A Real-Time Compressive Tracking System for Amphibious Spherical Robots

2018 ◽  
pp. 390-409
Author(s):  
Shuxiang Guo ◽  
Liwei Shi
Keyword(s):  
High Speed ◽  
Tracking System ◽  
Microsoft Kinect ◽  
Depth Cameras ◽  
Compressive Tracking ◽  
Depth Images ◽  
Working Environments ◽  
Robotic Tracking ◽  
Prediction Mechanism ◽  
Amphibious Robot

Given the special working environments and application functions of the amphibious robot, an improved RGB-D visual tracking algorithm with dual trackers is proposed and implemented in this chapter. Compressive tracking (CT) was selected as the basis of the proposed algorithm to process colour images from a RGB-D camera, and a Kalman filter with a second-order motion model was added to the CT tracker to predict the state of the target, select candidate patches or samples, and reinforce the tracker's robustness to high-speed moving targets. In addition, a variance ratio features shift (VR-V) tracker with a Kalman prediction mechanism was adopted to process depth images from a RGB-D camera. A visible and infrared fusion mechanism or feedback strategy is introduced in the proposed algorithm to enhance its adaptability and robustness. To evaluate the effectiveness of the algorithm, Microsoft Kinect, which is a combination of colour and depth cameras, was adopted for use in a prototype of the robotic tracking system.

Do elite soccer players cover longer distance when losing? Differences between attackers and defenders

2020 ◽  
pp. 174795412098227
Author(s):  
Carlos Lago-Peñas ◽  
Anton Kalén ◽  
Miguel Lorenzo-Martinez ◽  
Roberto López-Del Campo ◽  
Ricardo Resta ◽  
...  
Keyword(s):  
New York ◽  
High Speed ◽  
Large Scale ◽  
Tracking System ◽  
Soccer Players ◽  
Running Performance ◽  
Situational Variables ◽  
Total Distance ◽  
Professional Soccer ◽  
Score Line

This study aimed to evaluate the effects playing position, match location (home or away), quality of opposition (strong or weak), effective playing time (total time minus stoppages), and score-line on physical match performance in professional soccer players using a large-scale analysis. A total of 10,739 individual match observations of outfield players competing in the Spanish La Liga during the 2018–2019 season were recorded using a computerized tracking system (TRACAB, Chyronhego, New York, USA). The players were classified into five positions (central defenders, players = 94; external defenders, players = 82; central midfielders, players = 101; external midfielders, players = 72; and forwards, players = 67) and the following match running performance categories were considered: total distance covered, low-speed running (LSR) distance (0–14 km · h−1), medium-speed running (MSR) distance (14–21 km · h−1), high-speed running (HSR) distance (>21 km · h−1), very HSR (VHSR) distance (21–24 km · h−1), sprint distance (>24 km · h−1) Overall, match running performance was highly dependent on situational variables, especially the score-line condition (winning, drawing, losing). Moreover, the score-line affected players running performance differently depending on their playing position. Losing status increased the total distance and the distance covered at MSR, HSR, VHSR and Sprint by defenders, while attacking players showed the opposite trend. These findings may help coaches and managers to better understand the effects of situational variables on physical performance in La Liga and could be used to develop a model for predicting the physical activity profile in competition.

Study on Driver and Vehicle System With Lane-Tracking Control System Using Steering Torque Input

2001 ◽  
Author(s):  
Masao Nagai ◽  
Hidehisa Yoshida ◽  
Kiyotaka Shitamitsu ◽  
Hiroshi Mouri
Keyword(s):  
Tracking Control ◽  
High Speed ◽  
Driving Simulator ◽  
Tracking System ◽  
Torque Control ◽  
Steering Wheel ◽  
Control Input ◽  
Steering Angle ◽  
Lane Tracking ◽  
Steering Torque

Abstract Although the vast majority of lane-tracking control methods rely on the steering wheel angle as the control input, a few studies have treated methods using the steering torque as the input. When operating vehicles especially at high speed, drivers typically do not grip the steering wheel tightly to prevent the angle of the steering wheel from veering off course. This study proposes a new steering assist system for a driver not with the steering angle but the steering torque as the input and clarifies the characteristics and relative advantages of the two approaches. Then using a newly developed driving simulator, characteristics of human drivers and the lane-tracking system based on the steering torque control are investigated.

scholarly journals High Speed Running and Sprinting Profiles of Elite Soccer Players

2017 ◽  
Vol 58 (1) ◽  
pp. 169-176 ◽  
Author(s):  
Javier Miñano-Espin ◽  
Luis Casáis ◽  
Carlos Lago-Peñas ◽  
Miguel Ángel Gómez-Ruano
Keyword(s):  
Physical Performance ◽  
High Intensity ◽  
Repeated Measures ◽  
High Speed ◽  
Tracking System ◽  
Camera Tracking ◽  
The Real ◽  
Multiple Camera ◽  
Repeated Measures Analysis

AbstractReal Madrid was named as the best club of the 20th century by the International Federation of Football History and Statistics. The aim of this study was to compare if players from Real Madrid covered shorter distances than players from the opposing team. One hundred and forty-nine matches including league, cup and UEFA Champions League matches played by the Real Madrid were monitored during the 2001-2002 to the 2006-2007 seasons. Data from both teams (Real Madrid and the opponent) were recorded. Altogether, 2082 physical performance profiles were examined, 1052 from the Real Madrid and 1031 from the opposing team (Central Defenders (CD) = 536, External Defenders (ED) = 491, Central Midfielders (CM) = 544, External Midfielders (EM) = 233, and Forwards (F) = 278). Match performance data were collected using a computerized multiple-camera tracking system (Amisco Pro®, Nice, France). A repeated measures analysis of variance (ANOVA) was performed for distances covered at different intensities (sprinting (>24.0 km/h) and high-speed running (21.1-24.0 km/h) and the number of sprints (21.1-24.0 km/h and >24.0 km/h) during games for each player sectioned under their positional roles. Players from Real Madrid covered shorter distances in high-speed running and sprint than players from the opposing team (p < 0.01). While ED did not show differences in their physical performance, CD (p < 0.05), CM (p < 0.01), EM (p < 0.01) and F (p > 0.01) from Real Madrid covered shorter distances in high-intensity running and sprint and performed less sprints than their counterparts. Finally, no differences were found in the high-intensity running and sprint distances performed by players from Real Madrid depending on the quality of the opposition.

