Using Cumulative Histogram Maps in an Adaptive Color-Based Particle Filter for Real-Time Object Tracking

2010 ◽  
Vol 121-122 ◽  
pp. 585-590 ◽  
Author(s):  
San Lung Zhao ◽  
Shen Zheng Wang ◽  
Hsi Jian Lee ◽  
Hung I Pai
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
Tracking System ◽  
Target Object ◽  
Color Histogram ◽  
Human Tracking ◽  
Speed Up ◽  
Non Gaussian ◽  
The Cost ◽  
Gaussian Estimation

The study presents a human tracking system. To tracking a person, we adopt a particle filter as tracking kernel, since the method has proven successful for tracking in non-linear and non-Gaussian estimation. In a particle filter, a set of weighted particles represents the possible target sates. In this study, we measure the weight according to both the appearances of the target object and background scene to improve the discriminability between them. In our tracker, the appearances are modeled as color histogram, since it is scale and rotation invariant. However, the color histogram extraction for a large number of overlap regions is repeated redundantly and inefficiently. To speed up it, we reduce the cost for calculating overlapped regions by creating a cumulative histogram map for the processing image. The experimental results show that the tracker has the best precision improvement, and the tracking speed is 49.7 fps for 384 × 288 resolution, when we use 600 particles. The results show that the proposed method can be applied to a real-time human tracking system with high precision.

scholarly journals Cloud-Based Vehicle Tracking System

2020 ◽  
Vol 2 (4) ◽  
pp. 21-30
Author(s):  
Ali Mustafa ◽  
Mohammed I. Aal-Nouman ◽  
Osama A. Awad
Keyword(s):  
Real Time ◽  
Tracking System ◽  
Large Data ◽  
Vehicle Tracking ◽  
General Packet Radio Service ◽  
Remote Server ◽  
Real Time Tracking ◽  
The Cost ◽  
Police Vehicles ◽  
Vehicle Tracking System

 The need for vehicle tracking system in real time is growth continues due to increase the cases of theft. This type of system in real time needs to transmit large data with huge number of HTTP request to the server to keep tracking and monitoring in real time, thus causes spend extremely high cost every month for transportation the information on tracking vehicles to server therefor the needs for reducing the number of transportation and data size that transmits in each HTTP request to save expenses. This paper designed and implement an integrated vehicle tracking system in real time to track vehicle anywhere and anytime. This system is divided into two parts: vehicle tracking part and monitoring part. Tracking part is represented by installation the electronic devices in the vehicle using modern Global Positioning System (GPS), microcontroller Arduino UNO R3 and SIM800L GSM/GPRS modem. GPS is determined location of the vehicle via received coordinates from satellites such as latitude and latitude with accuracy ranging approximately 2.5 meters; the coordinates faked to add a type of protection to information on vehicles without effecting on characterizing real time tracking before sending it via a General Packet Radio service (GPRS). The monitoring part is in the cloud and will receive the coordinates and displays it on a map in a web page. The main contribution of this system is it reduced data size that sent from in-vehicle device via selected only necessary data for tracking vehicle from NEMA sentences of GPS and reduced number of HTTP request that sent to remote server via constrain the transmission of information with the movement of vehicles, since when vehicle moved the coordinates each 10s and did not send anything when the vehicle stopped thus will reduce the cost of expenses every month. This system can be utilized to track and monitoring the vehicles of large universities, companies, organization and also can be used in army vehicles and police vehicles.      

