Abstract:
A cyclic alternative pattern (CAP) detection device includes a memory storing a program, and at least one processor configured to execute the program stored in the memory, in which the processor is configured to: acquire pulse wave data of a subject; derive a baseline of the pulse wave data and an envelope of the baseline; identify a local maximum point of the envelope and determine, as CAP candidate points each indicating a cyclic alternative pattern, a first local maximum point of the baseline before the local maximum point of the envelope and a second local maximum point of the baseline after the local maximum point of the envelope on a time axis; and identify, for each of the identified CAP candidate points, a third local maximum point of the baseline before the CAP candidate point and a local minimum point of the baseline between the CAP candidate point and the third local maximum point and detect the CAP candidate point as a CAP based on an evaluation value obtained from a difference between the CAP candidate point and the third local maximum point and a difference between the CAP candidate point and the local minimum point.
Abstract:
An autonomous mobile apparatus creates an environment map and estimates a position using images captured by an imaging device. The autonomous mobile apparatus includes a controller and a storage unit. The controller creates environment maps in accordance with changes in the surrounding environment, normalizes the created environment maps to enable unified handling and saves the normalized environment maps in the storage unit, and estimates the position using the normalized environment maps.
Abstract:
An autonomous mobile apparatus that returns to a charger to be charged, the apparatus comprises a determiner that determines whether the apparatus is able to return to the charger, a location obtainer that obtains a predetermined location, an action planner that sets a destination, and sets a route to the destination, and a movement controller that controls a drive so that the apparatus is moved along the route that is set by the action planner, wherein, when the determiner determines that the apparatus is not able to return to the charger, the action planner sets the predetermined location obtained by the location obtainer as the destination.
Abstract:
An autonomous mobile apparatus includes a memory and a processor. The processor is configured to acquire environment information that is information of a surrounding environment of the autonomous mobile apparatus, based on the acquired environment information, select, as an estimation environment map, an environment map that is suitable for the surrounding environment from among environment maps that are saved in the memory, and estimate a location of the autonomous mobile apparatus using the selected estimation environment map and an image of surroundings of the autonomous mobile apparatus that is captured by an imager.
Abstract:
An image processing method for diagnosing a disease using a captured image of an affected area, includes separating the captured image memorized into a brightness component and a color information component; separating the brightness component into a base component and a detail component; performing a highlighting process on the detail component; and restoring a brightness component from the base component and a highlighted detail component, and then generating a highlighted image using a restored brightness component and the color information component. The highlighting process includes highlighting the detail component depending on likelihood of vessel of a region to be diagnosed. In the highlighting process, the color information component that corresponds to a direction of a red-based color in a first color space is acquired; a predetermined range of the color information component is normalized; and a likelihood (V) of vessel of the region as acquired via the normalization is reflected in a highlighting coefficient of the detail component to generate a highlighted detail component image.
Abstract:
An image generating apparatus (100) includes an animation acquiring unit (150) that acquires a plurality of items of animation data. A terminal apparatus (200) includes an index value acquiring unit (251), a composite skeleton generating unit (252), and a drawing processing unit (253). The index value acquiring unit (251) inputs an index value regarding a motion of animation data, and the composite skeleton generating unit (252) generates animation data according to the index value input by the index value acquiring unit (251), using the plurality of items of animation data acquired by the animation acquiring unit (150).
Abstract:
A sleep stage estimation device includes a subject data acquisition unit that acquires pulsation data and body movement data of a subject, a sleep stage probability estimation unit that acquires a feature quantity sequence from the pulsation data and estimates a sleep stage probability sequence of the subject from the acquired feature quantity sequence by using a learned sleep stage probability estimation model, a sleep stage transition probability estimation unit that acquires a body movement amount sequence from the body movement data and estimates a sleep stage transition probability sequence of the subject from the acquired body movement amount sequence by using a learned sleep stage transition probability estimation model, and a sleep stage estimation unit that estimates a sleep stage sequence of the subject from the sleep stage probability sequence and the sleep stage transition probability sequence by using a learned conditional random field model.
Abstract:
A diagnostic apparatus for diagnosing a disease using a captured image of an affected area, the apparatus including a memory configured to memorize the captured image; and a processor configured to process the memorized image memorized in the memory. The processor is configured to perform a highlighting process which includes separating the captured image into the brightness component and a color information component; separating the brightness component into a base component and a detail component; highlighting the separated brightness component; and adding a region to be diagnosed in the captured image to the highlighted brightness component while a specified color of the region to be diagnosed is maintained.
Abstract:
An exercise support device and an exercise support method are provided by which a judgment regarding the landing of the left and right feet of a user can be accurately made with low power consumption, so that the user can appropriately grasp and judge the balance of the use of the body in an exercise. First, based on changes in acceleration in a vertical direction with respect to the ground which has been acquired by a sensor section worn on the body during a running exercise, landing timing at which one of the left and right feet is landed is detected. Then, based on whether a difference between angular velocities around a traveling direction axis immediately after the latest landing timing and the preceding landing timing has a positive or negative value, whether the landed foot is the left foot or the right foot is judged.
Abstract:
The invention provides a method of processing an image in a diagnostic apparatus of diagnosing a cutaneous lesion using a cutaneous image, comprising the steps of: (a) obtaining a first detail image made by performing a first component separation filter on a brightness component of the cutaneous image; (b) obtaining a second detail image made by performing a second component separation filter on the brightness component of the cutaneous image, the second component separation filter having properties different from those of the first component separation filter; (c) generating a third detail image based on the first detail image and the second detail image; (d) newly generating a third base image based on the third detail image; and (e) combining the third detail image with the third base image to restore a brightness component and generate a highlighted image.