Abstract: Described is a multiple-camera system and process for re-identifying a user located in a materials handling facility based on user patterns and/or descriptors representative of the user. In one implementation, a user pattern and/or a plurality of descriptors representative of a user are maintained as a position of a user is tracked through a materials handling facility. If the tracking of the user is lost, the last known position is stored with the user pattern and/or descriptors. If a new object is detected and confirmed to be a user, a user pattern and/or descriptors of the new object are compared with the stored user pattern and/or descriptors to determine if the new object is the user.

Abstract: Markers may be presented on different objects in a facility, such as shelves or totes. A marker can use color, placement of elements, blending effects, or infrared light layers to encode data about the object. During operation, a camera within the facility may acquire an image, which includes an image of the marker as presented on the object. The marker can be analyzed to detect marker data encoded therein. By decoding the marker data, details about the marker can be extracted, such as an identification of the object. In addition, using details about the marker location within the image and location data associated with the camera, a location of the object relative to the camera can be determined, as well as an orientation of the object relative to the camera. As the object moves within the facility, the object can be tracked based on this location and orientation data.

Abstract: Cameras may be used to acquire information about objects in three-dimensional (3D) space. Described herein are techniques for determining a calibration between pixel coordinates in a two-dimensional image acquired by the camera and coordinates in the 3D space. In one implementation, the target assembly is positioned at a known 3D location and particular optical targets thereon having known 3D coordinates are activated sequentially. Images are acquired and processed to determine the pixel coordinates of the respective optical targets. Calibration data, such as a transformation matrix, is generated based on the information about which optical target is active in a given acquired image, the pixel coordinates of the optical target in that acquired image, and the known 3D coordinates of the individual optical target.

Abstract: Machine-readable optical markers may be presented on a surface of a shelf, on a display device, or on a structure. Markers are presented as an array of graphical elements arranged in rows and columns. The graphical elements in the array of the mark utilize color and placement to encode marker data. In addition, a source image graphic may also be blended with a portion of the graphical elements in the array to create a blended image. In other embodiments, the marker may be presented with one or more borders surrounding the perimeter of the graphical elements in the array. The marker data may be presented using infrared light with a visible light layer presented over the array of graphical elements.

Abstract: Described is a multiple-camera system and process for re-identifying a user located in a materials handling facility based on user patterns and/or descriptors representative of the user. In one implementation, a user pattern and/or a plurality of descriptors representative of a user are maintained as a position of a user is tracked through a materials handling facility. If the tracking of the user is lost, the last known position is stored with the user pattern and/or descriptors. If a new object is detected and confirmed to be a user, a user pattern and/or descriptors of the new object are compared with the stored user pattern and/or descriptors to determine if the new object is the user.

Abstract: Described is a multiple-camera system and process for re-identifying a user located in a materials handling facility based on user patterns and/or descriptors representative of the user. In one implementation, a user pattern and/or a plurality of descriptors representative of a user are maintained as a position of a user is tracked through a materials handling facility. If the tracking of the user is lost, the last known position is stored with the user pattern and/or descriptors. If a new object is detected and confirmed to be a user, a user pattern and/or descriptors of the new object are compared with the stored user pattern and/or descriptors to determine if the new object is the user.

Abstract: Described are systems and techniques for using machine-readable optical markers to calibrate a machine vision system. In one implementation, the machine vision system may generate calibration data associating spatial coordinates with image coordinates of the machine-readable marker in an image acquired by a camera. The machine-readable marker may comprise a blend of an optical code that encodes marker data and a human-readable source graphic image. In some implementations, the optical code of the markers may be detectable under infrared light while remaining invisible to the unaided eye.

Abstract: Systems involving a plurality of cameras with clocks may not remain time synchronized during operation. Described in this disclosure are techniques for synchronizing one or more of the clocks of a plurality of cameras or the images produced by the plurality of cameras. In one implementation, a timestamp projector produces an optical timestamp encoding data indicative of timing. One or more cameras may acquire images of a scene that include the optical timestamp. The images may be processed to recover the data indicative of timing. This data may be used to set the clock of the camera, set timestamps associated with the images for subsequent use, and so forth.