Abstract: A method of barrier detection in an imaging controller includes: obtaining an image of a support structure configured to support a plurality of items on a support surface extending between a shelf edge and a shelf back; extracting frequency components representing pixels of the image; based on the extracted frequency components, identifying a barrier region of the image, the barrier region containing a barrier adjacent to the shelf edge; and detecting at least one empty sub-region within the barrier region, wherein the empty sub-region is free of items between the barrier and the shelf back.

Abstract: A method of barrier detection in an imaging controller includes: obtaining an image of a support structure configured to support a plurality of items on a support surface extending between a shelf edge and a shelf back; extracting frequency components representing pixels of the image; based on the extracted frequency components, identifying a barrier region of the image, the barrier region containing a barrier adjacent to the shelf edge; and detecting at least one empty sub-region within the barrier region, wherein the empty sub-region is free of items between the barrier and the shelf back.

Abstract: A method in an imaging controller of detecting depth sensor artifacts includes: obtaining, from first and second sensors, first and second pluralities of points defined by respective (i) planar positions and depths in a common frame of reference, and (ii) scan angles relative to field of view centers of the first or second sensors; for each of a subset of candidate points from the first plurality of points: searching the second plurality of points for a validator point having (i) a planar position within a threshold distance of a planar position of the candidate point, and (ii) a scan angle smaller than a scan angle of the candidate point; responsive to identifying the validator point: when the depth of the validator point exceeds the depth of the candidate point, classifying the candidate point as an artifact.

Abstract: A method in an imaging controller of detecting depth sensor artifacts includes: obtaining, from first and second sensors, first and second pluralities of points defined by respective (i) planar positions and depths in a common frame of reference, and (ii) scan angles relative to field of view centers of the first or second sensors; for each of a subset of candidate points from the first plurality of points: searching the second plurality of points for a validator point having (i) a planar position within a threshold distance of a planar position of the candidate point, and (ii) a scan angle smaller than a scan angle of the candidate point; responsive to identifying the validator point: when the depth of the validator point exceeds the depth of the candidate point, classifying the candidate point as an artifact.

Abstract: A device, system and method for generating updated camera-projector correspondences from a reduced set of test patterns is provided. When a predetermined correspondences between projector points and camera points in an initial relative position of a projector and a camera have been previously determined, a recalibration therebetween may occur by projecting a single test pattern derived from the predetermined correspondences to estimate movement therebetween. When the movement is too great to be estimated by a single test pattern, another test pattern may be projected to determine an estimation function for the movement and in particular, estimate movement of one or more camera points in the projected images due to relative movement of the projector and the camera from the initial relative position to a current relative position.

Abstract: A device, system and method for generating updated camera-projector correspondences from a reduced set of test patterns is provided. When a predetermined correspondences between projector points and camera points in an initial relative position of a projector and a camera have been previously determined, a recalibration therebetween may occur by projecting a single test pattern derived from the predetermined correspondences to estimate movement therebetween. When the movement is too great to be estimated by a single test pattern, another test pattern may be projected to determine an estimation function for the movement and in particular, estimate movement of one or more camera points in the projected images due to relative movement of the projector and the camera from the initial relative position to a current relative position.

Abstract: A computer-implemented method for combining two 3-dimensional ultrasound images of a patient's body part containing blood vessels into a single 3-dimensional ultrasound image of that body part with a greater field of view. Blood vessels within the body part are used for registration. The two ultrasound images are preprocessed using a vessel enhancement algorithm to derive two corresponding enhanced images. The enhanced images can undergo a registration process based upon minimizing a mean-square-difference metric to derive an enhanced rigid transform, which represents a transform that maps the first enhanced image onto the second enhanced image. The two enhanced images are seamlessly combined via a blending process (via the use of a distance transform based weighting of the voxel values) to derive an output image.

Abstract: A device, system and method for automatic calibration of image devices is provided. Triplets of at least three image devices, including a projector, are in non-collinear arrangements, and pairs of the image devices have overlapping fields of view on a physical object. Pixel correspondences between the pairs are used to determine relative vectors between the image devices. Relative locations between each of the image devices are determined based on the relative vectors with a relative distance between one pair of the image devices is to an arbitrary distance, the relative locations being further relative to a cloud-of-points representing the object. A model of the object and the cloud-of-points are aligned to transform the relative locations of each of the image devices to locations relative to the model. The projector is controlled to project onto the object based at least on the locations relative to the model.

Abstract: A method for registering ultrasound (US) and computed tomography (CT) images, comprising: receiving US and CT images representative of a body portion comprising blood vessels and an initial approximate transform; enhancing the blood vessels in the US and CT images, thereby obtaining an enhanced US and CT images; creating a point-set for a given one of the enhanced US and CT images; determining a final transform between the point-set and the other one of the enhanced US and CT images using the initial transform; applying the final transform to a given one of the US and CT images to align together a coordinate system of the US image and a coordinate system of the CT image, thereby obtaining a transformed image; and outputting the transformed image.

Abstract: A computer-implemented method for combining two 3-dimensional ultrasound images of a patient's body part containing blood vessels into a single 3-dimensional ultrasound image of that body part with a greater field of view. Blood vessels within the body part are used for registration. The two ultrasound images are preprocessed using a vessel enhancement algorithm to derive two corresponding enhanced images. The enhanced images can undergo a registration process based upon minimizing a mean-square-difference metric to derive an enhanced rigid transform, which represents a transform that maps the first enhanced image onto the second enhanced image. The two enhanced images are seamlessly combined via a blending process (via the use of a distance transform based weighting of the voxel values) to derive an output image.

Abstract: A system and method for aligning stacked projectors is provided. A computing device is in communication with at least two projectors, configured to project images stacked onto each other, and at least one sensor configured to acquire respective images the projector images. Respective initial positions in a common space are determined of each of the projector images, from the sensor images, as well as a virtual projector image located at a common target position. Respective transforms for each of the projector images to one or more of shift and transform the projector images to the common target position of the virtual projector image. The respective transforms are applied to further first projector images to produce respective transformed projector images. The projectors are controlled to project the respective transformed projector images according to the common target position.

Abstract: A system and method for advanced lens geometry fitting is provided for projecting images using a projector with a non-planar lens. An initial estimate of intrinsic parameters of the projector can be determined, for example from a list; an initial estimate of extrinsic parameters of the projector can be determined based on the initial estimate of intrinsic parameters. The intrinsic parameters and extrinsic parameters can be optimized together by starting with a simple lens model and iteratively adding nonlinear terms, an error function evaluated at each iteration, for example for each set of intrinsic parameters in the list and the corresponding extrinsic parameters. As the values of the error function converges the optimized intrinsic parameters and the optimized extrinsic parameters can be used to generate images that are projected by the projector.