Determining object structure using physically mounted devices with only partial view of object

Abstract

Techniques are described for automated analysis and use of data acquired about an object of interest, such as from a physically mounted camera or other sensing device with only partial coverage of the object exterior, such as to automatically generate a computer model of the object from visual data in images and to use the computer model to automatically estimate values for one or more object attributes. For example, the described techniques may be used to measure the volume of a pile of material significantly larger than a human using images acquired by one or more fixed-location cameras that provide visual coverage of only a subset of the pile's exterior. The images from such physically mounted devices may be acquired at various times (e.g., when triggered by conditions in the environment of the object, dynamically upon request, etc.), and may be used to monitor changes in the object.