Abstract: A trajectory estimation apparatus includes: an image acceptance unit which accepts images that are temporally sequential and included in the video; a hierarchical subregion generating unit which generates subregions at hierarchical levels by performing hierarchical segmentation on each of the images accepted by the image acceptance unit such that, among subregions belonging to hierarchical levels different from each other, a spatially larger subregion includes spatially smaller subregions; and a representative trajectory estimation unit which estimates, as a representative trajectory, a trajectory, in the video, of a subregion included in a certain image, by searching for a subregion that is most similar to the subregion included in the certain image, across hierarchical levels in an image different from the certain image.

Abstract: An articulation region display apparatus includes: an articulatedness calculating unit calculating an articulatedness, based on a temporal change in a point-to-point distance and a temporal change in a geodetic distance between given trajectories; an articulation detecting unit detecting, as an articulation region, a region corresponding to a first trajectory based on the articulatedness between the trajectories, the first trajectory being in a state where the regions corresponding to the first trajectory and a second trajectory are present on the same rigid body, the regions corresponding to the first trajectory and third trajectory are present on the same rigid body, and the region corresponding to the second trajectory is connected with the region corresponding to the third trajectory via the same joint; and a display control unit transforming the articulation region into a form visually recognized by a user, and output the transformed articulation region.

Abstract: The present invention provides an apparatus that includes a color and polarization image capturing section 201, a whole sky polarization map getting section 202, a weather determining section 203, a fine-weather sky part separating section 204, a cloudy-weather normal estimating section 207, and a pseudo 3D image generating section 208. The apparatus obtains polarization information outdoors with the polarization state of the sky taken into account, and estimates surface normal information at an object's surface on a two-dimensional image, thereby generating a surface normal image. Using that normal image, the apparatus divides the object into multiple ranges, extracts three-dimensional information and generates a viewpoint changed image, thereby generating a pseudo 3D image.

Abstract: A moving object detection apparatus includes: a trajectory calculating unit which calculates a plurality of trajectories for each image subset; a subclass classification unit which classifies the trajectories into subclasses for each of the image subsets, an inter-subclass similarity calculating unit which calculates a trajectory share ratio which indicates the degree of sharing of the same trajectory between arbitrary two of the subclasses and calculates the similarity between the subclasses based on the share ratio; a moving object detection unit which detects the moving object in video by classifying the subclasses into classes such that the subclasses between which a higher similarity is present are more likely to be classified into the same class.

Abstract: A moving object detection apparatus includes: a stationary measure calculation unit calculating, for each of trajectories, a stationary measure representing likelihood that the trajectory belongs to a stationary object; a distance calculation unit calculating a distance representing similarity between trajectories; and a region detection unit (i) performing a transformation based on the stationary measures and the distances between the trajectories, so that a ratio of a distance between a trajectory on stationary object and a trajectory on moving object, to a distance between trajectories both belonging to stationary object becomes greater than a ratio obtained before the transformation and (ii) detecting the moving object region by separating the trajectory on the moving object from the trajectory on the stationary object, based on a geodesic distance between the trajectories.

Abstract: A moving object detection apparatus includes: an image input unit which receives a plurality of pictures included in video; a trajectory calculating unit which calculates a plurality of trajectories from the pictures; a subclass classification unit which classifies the trajectories into a plurality of subclasses; an inter-subclass approximate geodetic distance calculating unit which calculates, for each of the subclasses, an inter-subclass approximate geodetic distance representing similarity between the subclass and another subclass, using an inter-subclass distance that is a distance including a minimum value of a linear distance between each of trajectories belonging to the subclass and one of trajectories belonging to the other subclass; and a segmentation unit which performs segmentation by determining, based on the calculated inter-subclass approximate geodetic distance, a set of subclasses including similar trajectories as one class.

Abstract: An articulated object region detection apparatus includes: a subclass classification unit which classifies trajectories into subclasses; a distance calculating unit which calculates, for each of the subclasses, a point-to-point distance and a geodetic distance between the subclass and another subclass; and a region detection unit which detects, as a region having an articulated motion, two subclasses to which trajectories corresponding to two regions connected via the same articulation and indicating the articulated motion belong, based on a temporal change in the point-to-point distance and a temporal change in the geodetic distance between two given subclasses.

Abstract: A polarization camera that can capture polarization images and a color image at the same time is used. Specifically, a clear sky polarization image, which provides information about the polarization of a part of the sky, is captured by a clear sky polarization image capturing section 100. And by reference to the information provided by a sun position determining section 1301 that determines the sun's position at the time of shooting, a camera direction estimating section 101 determines in what direction and in what area of the whole sky the clear sky polarization image is located as a polarization pattern. Finally, information about what direction or orientation on the globe the camera (image capture device) is now facing is output. In this manner, the direction of the camera and the relative position of the camera with respect to the sun can be known without providing a sensor separately and without capturing the whole sky or the sun.

