Abstract: This posture state estimation device is capable of estimating with high accuracy the posture state of an object. The posture state estimation device (100) is a device for estimating the posture state of an object having a plurality of sections connected by joints on the basis of image data that images the object, and has a section candidate extraction unit (140) for extracting a section candidate for a section from the image data, a complementary section candidate extraction unit (160) which estimates that a portion of an unextracted section for which a section candidate has not been extracted is being shadowed by an already extracted section for which a section candidate has been extracted in order to extract a section candidate of the unextracted section, and a posture state estimation unit (170) for estimating the posture state of the object on the basis of the extracted section candidate.

Abstract: This posture state estimation device is capable of estimating with high accuracy the posture state of an object. The posture state estimation device (100) is a device for estimating the posture state of an object having a plurality of sections connected by joints on the basis of image data that images the object, and has a section candidate extraction unit (140) for extracting a section candidate for a section from the image data, a complementary section candidate extraction unit (160) which estimates that a portion of an unextracted section for which a section candidate has not been extracted is being shadowed by an already extracted section for which a section candidate has been extracted in order to extract a section candidate of the unextracted section, and a posture state estimation unit (170) for estimating the posture state of the object on the basis of the extracted section candidate.

Abstract: This posture state estimation device is capable of estimating with high accuracy the posture state of an object. The posture state estimation device (100) is a device for estimating the posture state of an object having a plurality of sections connected by joints on the basis of image data that images the object, and has a section candidate extraction unit (140) for extracting a section candidate for a section from the image data, a complementary section candidate extraction unit (160) which estimates that a portion of an unextracted section for which a section candidate has not been extracted is being shadowed by an already extracted section for which a section candidate has been extracted in order to extract a section candidate of the unextracted section, and a posture state estimation unit (170) for estimating the posture state of the object on the basis of the extracted section candidate.

Abstract: Provided is a posture estimation device with which it is possible to estimate the posture of an object having joints with a high degree of precision. A posture estimation device (100) carries out an estimation of a posture of an object on the basis of image data. An object having a plurality of sites which are connected by joints is photographed. The posture estimation device includes a reference model storage unit (140) which stores a reference model, which defines the locations of the sites, for each posture. A weighting computation unit (150) carries out weighting on the sites for each posture such that the weighting of concentrated parts is reduced. A posture estimation unit (160) estimates the posture of the object by applying the weighting and comparing the reference model with the object.

Abstract: The present invention is a posture estimation device for estimating a wide variety of 3-dimensional postures by using a skeletal model. The posture estimation device (200) has: a skeletal backbone estimation unit (230) for estimating the position of a feature location of a person within an acquired image; a location extraction unit (240) which generates a likelihood map indicating the certainty that a location other than the feature location of the person exists in the acquired image based on the position of the feature location of the person; and a skeletal model evaluation unit (250) for evaluating, based on the likelihood map, a candidate group which includes a plurality of 2-dimensional skeletal models as candidates and such that each 2-dimensional skeletal model is configured from a line group representing each location and a point group representing coupling between each location and corresponds to one posture of the person.

Abstract: Disclosed is an orientation state estimation device capable of estimating with high accuracy the orientation state of a jointed body. An orientation state estimation device (100) estimates the orientation state of a body on the basis of image data of the body having multiple parts connected by joints. The device is provided with: a likelihood map generation unit (150) which, from the image data, for at least two parts of the jointed body, generates a likelihood map showing the plausibility distribution of where each part is most plausibly positioned; and an orientation state estimation unit (160) which, when a learning likelihood map, which is associated in advance with an orientation state, and an estimated likelihood map, which is generated on the basis of the image data, coincide to a high degree, estimates that the orientation state associated with said learning likelihood map is the orientation state of the object.

