Tracking dynamic textures using a particle filter driven by intrinsic motion information

2010 ◽  
Vol 22 (5) ◽  
pp. 781-789 ◽  
Author(s):  
Renaud Péteri
Keyword(s):  
Particle Filter ◽  
Motion Information ◽  
Dynamic Textures ◽  
Intrinsic Motion

Study on Particle Filter Object Tracking Based on Weighted Fusion

2011 ◽  
Vol 403-408 ◽  
pp. 3049-3053
Author(s):  
Zhi Qiang Wen ◽  
Yan Hui Zhu ◽  
Zhao Yi Peng
Keyword(s):  
Particle Filter ◽  
Object Tracking ◽  
Linear Model ◽  
Information Fusion ◽  
Measurement Model ◽  
Color Histogram ◽  
Motion Information ◽  
Color Information ◽  
Model Based ◽  
Weighted Fusion

For the lack of self-adaptivity to environments, a measurement model based on weighted information fusion is presented in particle filter. Combined with color information and movement information of object, color histogram and motion Information histogram are built respectively, and then present a weighted linear model as the measurement model. The center-around method is adopted to compute the weight in the linear model. Lastly, a mass of experiments show the presented method be effective.

A Targets Detecting Approach in the Dynamic Background

2012 ◽  
Vol 220-223 ◽  
pp. 2288-2293
Author(s):  
Wei Wang ◽  
Yuan Lei Li ◽  
Lian Feng Zhang ◽  
Ping Wang
Keyword(s):  
Particle Filter ◽  
Level Set Method ◽  
Level Set ◽  
Curve Evolution ◽  
Motion Information ◽  
Processing Efficiency ◽  
Dynamic Background ◽  
Particle Filter Algorithm

The level set method (LSM) is one of the methods used frequently to get the precise contours of the targets when the background is dynamic. In order to use the motion information and improve the processing efficiency, an adaptive level set method (ALSM) is proposed. In this approach, the particle filter algorithm is used to track the targets, so we get the rough external contours and their centroids. Then the level set curve evolution is performed to get the precise external contours of the targets. Lastly, the detection results are fed back to the tracking frame to revise the updating regions. The experiment results show that the proposed algorithm can adapt to the motion variations of the targets, and distinguish the targets.

A mutual information‐based likelihood function for particle filter flood extent assimilation

2021 ◽  
Author(s):  
Antara Dasgupta ◽  
Renaud Hostache ◽  
RAAJ Ramasankaran ◽  
Guy J.‐P Schumann ◽  
Stefania Grimaldi ◽  
...  
Keyword(s):  
Mutual Information ◽  
Particle Filter ◽  
Likelihood Function

Visual Tracking of an Object with its Motion Information

2009 ◽  
Vol 129 (5) ◽  
pp. 977-984
Author(s):  
Atsutoshi Shimeno ◽  
Seiichi Uchida ◽  
Ryo Kurazume ◽  
Rin-ichiro Taniguchi ◽  
Tsutomu Hasegawa
Keyword(s):  
Visual Tracking ◽  
Motion Information

Tracking of Ocean-Floor Organisms Using a Particle Filter

2013 ◽  
Vol 133 (2) ◽  
pp. 116-125
Author(s):  
Takeshi Nishida ◽  
Shinichi Sagara ◽  
Fumiaki Takemura
Keyword(s):  
Particle Filter ◽  
Ocean Floor
Sign in / Sign up

Export Citation Format

Share Document