Dynamic vacuum pressure tracking control with high-speed on-off valves

2018 ◽  
Vol 232 (10) ◽  
pp. 1325-1336 ◽  
Author(s):  
Gang Yang ◽  
Kai Chen ◽  
Linglong Du ◽  
Jingmin Du ◽  
Baoren Li
Keyword(s):  
Mass Flow ◽  
Pulse Width ◽  
High Speed ◽  
Pulse Width Modulation ◽  
Sliding Mode ◽  
Tracking System ◽  
Vacuum Pressure ◽  
Chamber Pressure ◽  
Asymmetric Structure ◽  
The Impact

A vacuum pressure tracking system with high-speed on-off valves is a discontinuous system due to the discrete nature of high-speed on-off valves. Chamber pressure changes in the system are determined by the mass flow rates during the processes of charging and discharging. Here, a sliding mode controller with an asymmetric compensator based on average mass flow rate is designed for accurate vacuum pressure tracking. The controller output signal is converted into the duty cycles of the high-speed on-off valves via a pulse width modulation pulsing scheme. Owing to the extreme asymmetry of the processes, an asymmetric structure comprising one high-speed on-off valve in the charging unit and three high-speed on-off valves in the discharging unit is applied to weaken the impact of asymmetry. In addition, an asymmetric compensator is also designed to modify the pulse width modulation pulsing scheme to further eliminate the asymmetry. Experimental results indicate that the proposed controller achieves better performance in pressure tracking with the asymmetric compensator overcoming process asymmetry and enhancing system robustness.

scholarly journals Automatic Landmark Detection of Human Back Surface from Depth Images via Deep Learning

2021 ◽  
Author(s):  
Masumeh Delgarmi ◽  
Hamed Heravi ◽  
Ali Rahimpour Jounghani ◽  
Abdullah Shahrezie ◽  
Afshin Ebrahimi ◽  
...  
Keyword(s):  
Network Architecture ◽  
The Body ◽  
Microsoft Kinect ◽  
Training Data ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
X Rays ◽  
Depth Images ◽  
Physical Dysfunction ◽  
The Status

AbstractStudying human postural structure is one of the challenging issues among scholars and physicians. The spine is known as the central axis of the body, and due to various genetic and environmental reasons, it could suffer from deformities that cause physical dysfunction and correspondingly reduce people’s quality of life. Radiography is the most common method for detecting these deformities and requires monitoring and follow-up until full treatment; however, it frequently exposes the patient to X-rays and ionization and as a result, cancer risk is increased in the patient and could be highly dangerous for children or pregnant women. To prevent this, several solutions have been proposed using topographic data analysis of the human back surface. The purpose of this research is to provide an entirely safe and non-invasive method to examine the spiral structure and its deformities. Hence, it is attempted to find the exact location of anatomical landmarks on the human back surface, which provides useful and practical information about the status of the human postural structure to the physician.In this study, using Microsoft Kinect sensor, the depth images from the human back surface of 105 people were recorded and, our proposed approach - Deep convolution neural network-was used as a model to estimate the location of anatomical landmarks. In network architecture, two learning processes, including landmark position and affinity between the two associated landmarks, are successively performed in two separate branches. This is a bottom-up approach; thus, the runtime complexity is considerably reduced, and then the resulting anatomical points are evaluated concerning manual landmarks marked by the operator as the benchmark. Our results showed that 86.9% of PDJ and 80% of PCK. According to the results, this study was more effective than other methods with more than thousands of training data.

An Active Low Cost Mesh Networking Indoor Tracking System

2014 ◽  
Vol 6 (1) ◽  
pp. 45-79 ◽  
Author(s):  
Sean Carlin ◽  
Kevin Curran
Keyword(s):  
Tracking System ◽  
Low Cost ◽  
Cost Effective ◽  
Limiting Factors ◽  
Unique Contribution ◽  
Scalable Vector Graphics ◽  
Web Technologies ◽  
Working Environments ◽  
System A ◽  
The Cost

Indoor radio frequency tracking systems are generally quite expensive and can vary in accuracy due to interference, equipment quality or other environmental factors. Due to these limiting factors of the technology, many businesses today find it hard to justify investing in RFID tracking technologies to improve the safety, efficiency and security of their working environments. The aim of this project was to provide a budget RFID tracking system that was capable of tracking a person or object through an indoor environment. To minimize the cost of the RFID tracking system, the components of the system were built from existing electronic equipment and hardware. The software was also written to minimize licensing and support fees allowing a cost effective budget RFID tracking system to be developed. The tracking system consists of a tag, reader nodes and a PC reader which utilize synapse RF 100 engines with python scripts embedded on to the chips. The tracking system software operates through a web portal utilizing web technologies such as HTML, JavaScript and PHP to allow the tags location to be represented on a two dimensional map using scalable vector graphics. During development of the system a new trilateration algorithm was developed and used convert the signals received from the tag to a virtual position on the map correlating to the actual physical position of the tag. A unique contribution of this system is the low cost of building which we estimate as less than £200 UK sterling for a five node system.

Sign in / Sign up

Export Citation Format

Share Document