A Stereovision Sensor for Forest Inventories

This paper describes a device, based on stereovision, which is designed for forest inventories purposes. It captures pairs of omni-directional stereoscopic images through a fish-eye lens, from which different tri-dimensional measures can be obtained by applying a stereovision process, including image acquisition, feature and attribute extraction, feature matching and depth determination. This paper explains and summarizes two specific methods for solving the matching problem, as the key step in stereovision. They are pixel-based and region-based, applied in two kinds of forests environments, the first one highly illuminated and the second one with poor illumination. The performance achieved validates both designs.