Application of Bayesian a Priori Distributions for Vehicles’ Video Tracking Systems

2010 ◽  
pp. 347-355 ◽  
Author(s):  
Przemysław Mazurek ◽  
Krzysztof Okarma
Keyword(s):  
A Priori ◽  
Video Tracking ◽  
Tracking Systems

Noise parameter identification for video tracking systems

2017 ◽  
Vol 72 (2) ◽  
pp. 40-47
Author(s):  
T. Yu. Bokov ◽  
A. G. Yakushev
Keyword(s):  
Parameter Identification ◽  
Video Tracking ◽  
Tracking Systems ◽  
Noise Parameter

scholarly journals Predicting Sagittal Plane Lifting Postures From Image Bounding Box Dimensions

2018 ◽  
Vol 61 (1) ◽  
pp. 64-77 ◽  
Author(s):  
Runyu L. Greene ◽  
Yu Hen Hu ◽  
Nicholas Difranco ◽  
Xuan Wang ◽  
Ming-Lun Lu ◽  
...  
Keyword(s):  
Sagittal Plane ◽  
A Priori ◽  
Regression Tree ◽  
Video Tracking ◽  
Classification And Regression Tree ◽  
Handheld Devices ◽  
Bounding Box ◽  
Wide Range ◽  
Four Levels ◽  
Bounding Boxes

Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination. Background: Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle. Methods: Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures. Results: The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing. Conclusions: The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes. Applications: It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners.

A Fast Search Coil Sensing Method for Tracking Systems

2005 ◽  
Vol 295-296 ◽  
pp. 601-606
Author(s):  
Z.J. Cai ◽  
Li Jiang Zeng
Keyword(s):  
Real Time ◽  
Video Tracking ◽  
Flight Performance ◽  
Tracking Systems ◽  
Feedback Information ◽  
Magnetic Device ◽  
Fast Search ◽  
Search Coil

It is important to track a free flying insect to investigate its flight performance. Conventional video tracking systems are difficult to track a highly maneuverable insect, because the capture frequency of the camera is limited and it can hardly get the position of the insect in real time. We proposed a fast sensing method for insect tracking based on magnetic search coil sensors. It can simultaneously determine the orientation and position of the sensors. We constructed a system, calibrated the magnetic device. We developed a set of calculating methods and measured several positions and angles of coil sensors. The results show that it can rapidly provide the tracking feedback information to meet the requirement for insect tracking.

scholarly journals Football-specific validity of TRACAB’s optical video tracking systems

PLoS ONE ◽  
2020 ◽  
Vol 15 (3) ◽  
pp. e0230179 ◽  
Author(s):  
Daniel Linke ◽  
Daniel Link ◽  
Martin Lames
Keyword(s):  
Video Tracking ◽  
Tracking Systems

scholarly journals Video tracking of swimming rodents on a reflective water surface

2015 ◽  
Vol 1 (1) ◽  
pp. 232-235
Author(s):  
Olaf Christ ◽  
Ulrich G. Hofmann
Keyword(s):  
Animal Models ◽  
Spatial Memory ◽  
Brain Stimulation ◽  
Background Subtraction ◽  
Water Surface ◽  
Video Camera ◽  
Video Tracking ◽  
Tracking Systems ◽  
Ambient Lighting ◽  
The Waves

AbstractAnimal models are an essential testbed for new devices on their path from the bench to the patient. Potential impairments by brain stimulation are often investigated in water mazes to study spatial memory and learning. Video camera based tracking systems exist to quantify rodent behaviour, but reflections of ambient lighting on the water surface and artefacts due to the waves caused by the swimming animal cause errors. This often requires tweaking of algorithms and parameters, or even potentially modifying the lab setup. In the following, we provide a simple solution to alleviate these problem using a combination of region based tracking and independent multimodal background subtraction (IMBS) without hav ing to tweak a plethora of parameters.

Algorithm development for real-time automatic video tracking systems

2005 ◽  
Author(s):  
R.J. Schalkoff ◽  
E.S. McVey
Keyword(s):  
Real Time ◽  
Video Tracking ◽  
Tracking Systems ◽  
Algorithm Development

A Reliability Assessment Paradigm for Automated Video Tracking Systems

2010 ◽  
Author(s):  
Chung-Hao Chen ◽  
Yi Yao ◽  
Andreas Koschan ◽  
Mongi Abidi
Keyword(s):  
Reliability Assessment ◽  
Video Tracking ◽  
Tracking Systems ◽  
Automated Video Tracking

3-D Dynamic Displacement Field Model and Its Application to Video Tracking Systems

2011 ◽  
Vol 30 (11) ◽  
pp. 2784-2787
Author(s):  
Yan Liu ◽  
Mou-yan Zou
Keyword(s):  
Displacement Field ◽  
Field Model ◽  
Video Tracking ◽  
Tracking Systems ◽  
Dynamic Displacement
Sign in / Sign up

Export Citation Format

Share Document