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.

Abstract: Techniques are described for automated analysis and use of images acquired of an object and of associated image acquisition metadata, such as for manmade largescale objects at fixed locations in outdoor environments, and to automatically generate a 3D computer model of the object (e.g., the 3D shape of the object exterior's surface) from visual data in the acquired images and from image acquisition device motion data during the image acquisition, to use the computer model to automatically determine measurements for object attribute(s), and to display or otherwise provide information about the generated computer model and/or determined object attributes. The image acquisition metadata may include motion data from IMU (inertial measurement unit) sensors on the image acquisition device, and include additional related data that is determined based at least in part on that motion data (e.g., acquisition pose data for particular acquired images, 3D positions on object exterior, etc.).

Abstract: Techniques are described for automated analysis and use of images acquired of an object and of associated image acquisition metadata, such as for manmade largescale objects at fixed locations in outdoor environments, and to automatically generate a 3D computer model of the object (e.g., the 3D shape of the object exterior's surface) from visual data in the acquired images and from image acquisition device motion data during the image acquisition, to use the computer model to automatically determine measurements for object attribute(s), and to display or otherwise provide information about the generated computer model and/or determined object attributes. The image acquisition metadata may include motion data from IMU (inertial measurement unit) sensors on the image acquisition device, and include additional related data that is determined based at least in part on that motion data (e.g., acquisition pose data for particular acquired images, 3D positions on object exterior, etc.).

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.

Abstract: Techniques are described for automated analysis and use of images acquired of an object of interest, such as from one or more fixed-location camera devices with only partial visual coverage of the object exterior, such as to automatically generate a computer model of the object from visual data in the 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 fixed-location cameras 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.