Stereo Vision Depth Estimation Methods for Robotic Applications

Stereo Vision Depth Estimation Methods for Robotic Applications

Lazaros Nalpantidis, Antonios Gasteratos
Copyright: © 2014 |Pages: 21
DOI: 10.4018/978-1-4666-4607-0.ch071
(Individual Chapters)
No Current Special Offers


Vision is undoubtedly the most important sense for humans. Apart from many other low and higher level perception tasks, stereo vision has been proven to provide remarkable results when it comes to depth estimation. As a result, stereo vision is a rather popular and prosperous subject among the computer and machine vision research community. Moreover, the evolution of robotics and the demand for vision-based autonomous behaviors has posed new challenges that need to be tackled. Autonomous operation of robots in real working environments, given limited resources requires effective stereo vision algorithms. This chapter presents suitable depth estimation methods based on stereo vision and discusses potential robotic applications.
Chapter Preview

Issues Of Robotics-Oriented Stereo Vision

While a heavily investigated problem, stereo correspondence is far from being solved. Furthermore, the recent advances in robotics and related technologies have placed more challenges and stricter requirements to the issue. However, common problems related to outdoor exploration, such as possible decalibration of the stereo system and tolerance to non-perfect lighting conditions, have been barely addressed. Robotic applications demand stereo correspondence algorithms to be able to cope with not ideally captured images of the working environments of the robots (see Figure 1) and at the same time to be able to provide accurate results operating in real-time frame rates. Some of the open issues of robotics-oriented stereo vision methods are the handling of non-ideal lighting conditions, the requirement for simple calculation schemes, the use of multi-view stereo systems, the handling of miscalibrated image sensors, and the introduction of new biologically inspired methods to robotic vision.

Figure 1.

Robots equipped with stereo cameras in a real environments


Complete Chapter List

Search this Book: