Research of Tracking and Prediction of Moving Object with Kalman

2014 ◽  
Vol 599-601 ◽  
pp. 1287-1290
Author(s):  
Zhong Yong Wang ◽  
Song Chao Yang
Keyword(s):  
Computer Simulation ◽  
Convex Hull ◽  
Optical Flow ◽  
Moving Objects ◽  
Test Results ◽  
Tracking Accuracy ◽  
Knowledge Use ◽  
Separation Problem ◽  
Forecasting Models ◽  
Harris Corner

This paper puts forward a complete track forecasting models, using Kalman filter to track and predict the movement of objects without prior knowledge. Use the extracted Harris corner to calculate optical flow between two frames by L-K pyramid method, getting the convex hull of moving objects by optical flow clustering to separate the moving objects from background. Tracking and predicting the gravity of moving objects convex hull can solve the occlusion and separation problem between moving objects. Computer simulation and field test results show that the proposed method has higher tracking accuracy, and small amount of calculation.

Moving Target Tracking Using Sparse Optical Flow Method

2013 ◽  
Vol 718-720 ◽  
pp. 2335-2339
Author(s):  
Tian Ding Chen ◽  
Jian Hu ◽  
Chao Lu ◽  
Zhong Jiao He
Keyword(s):  
Optical Flow ◽  
Target Tracking ◽  
New Method ◽  
Moving Target ◽  
Tracking Accuracy ◽  
Experimental Conditions ◽  
Moving Target Tracking ◽  
Research Production ◽  
Harris Corner ◽  
Comparison Results

Moving target tracking is a hot research spot of computer vision and applied in various fields. In this paper, a new tracking method base on sparse optical flow is put forward. In this method, targets are tracked through calculating the movements of Harris corner points, rather than the movements of all pixel points. Experiments results show that the tracking effect of this new method is pretty good. Tracking accuracy can reach more than 80% in most experimental conditions. And according to other peoples research production, experiments based on dense optical flow are done to compare with the new method proposed in this paper. The comparison results show that the new method has high calculation efficiency. This indicates that the method has feasibility and practical value.

scholarly journals A Two-Stage Data Association Approach for 3D Multi-Object Tracking

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2894
Author(s):  
Minh-Quan Dao ◽  
Vincent Frémont
Keyword(s):  
Object Detection ◽  
Object Tracking ◽  
Moving Objects ◽  
Data Association ◽  
Autonomous Driving ◽  
Tracking Accuracy ◽  
Two Stage ◽  
Bipartite Matching ◽  
3D Object ◽  
3D Object Detection

Multi-Object Tracking (MOT) is an integral part of any autonomous driving pipelines because it produces trajectories of other moving objects in the scene and predicts their future motion. Thanks to the recent advances in 3D object detection enabled by deep learning, track-by-detection has become the dominant paradigm in 3D MOT. In this paradigm, a MOT system is essentially made of an object detector and a data association algorithm which establishes track-to-detection correspondence. While 3D object detection has been actively researched, association algorithms for 3D MOT has settled at bipartite matching formulated as a Linear Assignment Problem (LAP) and solved by the Hungarian algorithm. In this paper, we adapt a two-stage data association method which was successfully applied to image-based tracking to the 3D setting, thus providing an alternative for data association for 3D MOT. Our method outperforms the baseline using one-stage bipartite matching for data association by achieving 0.587 Average Multi-Object Tracking Accuracy (AMOTA) in NuScenes validation set and 0.365 AMOTA (at level 2) in Waymo test set.

Robust Autonomous Car-Like Robot Tracking Based on Tracking-Learning-Detection

2014 ◽  
Vol 687-691 ◽  
pp. 564-571 ◽  
Author(s):  
Lin Bao Xu ◽  
Shu Ming Tang ◽  
Jin Feng Yang ◽  
Yan Min Dong
Keyword(s):  
Optical Flow ◽  
Fast Moving ◽  
Moving Objects ◽  
Tracking Algorithm ◽  
Robust Tracking ◽  
Symmetry Detection ◽  
Tracking Method ◽  
Robot Tracking ◽  
Improve Accuracy ◽  
First Time

This paper proposes a robust tracking algorithm for an autonomous car-like robot, and this algorithm is based on the Tracking-Learning-Detection (TLD). In this paper, the TLD method is extended to track the autonomous car-like robot for the first time. In order to improve accuracy and robustness of the proposed algorithm, a method of symmetry detection of autonomous car-like robot rear is integrated into the TLD. Moreover, the Median-Flow tracker in TLD is improved with a pyramid-based optical flow tracking method to capture fast moving objects. Extensive experiments and comparisons show the robustness of the proposed method.

scholarly journals Convex hull as a heuristic

2018 ◽  
Author(s):  
Naama Katzin
Keyword(s):  
Computer Simulation ◽  
Convex Hull ◽  
Physical Properties ◽  
Spatial Data ◽  
Good Predictor ◽  
Numerical Cognition ◽  
Numerical Estimation ◽  
Geometrical Properties ◽  
Numerical Discrimination ◽  
The Impact

