Abstract
After mechanization, the next disruptive technology in agriculture will probably be robotization. The introduction of information technology and automation in farm fields started in the eighties with the advent of the Global Positioning System (GPS) and the subsequent development of Precision Agriculture. While being indispensable for many innovative applications, global positioning is not sufficient for all situations encountered in the field, where local sensing is essential if accurate and updated, information has to control automated vehicles. Safeguarding, high resolution mapping, and real time monitoring can only be achieved with local perception sensors such as cameras, lasers, and sonar rangers. However, machine vision offers multiple advantages over other sensing alternatives, and among imaging sensors, stereo vision provides the richest source of information for real time actuation. This chapter presents an overview of current and future applications of 3D stereo vision to off-road intelligent vehicles, with special emphasis in real problems found in agricultural environments and practical solutions devised to cope with them, as image noise, system configuration, and 3D data management. Several examples of stereo perception engines implemented in robotized off-road vehicles illustrate the concepts introduced along the chapter.
TopBackground
Although the principles of stereoscopy have been known since the nineteen century, the availability of commercial stereo cameras only dates from the turn of this century. The processing speed of current computers allows the execution of algorithms that can correlate two stereo images and generate a depth map in real time. The level of detail and amount of information supplied by stereoscopic perception has placed stereo-based devices in a privileged position among other sensors used in field robotics. Mars exploration (Olson et al., 2003) and defense mobile robots like Urbie rely on stereo cameras to acquire critical information of remote and often hazardous environments. The application of 3D vision technology to agricultural vehicles, in spite of having a high potential (Rovira-Más, 2003), is still in its infancy. Some timid efforts have been made to apply the idea of stereoscopy to automatically locate fruits in plants (Kondo et al., 1996), but human intervention has been normally required to assist in pixel matching. Real time stereo-based perception for mobile robots is relatively recent, and although some solutions have been successfully developed for small indoor robots (Herath et al., 2006) and on-highway vehicles (Kato et al., 1996), the scenarios typically perceived in these applications are substantially different from those encountered by off-road vehicles; therefore, the latter demand specific solutions motivated by very distinctive needs. Even the off-road prototypes that participated in the DARPA Grand Challenge competition, organized by the United States Department of Defense, were set to fulfill elaborated missions that nothing have to do with habitual agronomical tasks (Kogler et al., 2006).