Robust Real Time Color Tracking

Simon, Mark; Behnke, Sven; Rojas, Raúl

doi:10.1007/3-540-45324-5_22

Cited by 28 publications

(22 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The only physical sensors we use for behavior control are two S-Video cameras. 3 The cameras capture a view of the field from above and produce two output video streams, which are forwarded to the central PC. Images are captured by frame grabbers and passed to the vision module.…”

Section: System Architecturementioning

confidence: 99%

Predicting Away Robot Control Latency

Behnke

Egorova

Gloye

et al. 2004

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes a method to reduce the effects of the system immanent delay when tracking and controlling fast moving robots using a fixed video camera as sensor. The robots are driven by a computer with access to the video signal. The paper explains how we cope with system latency by predicting the movement of our robots using linear models and neural networks. We use past positions and orientations of the robot for the prediction, as well as the most recent commands sent. The setting used for our experiments is the same used in the small-size league of the RoboCup competition. We have successfully field-tested our predictors at several RoboCup events with our FU-Fighters team. Our results show that path prediction can significantly improve speed and accuracy of robotic play.

show abstract

Section: System Architecturementioning

confidence: 99%

Predicting Away Robot Control Latency

Behnke

Egorova

Gloye

et al. 2004

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…These models are robust under changing illumination, since they remain invariant over a wide dynamic range when the spectral energy of colored light changes by a constant multiplicative factor [8]. Some papers presenting vision systems with these color models include, for example, [2,4] on HSI, [1,7] on YUV, and [10,12,15] on RGB.…”

Section: Color Modelmentioning

confidence: 99%

“…As technology continues to improve, truly inexpensive possibilities emerge and set new challenges for research. In this work, instead of integrating a 3CCD color camera, DSP based frame grabber and other special hardware [4], the real-time vision problem was faced using a consumer-end web-cam (U$ 40). It is directly plugged into a Pentium III desktop computer through a USB 1.1 connection, which means that even the frame grabbing process must be done by software.…”

Section: Introductionmentioning

confidence: 99%

Low cost vision system for an educational platform in artificial intelligence and robotics

Martı́n

Chiang

2002

Comp Applic In Engineering

View full text Add to dashboard Cite

This paper presents a web-cam based vision system for performing image processing in real time. It was implemented as part of an AI and Robotics educational platform designed to study collaborative moving robots in a dynamic environment. A color based image segmentation algorithm was developed with careful attention to algorithm efficiency, due to hardware limitations for the maximum frame rate. This led to a simple and cost-effective vision system that is able to detect and identify several mobile robots through successive frames.

show abstract

“…For example, global vision systems for robotic soccer (e.g. (Bruce and Veloso, 2003;Browning et al, 2002;Simon et al, 2001;Ball et al, 2004)) generally require a camera to be mounted perfectly overhead in order to provide a simple geometric perspective (and thus ensure that any object is the same size in the image no matter where in the field of view it appears), simplify tracking, and eliminate complex problems such as occlusion between agents. If a camera cannot be placed perfectly overhead, these systems cannot be used.…”

Section: Introduction: Global Visionmentioning

confidence: 99%