated linear approximation of the Bhattacharyya can be described by:…”

Section: A Mean Shift Tracking Algorithmmentioning

confidence: 99%

“…In order to simplify the problem, we suppose that the system noise and the observation noise are all white noise which has not relationship to each other [5], [11]. We will predict the location, velocity and acceleration of moving target after finding out the center of it with Mean Shift algorithm.…”

Section: B Kalman Filtermentioning

confidence: 99%

“…One of the most important disadvantages of this algorithm is that it does not work properly when the color of target candidate is similar to background and in this situation we may lose important data. Of course there is another problem and it occurs when the target occludes [1], [5], [6], [7]. Hence Mean Shift can not track the object in all frames.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Object tracking with occlusion handling using mean shift, Kalman filter and Edge Histogram

Iraei

Faez

2015

2015 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA)

View full text Add to dashboard Cite

This paper propose an algorithm that uses Mean Shift and Kalman Filter for object tracking. Also this method uses Edge Histogram for occlusion handling. Firstly, we use Mean Shift algorithm to obtain center of desired object. But the robust of tracking is not very well, so we use Kalman Filter to improve the effect of tracking. Bhattacharyya coefficient and Edge Histogram are used for finding out both partial and full occlusions. With this approach we can track the object more accurately. The results prove that the robust of tracking is very well.

show abstract

“…In statespace tracking and in particular the Kalman Filter, target tracking is divided into two parts [13]: precision and correction. First, the target position is predicted, and then in the next frame the predicted position will be corrected using relationship measure and the target position will be estimate in a better way.…”

Section: ) Kalman Filtermentioning

confidence: 99%

Small target detection and tracking based on the background elimination and Kalman filter

Dehghani

Pourmohammad

2015

2015 the International Symposium on Artificial Intelligence and Signal Processing (AISP)

View full text Add to dashboard Cite

The problem of small target detection in infrared images is one of the most important areas of research in passive defense systems. This detection method is classified in the Electro optic systems group. Generally, the challenges of the field are divided into two parts: detection and tracking. 1) Due to long detection distance, the amplitude of target signal compared with heavy background clutter is weak. On the other hand, targets appear with few pixels, so that there is no obvious and usable structural and contextual information. 2) Another challenge in tracking small targets is partial obstruction or closeness of background's brightness level to brightness level of the desired target (fading). In this paper, first background is removed by subtracting row mean, then the target are tracking using morphological filtering, thresholding the identified targets and finally by Kalman filter.

show abstract

A New Approach to Track Moving Target with Improved Mean Shift Algorithm and Kalman Filter

Cited by 10 publications

References 10 publications

Real time occlusion handling using Kalman Filter and mean-shift

Real time occlusion handling using Kalman Filter and mean-shift

Object tracking with occlusion handling using mean shift, Kalman filter and Edge Histogram

Small target detection and tracking based on the background elimination and Kalman filter

Contact Info

Product

Resources

About