Abstract: An articulation region display apparatus includes: an articulatedness calculating unit calculating an articulatedness, based on a temporal change in a point-to-point distance and a temporal change in a geodetic distance between given trajectories; an articulation detecting unit detecting, as an articulation region, a region corresponding to a first trajectory based on the articulatedness between the trajectories, the first trajectory being in a state where the regions corresponding to the first trajectory and a second trajectory are present on the same rigid body, the regions corresponding to the first trajectory and third trajectory are present on the same rigid body, and the region corresponding to the second trajectory is connected with the region corresponding to the third trajectory via the same joint; and a display control unit transforming the articulation region into a form visually recognized by a user, and output the transformed articulation region.

Abstract: A moving object detection apparatus includes: a stationary measure calculation unit calculating, for each of trajectories, a stationary measure representing likelihood that the trajectory belongs to a stationary object; a distance calculation unit calculating a distance representing similarity between trajectories; and a region detection unit (i) performing a transformation based on the stationary measures and the distances between the trajectories, so that a ratio of a distance between a trajectory on stationary object and a trajectory on moving object, to a distance between trajectories both belonging to stationary object becomes greater than a ratio obtained before the transformation and (ii) detecting the moving object region by separating the trajectory on the moving object from the trajectory on the stationary object, based on a geodesic distance between the trajectories.

Abstract: A moving object detection method with which a region of a moving object is accurately extracted without being affected by a change in shape or size or occlusion of the moving object and in which a distance indicating a similarity between trajectories of an image in each of the blocks included in video is calculated (S203) and a group of similar trajectories is identified as one region based on the distance (S209).

Abstract: A trajectory estimation apparatus includes: an image acceptance unit which accepts images that are temporally sequential and included in the video; a hierarchical subregion generating unit which generates subregions at hierarchical levels by performing hierarchical segmentation on each of the images accepted by the image acceptance unit such that, among subregions belonging to hierarchical levels different from each other, a spatially larger subregion includes spatially smaller subregions; and a representative trajectory estimation unit which estimates, as a representative trajectory, a trajectory, in the video, of a subregion included in a certain image, by searching for a subregion that is most similar to the subregion included in the certain image, across hierarchical levels in an image different from the certain image.

Abstract: A moving object detection apparatus includes: an image input unit which receives a plurality of pictures included in video; a trajectory calculating unit which calculates a plurality of trajectories from the pictures; a subclass classification unit which classifies the trajectories into a plurality of subclasses; an inter-subclass approximate geodetic distance calculating unit which calculates, for each of the subclasses, an inter-subclass approximate geodetic distance representing similarity between the subclass and another subclass, using an inter-subclass distance that is a distance including a minimum value of a linear distance between each of trajectories belonging to the subclass and one of trajectories belonging to the other subclass; and a segmentation unit which performs segmentation by determining, based on the calculated inter-subclass approximate geodetic distance, a set of subclasses including similar trajectories as one class.

Abstract: An articulated object region detection apparatus includes: a subclass classification unit which classifies trajectories into subclasses; a distance calculating unit which calculates, for each of the subclasses, a point-to-point distance and a geodetic distance between the subclass and another subclass; and a region detection unit which detects, as a region having an articulated motion, two subclasses to which trajectories corresponding to two regions connected via the same articulation and indicating the articulated motion belong, based on a temporal change in the point-to-point distance and a temporal change in the geodetic distance between two given subclasses.

Abstract: The present invention provides an apparatus that includes a color and polarization image capturing section 201, a whole sky polarization map getting section 202, a weather determining section 203, a fine-weather sky part separating section 204, a cloudy-weather normal estimating section 207, and a pseudo 3D image generating section 208. The apparatus obtains polarization information outdoors with the polarization state of the sky taken into account, and estimates surface normal information at an object's surface on a two-dimensional image, thereby generating a surface normal image. Using that normal image, the apparatus divides the object into multiple ranges, extracts three-dimensional information and generates a viewpoint changed image, thereby generating a pseudo 3D image.

Abstract: A polarization camera that can capture polarization images and a color image at the same time is used. Specifically, a clear sky polarization image, which provides information about the polarization of a part of the sky, is captured by a clear sky polarization image capturing section 100. And by reference to the information provided by a sun position determining section 1301 that determines the sun's position at the time of shooting, a camera direction estimating section 101 determines in what direction and in what area of the whole sky the clear sky polarization image is located as a polarization pattern. Finally, information about what direction or orientation on the globe the camera (image capture device) is now facing is output. In this manner, the direction of the camera and the relative position of the camera with respect to the sun can be known without providing a sensor separately and without capturing the whole sky or the sun.

Abstract: A moving object detection method with which a region of a moving object is accurately extracted without being affected by a change in shape or size or occlusion of the moving object and in which a distance indicating a similarity between trajectories of an image in each of the blocks included in video is calculated (S203) and a group of similar trajectories is identified as one region based on the distance (S209).