Abstract: Methods and systems of locating an object of interest with a hyperspectral imaging system include placing a hyperspectral tag on the object of interest. A hyperspectral camera then then collects light emitted by an area of interest. An analyzer unit of the hyperspectral imaging system processes the collected light emitted by the area of interest into a hyperspectral image. The hyperspectral image includes a data file that includes information regarding a spectral response at each pixel of the first hyperspectral image. The analyzer unit then compares the spectral response at a first pixel of the hyperspectral image with the spectral response of the hyperspectral tag. Based upon the comparison, the analyzer unit generates an identity of the object of interest.

Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.

Abstract: An aerial vehicle is navigated using hierarchical vision-aided navigation that classifies regions of acquired still image frames as featureless or feature-rich, and thereby avoids expending time and computational resources attempting to extract and match false features from the featureless regions. Pattern recognition registers an acquired image to a general area of a map database before performing feature matching to a finer map region. This hierarchical position determination is more efficient than attempting to ascertain a fine-resolution position without knowledge of coarse-resolution position. Resultant matched feature observations can be data-fused with other sensor data to correct a navigation solution based on GPS and/or IMU data.

Abstract: Images of a scene may be captured by a set of image capture devices. Overlapping areas of the images may be identified based on the topology of the set of image capture devices. Frontiers within the overlapping areas of the images may be identified based on borders of the images. Sample points for the images may be distributed along the frontiers. Warp parameters including an anti-symmetric warping portion and a symmetric warping portion may be determined at the sample points. Displacement values may be determined at the sample points based on the warp parameters. Warp maps for the images may be determined based on diffusion of the displacement values. Displacement maps for the images may be determined based on interpolation of the warp maps. The images may be modified based on the displacement maps.

Abstract: An image processing apparatus according to the present disclosure includes an acquisition unit configured to acquire a position for identifying a region in which a plurality of images are combined in an overlap region, the plurality of images being obtained in a partially-overlapping manner, a detection unit configured to detect an edge in vicinity of the position for identifying the region in the plurality of images, and a combining unit configured to combine the plurality of images to generate an output image by blending pixel values of pixels constituting the plurality of images, in vicinity of the position for identifying the region, wherein the combining unit sets a parameter for controlling the region in which the plurality of images are combined, according to a correlation between the position for identifying the region and the edge.

Abstract: A method of determining camera poses includes capturing a plurality of image frames using a camera, computing relative poses between each set of image frame pairs to provide a relative pose set and an uncategorized relative pose set, and detecting and removing miscategorized relative poses to provide a remaining relative pose set. The method also includes determining global poses using the remaining relative pose set and computing extended relative poses for at least a portion of the miscategorized relative poses and at least a portion of the uncategorized relative pose set to provide an extended relative pose set and an extended uncategorized relative pose set. The method further includes detecting and removing extended miscategorized relative poses to provide a remaining extended relative pose set and determining updated global poses for the plurality of image frames using the remaining relative pose set and the remaining extended relative pose set.

Abstract: A computer peripheral that may operate as a scanner. The scanner captures image frames as it is moved across an object. The image frames are formed into a composite image based on computations in two processes. In a first process, fast track processing determines a coarse position of each of the image frames based on a relative position between each successive image frame and a respective preceding image determine by matching overlapping portions of the image frames. In a second process, fine position adjustments are computed to reduce inconsistencies from determining positions of image frames based on relative positions to multiple prior image frames. The peripheral may also act as a mouse and may be configured with one or more navigation sensors that can be used to reduce processing time required to match a successive image frame to a preceding image frame.

Abstract: Panoramic imaging systems and techniques are disclosed. In one aspect, a technique for automatic detecting and tracking of a foreground object includes the steps of: receiving a first set of raw images in an image sequence captured by a panoramic imaging system; stitching, by the panoramic imaging system, the first set of raw images to generate a panoramic image; detecting, by the panoramic imaging system, a foreground object in the panoramic image; tracking, by the panoramic imaging system, a movement of the foreground object in the image sequence; and generating, by the panoramic imaging system, a panoramic video based on the image sequence with tracking the movement of the foreground object.

Abstract: A computing device is described which has a memory holding at least two input images depicting different parts of a panoramic scene, the images having been captured by a user moving the camera by hand to capture the panorama. The computing device has an image stitching component configured to identify, at a processor, a region of overlap between the at least two images and to calculate a displacement vector for each of a plurality of warp points in the region of overlap. The image stitching component is arranged to warp a second one of the at least two images using the warp points; and to join the warped second image to the first image.

Abstract: One or more techniques and/or systems are provided for image blending and/or facilitating image transitions. In an example, a map interface displays map information, such as of a town, through a visualization. A first image having a first level of detail and a first image type (e.g., satellite imagery of the town) may be displayed through the visualization. While zoomed into the town, a second image having a second level of detail and a second image type (e.g., aerial imagery of the town) may be displayed through the visualization. Instead of merely transitioning the visualization from displaying the first image to displaying the second image (during zooming), which may otherwise provide a visually abrupt transition, one or more intermediate blended images, having intermediate levels of detail between the first image and the second image, may be generated and displayed during the transition between the first image and the second image.