People Detection by a Mobile Robot Using Stereo Vision in Dynamic Indoor Environments

Mendez-Polanco, J.A.; Muñoz-Meléndez, Angélica; Morales, Eduardo F.

doi:10.1007/978-3-642-05258-3_31

Cited by 7 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As future work we propose to integrate schemes to object segmentation for dynamic environments. For instance, using an object segmentation based on distance as in Méndez-Polanco et al, 2009. Use a different set of features and identify possible conflicts be-tween more that two kind of features.…”

Section: Discussionmentioning

confidence: 99%

Collective Learning of Concepts Using a Robot Team

Palacios-García

Muñoz-Meléndez

Morales

2010

Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

Autonomous learning of objects using visual information is important to robotics as it can be used for local and global localization problems, and for service tasks such as searching for objects in unknown places. In a robot team, the learning process can be distributed among robots to reduce training time and produce more accurate models. This paper introduces a new learning framework where individual representations of objects are learned on-line by a robot team while traversing an environment without prior knowledge on the number or nature of the objects to learn. Individual concepts are shared among robots to improve their own concepts, combining information from other robots that saw the same object, and to acquire a new representation of an object not seen by the robot. Since the robots do not know in advance how many objects they will encounter, they need to decide whether they are seeing a new object or a known object. Objects are characterized by local and global features and a Bayesian approach is used to combine them, and to recognize objects. We empirically evaluated our approach with a real world robot team with very promising results.

show abstract

Section: Discussionmentioning

confidence: 99%

Collective Learning of Concepts Using a Robot Team

Palacios-García

Muñoz-Meléndez

Morales

2010

Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

show abstract

“…Stereo vision is applied to obtain distance information of an object with respect to the observer. There have been previous works estimating the position of a person relative to a robot for tracking purposes (Méndez-Polanco, Muñoz Meléndez, & Morales, 2009), and to compute distance information in order to build a map for navigation (Murray & Little, 2000). In both cases, distance estimation based on stereovision focuses on the distance between the target object and the observer.…”

Section: Introductionmentioning

confidence: 99%

Burrow-centric distance-estimation methods inspired by surveillance behavior of fiddler crabs

Kim

2012

Adaptive Behavior

View full text Add to dashboard Cite

There are several ways to estimate the distance to an object based on visual information. Many robotic systems compute object distances based on disparity values or motion information. In addition to a disparity cue or image motion, research has shown that animals can possibly estimate the distance using the image size as well as the azimuth and elevation angles in their visual field. In this paper, inspired by the vigilance behavior of fiddler crabs, we suggest distanceestimation methods with several visual cues for engineering applications. A foraging fiddler crab can estimate the distance of an intruder from the burrow entrance. If the intruder is close to the burrow, the crab rushes back home to maintain possession of the burrow. In this study, we investigated burrow-centered distance-estimation methods based on visual information such as the retinal position, that is, the azimuth and elevation angles in an omnidirectional view as well as the image size and retinal speed of a target object. The methods show potential for engineering applications to the surveillance problem.

show abstract