Abstract: A stereo image processor (1) performs image matching, in an image matching section (6), on partial images of the same object included in a base image and a comparative image respectively and detects pixel-precision partial displacement between the base image and the comparative image based on a result of the image matching. Next, in an inverted phase filter processing section (9) in a second matching section (8), pixel values from the comparative image are filtered with an inverted phase filter using, as a filter coefficient, pixel values from the base image with the order thereof reversed, given the partial images of the same object that have minimum pixel-precision partial displacement. Then, in a peak detecting section (10), a peak position where an output value of the filtering with the inverted phase filter is maximum is detected and sub-pixel-precision partial displacement between the base image and the comparative image is detected based on the peak position.

Abstract: An image segmenting unit (401) in the stereo image processing device (100) extracts M (a natural number between 2 and N, inclusive) number of segmented target images wherein a first partial area within a target image has been segmented into N (a natural number of 2 or more), and also extracts M number of segmented reference images wherein a second partial area within a reference image has been segmented into N. An image concatenating unit (402) serially concatenates M data strings, each comprising a intensity value from each segmented target image, to form a first image data string and also serially concatenates M data strings, each comprising a intensity value from each segmented reference image, to form a second image data string. A filtering unit (403) and a peak position detection unit (104) calculate the disparity between the standard images and the reference images.

Abstract: Provided is a stereo image processing apparatus wherein parallax can be calculated with high precision. A window-function shifting unit (411) sets a third window function, which is formed by shifting a second window function on the basis of the amount of deviation in sub-pixel units, onto an image cutting-out unit (412). The image cutting-out unit (412) applies the second window function to a position subjected to a cut-out, cuts out a unit partial target image from a standard image, applies the second window function or the third window function, and cuts out a unit partial reference image from a reference image. A peak-position detection unit (106) calculates the amount of deviation in sub-pixel units on the basis of the phase difference between a data string comprising brightness of the cut-out unit partial target image, and a data string comprising brightness of the cut-out unit partial reference image.

Abstract: Disclosed is an object detection method capable of detecting with high precision information relating to a jointed object from image data. An object detection device (160) detects information relating to an object from image data of images captured of an object having multiple parts connected by joints. The disclosed object detection device (160) is provided with a joint angle extraction unit (161) which extracts the angle of a joint connecting two parts from candidates of the positions of two neighboring parts obtained from the image data, and a part length ratio estimation unit (165) which uses the joint angle to perform the detection described above.

Abstract: A stereo image processor (1) performs image matching, in an image matching section (6), on partial images of the same object included in a base image and a comparative image respectively and detects pixel-precision partial displacement between the base image and the comparative image based on a result of the image matching. Next, in an inverted phase filter processing section (9) in a second matching section (8), pixel values from the comparative image are filtered with an inverted phase filter using, as a filter coefficient, pixel values from the base image with the order thereof reversed, given the partial images of the same object that have minimum pixel-precision partial displacement. Then, in a peak detecting section (10), a peak position where an output value of the filtering with the inverted phase filter is maximum is detected and sub-pixel-precision partial displacement between the base image and the comparative image is detected based on the peak position.

Abstract: Provided is a person detection device with which it is possible to estimate a state of a part of a person from an image. A person detection device (100) comprises: an evaluation unit (430) which acquires a prescribed outline of a person from an evaluation image; and a shoulder position calculation unit (440) and an orientation estimation unit (500) which estimate a state of a prescribed part of a person which is included in the evaluation image from the prescribed outline of the person which is acquired from the evaluation image, on the basis of an estimation model which denotes a relation between the prescribed outline and the state of the prescribed part of the person.

Abstract: A stereo image processor (1) performs image matching, in an image matching section (6), on partial images of the same object included in a base image and a comparative image respectively and detects pixel-precision partial displacement between the base image and the comparative image based on a result of the image matching. Next, in an inverted phase filter processing section (9) in a second matching section (8), pixel values from the comparative image are filtered with an inverted phase filter using, as a filter coefficient, pixel values from the base image with the order thereof reversed, given the partial images of the same object that have minimum pixel-precision partial displacement. Then, in a peak detecting section (10), a peak position where an output value of the filtering with the inverted phase filter is maximum is detected and sub-pixel-precision partial displacement between the base image and the comparative image is detected based on the peak position.

