Abstract: An image acquisition unit configured to acquire an image representing a three-dimensional shape of a surface of a human body, a spinal-column arrangement estimation-unit configured to estimate spinal-column arrangement of the human body using accumulated data, and an angle calculation unit configured to calculate at least one of a Cobb angle and a rotation angle from the estimated spinal-column arrangement are included.

Abstract: An image acquisition unit configured to acquire an image representing a three-dimensional shape of a surface of a human body, a spinal-column arrangement estimation-unit configured to estimate spinal-column arrangement of the human body using accumulated data, and an angle calculation unit configured to calculate at least one of a Cobb angle and a rotation angle from the estimated spinal-column arrangement are included.

Abstract: Image processing apparatus capable of detecting a person independently of the positional relationship between a camera and the person. The image processing apparatus (100) detects a human region included in an input image. The image processing apparatus (100) includes: head detection unit (210) for detecting head position of a person in an input image; determination unit (220) for determining a relative positional relationship between the head and another body part in the input image with use of feature amounts extracted from an image region around the head position detected by head detection unit (210); and human detection unit (230) for setting at least one of the direction of searching for a human region and the region of searching for the human region in accordance with a relative relation determined by determination unit (220), and detecting the human region from the input image.

Abstract: Image processing apparatus programmed to: continuously shoot a subject to obtain images, and detect the object and extract a position of the object from a three-dimensional position of the subject in the images; detect the person and extract a position of the person from the three-dimensional position, and extract, from the position of the person, part information pieces including respective positions of characteristic parts of the person; generate a pose class for each set of part information pieces, the part information pieces being similar to one another in correlation between parts of the person calculated from each of the part information pieces; identify a pose class to which the correlation between parts of the person belongs, among generated pose classes, when a distance between the person and the object is within a predetermined range; and store the identified pose class in association with the object.

Abstract: The present disclosure provides a person tracking method of tracking a person with high precision. According to a person tracking method and a person tracking device of the present disclosure, a processor determines coordinates of a plurality of persons of a video within the video. The processor specifies a group area as an area where the persons of the video are dense. The processor tracks coordinates of a certain person within the video. The processor determines a locus of coordinates of the certain person in the group area based on coordinates of the certain person out of the group area and a number depicted on a clothing.

Abstract: The present disclosure provides a person tracking method of tracking a person with high precision. According to a person tracking method and a person tracking device of the present disclosure, a processor determines coordinates of a plurality of persons of a video within the video. The processor specifies a group area as an area where the persons of the video are dense. The processor tracks coordinates of a certain person within the video. The processor determines a locus of coordinates of the certain person in the group area based on coordinates of the certain person out of the group area and a number depicted on a clothing.

Abstract: Image processing apparatus programmed to: continuously shoot a subject to obtain images, and detect the object and extract a position of the object from a three-dimensional position of the subject in the images; detect the person and extract a position of the person from the three-dimensional position, and extract, from the position of the person, part information pieces including respective positions of characteristic parts of the person; generate a pose class for each set of part information pieces, the part information pieces being similar to one another in correlation between parts of the person calculated from each of the part information pieces; identify a pose class to which the correlation between parts of the person belongs, among generated pose classes, when a distance between the person and the object is within a predetermined range; and store the identified pose class in association with the object.

Abstract: Image processing apparatus capable of detecting a person independently of the positional relationship between a camera and the person. The image processing apparatus (100) detects a human region included in an input image. The image processing apparatus (100) includes: head detection unit (210) for detecting head position of a person in an input image; determination unit (220) for determining a relative positional relationship between the head and another body part in the input image with use of feature amounts extracted from an image region around the head position detected by head detection unit (210); and human detection unit (230) for setting at least one of the direction of searching for a human region and the region of searching for the human region in accordance with a relative relation determined by determination unit (220), and detecting the human region from the input image.

Abstract: There is provided a respiratory movement measurement apparatus that can obtain a respiratory movement signal for each region by dividing and setting a region to be evaluated in a simple manner with good reproducibility. The respiratory movement measurement apparatus emits a light flux to a body surface 32 of a subject 31, captures reflected light by a camera 35, and thereby measures a respiration rate of the subject, wherein a merkmal indicating a mark position is further set on the body surface of the subject, a mark having a reflectance different from that of the body surface is placed on the merkmal, the body surface is divided into a plurality of regions on an observed image by a dividing line passing through the mark, bright spot reflection for each of the divided regions is summed, and thereby a respiratory movement signal is obtained.

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: 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: For a semiconductor device S, an inspection is performed in a zero-bias state by use of electromagnetic waves generated by irradiation of pulsed laser light, and an inspection range is set with reference to layout information of the semiconductor device S to perform two-dimensional scanning by inspection light L1 of the pulsed laser light within the range. Moreover, with the inspection range of the semiconductor device S arranged at a predetermined position with respect to an optical axis of an optical system, and with a solid immersion lens 36 disposed for the semiconductor device S, by a galvanometer scanner 30 being scanning means, the inspection range of the semiconductor device S is two-dimensionally scanned by the inspection light L1 via the solid immersion lens 36, and an electromagnetic wave emitted from the semiconductor device S is detected by a photoconductive element 40.

Abstract: The ferrite stainless steel welding rod of this invention comprises the following: 0.03% by weight or less of carbon, 1.00% by weight or less of silicon, 1.00% by weight or less of manganese, from 16.0 to 21.0% by weight of chromium, from 0.30 to 0.80% by weight of niobium, from 0.30 to 0.80% by weight of copper, 0.025% by weight or less of nitrogen, and the balance of iron. The ferrite stainless steel welding rod of this invention offers a good weldability not only in welding stainless steels of the same type but also in welding stainless steels of different types. Further, the welding steel of this invention has a good oxidation resistance, and a good workability and mechanical property.

Abstract: An improved cut wire used as an electrode in electrical discharge machining which has higher tensile strength at high temperatures. It is a composite wire having a core of stainless steel and a covering layer of copper or copper alloy provided around the core. The diameter and the tensile strength of the cut wire and the percentage of the sectional area of the core to that of the entire cut wire are important parameters in the composite wire.