Abstract: Image analysis is used to map objects in an arrangement. For example, images of a retail shelf are used to map items for sale on the retail shelf A first vector can used to identify a relative position of a first item on a shelf to a shelving diagram, and a second vector can be used to identify a relative position of a second on the shelf to the shelving diagram, using locations of optical codes (e.g., barcodes). Absolute positions can be calculated. In some configurations, multiple images having different fields of view are matched to an overview image.

Abstract: Visual odometry is used for tracking an optical pattern outside a preview area of a camera. The optical pattern is detected in a first image, while the camera is at a first position. A second image is acquired while the camera is at a second position. A transformation is calculated that relates the first position to the second position. A location of the optical pattern in relation to the second image is calculated based on the transformation. Calculation of the transformation can be simplified by assuming that the camera is moved in a plane parallel to a plane having multiple optical patterns.

Abstract: Depth information from a depth sensor, such as a LiDAR system, is used to correct perspective distortion for decoding an optical pattern in a first image acquired by a camera. Image data from the first image is spatially correlated with the depth information. The depth information is used to identify a surface in the scene and to distort the first image to generate a second image, such that the surface in the second image is parallel to an image plane of the second image. The second image is then analyzed to decode an optical pattern on the surface identified in the scene.

Abstract: Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.

Abstract: Image data from a camera and depth information from a depth sensor, such as a LiDAR system, are used to segment an image for decoding an optical pattern. The image data is spatially correlated with the depth information. The depth information is used to partition the image into one or more foreground segments and one or more background segments. Scanning for the optical pattern is performed on the one or more foreground segments.

Abstract: Image analysis is used to map objects in an arrangement. For example, images of a retail shelf are used to map items for sale on the retail shelf. A first vector can used to identify a relative position of a first item on a shelf to a shelving diagram, and a second vector can be used to identify a relative position of a second on the shelf to the shelving diagram, using locations of optical codes (e.g., barcodes). Absolution positions can be calculated. In some configurations, multiple images having different fields of view are matched to an overview image.

Abstract: Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.

Abstract: Image analysis is used to track multiple optical patterns, such as barcodes. Many applications are becoming web-based. However, web-based applications can have less computational resources than a native application. For example, a native application can be used to track barcodes based on decoding barcodes from a plurality of images. However, decoding barcodes can be computationally intense and cause lag when moved to a web-based platform. To reduce computational resources used for decoding barcodes, barcodes are tracked in several frames and decoded only periodically for a web-based application used to decode barcodes. Positions of barcodes can be tracked relative to each other to form a digital shelf. The digital shelf can be used to visualize a state of a shelf.