Abstract: An object detection device that can accurately identify an object candidate in captured stereo images as an object or a road surface. The object detection device (100) have a disparity map generator (120) that generates a disparity map based on the stereo images; a road surface estimator (130) that estimates a road surface based on the disparity map; an object candidate location extractor (140) that extracts an object candidate region above the road surface, based on the disparity map and the road surface; an object identifying region extractor (150) that extracts an object identifying region including a region around the object candidate region; a geometric feature extractor (160) that extracts a geometric feature of the object candidate based on the object identifying region; and an object identifying unit (170) that identifies whether the object candidate is an object or a road surface based on the geometric feature.

Abstract: Provided is a posture estimation device with which it is possible to estimate the posture of an object having joints with a high degree of precision. A posture estimation device (100) carries out an estimation of a posture of an object on the basis of image data wherein an object having a plurality of sites which are connected by joints is photographed. The device comprises: a reference model storage unit (140) which stores a reference model, which defines the locations of the sites, for each posture; a weighting computation unit (150) which carries out weighting on the sites for each posture such that the weighting of concentrated parts is reduced; and a posture estimation unit (160) which estimates the posture of the object by applying the weighting and comparing the reference model with the object.

Abstract: A line-of-sight direction determination device includes: a line-symmetric position determiner that determines that the corneal reflection image of a left eye or a right eye is located at a line-symmetric position with respect to the center line of the pupils of the left and right eyes; and a line-of-sight direction determiner that determines, from the line-symmetric position determination result, a line-of-sight direction at a specific position including the installation position of an imaging unit or an irradiation unit at the substantially same position as the imaging unit. The line-of-sight direction determination device determines that the corneal reflection image is line symmetric and, from this line symmetry property, determines a specific line-of-sight direction.

Abstract: Disclosed is an orientation state estimation device capable of estimating with high accuracy the orientation state of a jointed body. An orientation state estimation device (100) estimates the orientation state of a body on the basis of image data of the body having multiple parts connected by joints. The device is provided with: a likelihood map generation unit (150) which, from the image data, for at least two parts of the jointed body, generates a likelihood map showing the plausibility distribution of where each part is most plausibly positioned; and an orientation state estimation unit (160) which, when a learning likelihood map, which is associated in advance with an orientation state, and an estimated likelihood map, which is generated on the basis of the image data, coincide to a high degree, estimates that the orientation state associated with said learning likelihood map is the orientation state of the object.

Abstract: This posture state estimation device is capable of estimating with high accuracy the posture state of an object. The posture state estimation device (100) is a device for estimating the posture state of an object having a plurality of sections connected by joints on the basis of image data that images the object, and has a section candidate extraction unit (140) for extracting a section candidate for a section from the image data, a complementary section candidate extraction unit (160) which estimates that a portion of an unextracted section for which a section candidate has not been extracted is being shadowed by an already extracted section for which a section candidate has been extracted in order to extract a section candidate of the unextracted section, and a posture state estimation unit (170) for estimating the posture state of the object on the basis of the extracted section candidate.

Abstract: Provided is a person detection device with which it is possible to estimate a state of a part of a person from an image. A person detection device (100) comprises: an evaluation unit (430) which acquires a prescribed outline of a person from an evaluation image; and a shoulder position calculation unit (440) and an orientation estimation unit (500) which estimate a state of a prescribed part of a person which is included in the evaluation image from the prescribed outline of the person which is acquired from the evaluation image, on the basis of an estimation model which denotes a relation between the prescribed outline and the state of the prescribed part of the person.

Abstract: Disclosed is an object detection method capable of detecting with high precision information relating to a jointed object from image data. An object detection device (160) detects information relating to an object from image data of images captured of an object having multiple parts connected by joints. The disclosed object detection device (160) is provided with a joint angle extraction unit (161) which extracts the angle of a joint connecting two parts from candidates of the positions of two neighboring parts obtained from the image data, and a part length ratio estimation unit (165) which uses the joint angle to perform the detection described above.