# US 2019/0244101 A1 · Classification apparatus, classification method, and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0244101 A1 - Document ID: US20190244101A1 - Status: Published application - Kind: A1 - Application number: 16/386,431 - Filed: 2019-04-17 - Published: 2019-08-08 - Earliest claimed: 2016-12-06 - Assignees: OMRON Corporation - Applicants: OMRON Corporation - Inventors: Tanichi ANDO - Web page: https://patentgrep.com/patent/US20190244101A1 ## CPC - G06N 3/09: Supervised learning - G01B 11/00: Measuring arrangements characterised by the use of optical techniques - G06N 3/067: using optical means - G06N 3/08: Learning methods - G06T 7/00: Image analysis - G06V 10/141: Control of illumination - G06V 10/764: using classification, e.g. of video objects - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A classification apparatus includes: a specifying unit integrated with a neural network that has been trained to classify a state of a space using information indicating a light projection pattern and information indicating a light reception pattern; a light projection information acquisition unit configured to acquire information indicating a light projection pattern of light projected into a predetermined space, and output the acquired information to the specifying unit; and a light receiving unit configured to acquire information indicating a light reception pattern of light received from the predetermined space, and output the acquired information to the specifying unit, wherein the specifying unit outputs a classification result of classifying a state of the predetermined space, based on the information indicating the light projection pattern acquired by the light projection information acquisition unit and on the information indicating the light reception pattern of the light received by the light receiving unit. ## Claims ### Claim 1 A classification apparatus comprising a processor configured with a program to perform operations comprising: operation as a specifying unit into which a neural network is integrated that has been trained to classify a state of a space using information indicating a light projection pattern and information indicating a light reception pattern; operation as a light projection information acquisition unit configured to acquire information indicating a light projection pattern of light projected into a predetermined space, and output the acquired information to the specifying unit; and operation as a light receiving unit configured to acquire information indicating a light reception pattern of light received from the predetermined space, and output the acquired information to the specifying unit, wherein the processor is configured with the program to perform operations comprising operations such that operation as the specifying unit is configured to output a classification result of classifying a state of the predetermined space, based on the information indicating the light projection pattern acquired by the light projection information acquisition unit and on the information indicating the light reception pattern of the light received by the light receiving unit. ### Claim 2 (depends on 1) The classification apparatus according to claim 1, wherein the processor is configured with the program to perform operations comprising operations such that: operation as the light projection information acquisition unit is configured to acquire information indicating a light projection pattern of light projected onto a target within the predetermined space, and to output the acquired information to the specifying unit; operation as the light receiving unit is configured to acquire a light reception pattern of the light projected onto the target within the predetermined space, and to output the acquired light reception pattern to the specifying unit; and operation as the specifying unit is configured to output a classification result of classifying a presence or a state of the target within the predetermined space. ### Claim 3 (depends on 1) The classification apparatus according to claim 1, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using information indicating a light projection pattern of light that is projected into a space that is given in advance, and information indicating a light reception pattern of light received from the space that is given in advance. ### Claim 4 (depends on 1) The classification apparatus according to claim 1, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using information indicating a plurality of light projection patterns, and information indicating light reception patterns of light that is received in response to projecting the plurality of light projection patterns. ### Claim 5 (depends on 1) The classification apparatus according to claim 1, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using learning data in which the information indicating the light projection pattern, the information indicating the light reception pattern, and information indicating the state of the space are associated with each other. ### Claim 6 (depends on 1) The classification apparatus according to claim 1, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using auxiliary information from an auxiliary sensor, in addition to the information indicating the light projection pattern and the information indicating the light reception pattern. ### Claim 7 (depends on 2) The classification apparatus according to claim 2, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using information indicating a light projection pattern of light that is projected into a space that is given in advance, and information indicating a light reception pattern of light received from the space that is given in advance. ### Claim 8 (depends on 2) The classification apparatus according to claim 2, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using information indicating a plurality of light projection patterns, and information indicating light reception patterns of light that is received in response to projecting the plurality of light projection patterns. ### Claim 9 (depends on 2) The classification apparatus according to claim 2, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using learning data in which the information indicating the light projection pattern, the information indicating the light reception pattern, and information indicating the state of the space are associated with each other. ### Claim 10 (depends on 2) The classification apparatus according to claim 2, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using auxiliary information from an auxiliary sensor, in addition to the information indicating the light projection pattern and the information indicating the light reception pattern. ### Claim 11 (depends on 3) The classification apparatus according to claim 3, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using information indicating a plurality of light projection patterns, and information indicating light reception patterns of light that is received in response to projecting the plurality of light projection patterns. ### Claim 12 (depends on 3) The classification apparatus according to claim 3, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using learning data in which the information indicating the light projection pattern, the information indicating the light reception pattern, and information indicating the state of the space are associated with each other. ### Claim 13 (depends on 3) The classification apparatus according to claim 3, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using auxiliary information from an auxiliary sensor, in addition to the information indicating the light projection pattern and the information indicating the light reception pattern. ### Claim 14 (depends on 4) The classification apparatus according to claim 4, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using learning data in which the information indicating the light projection pattern, the information indicating the light reception pattern, and information indicating the state of the space are associated with each other. ### Claim 15 (depends on 4) The classification apparatus according to claim 4, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using auxiliary information from an auxiliary sensor, in addition to the information indicating the light projection pattern and the information indicating the light reception pattern. ### Claim 16 (depends on 5) The classification apparatus according to claim 5, wherein the neural network integrated into the specifying unit has been trained to classify the state of the space using auxiliary information from an auxiliary sensor, in addition to the information indicating the light projection pattern and the information indicating the light reception pattern. ### Claim 17 A classification method comprising: integrating a neural network that has been trained to classify a state of a space using information indicating a light projection pattern and information indicating a light reception pattern; acquiring information indicating a light projection pattern of light projected into a predetermined space, and outputting the acquired information to a specifying unit; and acquiring information indicating a light reception pattern of light received from the predetermined space, and outputting the acquired information to the specifying unit, wherein in the integrating, a classification result of classifying a state of the predetermined space is output based on the acquired information indicating the light projection pattern and the information indicating the light reception pattern of the received light. ### Claim 18 Anon-transitory computer-readable storage medium storing a program, which when read and executed, causes a computer to perform operations comprising: integrating a neural network that has been trained to classify a state of a space using information indicating a light projection pattern and information indicating a light reception pattern; acquiring information indicating a light projection pattern of light projected into a predetermined space, and outputting the acquired information to a specifying unit; and acquiring information indicating a light reception pattern of light received from the predetermined space, and outputting the acquired information to the specifying unit, wherein the integrating outputs a classification result of classifying a state of the predetermined space based on the acquired information indicating the light projection pattern and the information indicating the light reception pattern of the received light.