Pedestrian Detection and Tracking Based on Fast HOG and Time Varying System Particle Filter

2014 ◽  
Vol 568-570 ◽  
pp. 721-725
Author(s):  
Zuo Juan Liang ◽  
Chang Xu Dong Ye ◽  
Shan Shan Zhang ◽  
Yong Chen
Keyword(s):  
Real Time ◽  
Tracking System ◽  
Pedestrian Detection ◽  
Model Description ◽  
Uniform Motion ◽  
Low Level ◽  
System Equation ◽  
Single Feature ◽  
Time Problem ◽  
Speed Up

Pedestrians are quite visually different at multi-scale changes and view-point variations, which are crucial factors for detection. Firstly calculations of multiscale features of HOG(Histogram of Oriented Gradient) from video images are usually based on finer scale pyramid strategy, which is to figure out low-level features respectively at each scale level. This scheme has redundent information and worse real-time performance, which become urgent bottleneck in applications. A new fast scale pyramid strategy based on feature forecast algorithm was adopted according to [1], which can speed up low-level feature calculations and solve real-time problem fundamentally. Secondly a new tracking pedestrian algorithm was proposed, which combined local LBP(Local Binary Pattern) and HOG as a model description of the pedestrian target, the tracking system equation was improved according to the non-uniform motion of the pedestrian in order to enhance the effectiveness and the guidance of the particle propagation. The final experimental results show that this method is more robust than those based on single feature.

Real-time human tracking system with multiple omnidirectional vision sensors

2004 ◽  
Vol 35 (2) ◽  
pp. 79-90 ◽  
Author(s):  
Takushi Sogo ◽  
Hiroshi Ishiguro ◽  
Mohan M. Trivedi
Keyword(s):  
Real Time ◽  
Tracking System ◽  
Human Tracking ◽  
Omnidirectional Vision ◽  
Vision Sensors

scholarly journals Pipeline Gaussian Particle Filter and Hardware Design for Attitude Estimation with UAV

2020 ◽  
Vol 2020 ◽  
pp. 1-6 ◽  
Author(s):  
Yali Xue ◽  
Hu Chen ◽  
Jie Chen ◽  
Jiahui Wang
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
Gaussian Noise ◽  
Estimation Algorithm ◽  
Attitude Estimation ◽  
Estimation Accuracy ◽  
Gaussian State ◽  
Time Performance ◽  
Simulation Results ◽  
Non Gaussian

This paper based on the Gaussian particle filter (GPF) deals with the attitude estimation of UAV. GPF algorithm has better estimation accuracy than the general nonlinear non-Gaussian state estimation and is usually used to improve the system’s real-time performance whose noise is specific such as Gaussian noise during the mini UAV positioning and navigation. The attitude estimation algorithm is implemented on FPGA to verify the effectiveness of the Gaussian particle filter. Simulation results have illustrated that the GPF algorithm is effective and has better real-time performance than that of the particle filter.

scholarly journals An Adaptive Unscented Particle Filter Algorithm through Relative Entropy for Mobile Robot Self-Localization

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Wentao Yu ◽  
Jun Peng ◽  
Xiaoyong Zhang ◽  
Shuo Li ◽  
Weirong Liu
Keyword(s):  
Nonlinear System ◽  
Particle Filter ◽  
State Estimation ◽  
Real Time ◽  
Relative Entropy ◽  
Gaussian Noise ◽  
The Real ◽  
Unscented Particle Filter ◽  
Non Gaussian ◽  
Number Of Particles

Self-localization is a basic skill for mobile robots in the dynamic environments. It is usually modeled as a state estimation problem for nonlinear system with non-Gaussian noise and needs the real-time processing. Unscented particle filter (UPF) can handle the state estimation problem for nonlinear system with non-Gaussian noise; however the computation of UPF is very high. In order to reduce the computation cost of UPF and meanwhile maintain the accuracy, we propose an adaptive unscented particle filter (AUPF) algorithm through relative entropy. AUPF can adaptively adjust the number of particles during filtering to reduce the necessary computation and hence improve the real-time capability of UPF. In AUPF, the relative entropy is used to measure the distance between the empirical distribution and the true posterior distribution. The least number of particles for the next step is then decided according to the relative entropy. In order to offset the difference between the proposal distribution, and the true distribution the least number is adjusted thereafter. The ideal performance of AUPF in real robot self-localization is demonstrated.

Sign in / Sign up

Export Citation Format

Share Document