Recent studies in the field of numerical cognition quantify the impact of physical properties of an array on its enumeration, demonstrating that enumeration relies on the perception of these properties. This paper marks a shift in reasoning as it changes the focus from demonstrating this effect to explaining it. Interestingly, we were inspired by one of the very first articles in the field, “The power of numerical discrimination” by Stanley Jevons that was published in Nature in 1871. In his report, Jevons attempts to answer the question of how many objects can be perceived in “a single mental beat of attention”. We relate directly to Jevons’s records, putting forward a plausible heuristic mechanism that relies on the physical geometrical properties of the arrays to be enumerated. We use a mathematical theorem and computer simulation to show that the shape of the convex hull, the smallest polygon containing all dots in an array, is a good predictor of numerosity. We show that convex hull downsamples the spatial data, allowing quick and fairly accurate numerical estimation. Moreover, convex hull predictability changes as numerosity grows, corresponding to the psychophysical curve of enumeration shown by Jevons and many others that followed.

scholarly journals Optical Flow Approach Followed by SVM Classification Model to Recognize Abnormal Behavior of a Crowd

2018 ◽  
Vol 7 (3.34) ◽  
pp. 156
Author(s):  
Basavaraj G.M ◽  
Dr Ashok Kusagur
Keyword(s):  
Optical Flow ◽  
Promising Result ◽  
Classification Model ◽  
Abnormal Behavior ◽  
Support Vector ◽  
Force Model ◽  
Feature Points ◽  
Crowd Behavior ◽  
Operating Characteristics ◽  
Harris Corner

A many of researches have been carried out in the field of the crowd behavior recognition system. Recognizing crowd behavior in videos is most challenging and occlusions because of irregular human movement. This paper gives an overview of optical flow model along with the SVM (Support Vector Machine) classification model. This proposed approach evaluates sudden changes in motion of an event and classifies that event to a category: Normal and Abnormal.  Geometric means of location, direction, and displacement of the feature points of each frame are estimated. Harris corner Detector is used in each frame for tracking a set of feature points. Proposed approach is very effective in real time scenario like public places where security is most important. After analyzing result ROC curve (receiver operating characteristics) is plotted which gives classification accuracy. We also presented frame level comparison with Ground truth and social force model (SFM) techniques. Our proposed approach is giving a promising result compare to all state of art methods.  

scholarly journals Object-Moving Robot Arm based on Color

2019 ◽  
Vol 1 (3) ◽  
pp. 13-19
Author(s):  
Areepen Sengsalong ◽  
Nuryono Satya Widodo
Keyword(s):  
Moving Objects ◽  
Robot Arm ◽  
Test Results ◽  
System Testing ◽  
Green Is

The aim of this research is to make a robot arm moving objects based on color using 2 servo motors and 6 light photodiode sensors integrated with the Arduino Mega 2560 microcontroller.  The light photodiode sensor is used to detect red, green and blue colors. This system is equipped with an LCD to display the output of the Arduino Mega 2560 which is a notice of the color detected. The process of moving objects based on color is simulated using 3 colored objects namely red, green, and blue. The robot arm gripper will move to pick and move objects based on color, when the light photodiode sensor detects a color input.  Based on system testing, overall the robot arm is functioning properly, i.e. it shows that the robot arm is able to move objects automatically with large test results obtained by 0 °, 40 °, 60 °, 90 °, and 120 °. Whereas for sensor testing the value of red is 400, the value of green is 150, and the value of blue is 600.

scholarly journals Accurate moving object segmentation in unconstraint videos based on robust seed pixels selection

2020 ◽  
Vol 17 (4) ◽  
pp. 172988142094727
Author(s):  
Wenlong Zhang ◽  
Xiaoliang Sun ◽  
Qifeng Yu
Keyword(s):  
Optical Flow ◽  
Moving Objects ◽  
Object Segmentation ◽  
Moving Object ◽  
Data Sets ◽  
Seed Selection ◽  
Current Frame ◽  
Moving Object Segmentation ◽  
Random Walker ◽  
Previous Frame

Due to the clutter background motion, accurate moving object segmentation in unconstrained videos remains a significant open problem, especially for the slow-moving object. This article proposes an accurate moving object segmentation method based on robust seed selection. The seed pixels of the object and background are selected robustly by using the optical flow cues. Firstly, this article detects the moving object’s rough contour according to the local difference in the weighted orientation cues of the optical flow. Then, the detected rough contour is used to guide the object and the background seed pixel selection. The object seed pixels in the previous frame are propagated to the current frame according to the optical flow to improve the robustness of the seed selection. Finally, we adopt the random walker algorithm to segment the moving object accurately according to the selected seed pixels. Experiments on publicly available data sets indicate that the proposed method shows excellent performance in segmenting moving objects accurately in unconstraint videos.

Sign in / Sign up

Export Citation Format

Share Document