Patents by Inventor Masato Takami
Masato Takami has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240177501Abstract: A method for detecting an end of a journey of a vehicle. The method includes: determining a movement of the vehicle; determining a closing of at least one door of the vehicle; determining an entry and/or an exit of one or more persons into or from the vehicle; detecting the end of the journey of the vehicle when it is determined that the movement of the vehicle is zero, and when a closing of at least the one door of the vehicle is determined, and when an entry and/or an exit of the one or more persons into or from the vehicle is detected.Type: ApplicationFiled: November 27, 2023Publication date: May 30, 2024Inventors: Masato Takami, Fabian Brickwedde, Uwe Brosch
-
Patent number: 11990759Abstract: An electric power management system includes a solar radiation amount measurement device that measures a solar radiation amount received by the solar power generation device, and a control device that outputs a control command including a command for the load facility. The control device includes a pre-processing unit that outputs information used to generate the control command, and a command generation unit that outputs the control command, on the basis of the information output by the pre-processing unit. The pre-processing unit includes a prediction unit that outputs electric power expected to be output by the electric power generation facility as estimated generation electric power, on the basis of the solar radiation amount. The command generation unit includes a load command unit that outputs the control command including a command for increasing and decreasing the load electric power to the load facility, on the basis of the estimated generation electric power.Type: GrantFiled: March 30, 2020Date of Patent: May 21, 2024Assignee: IHI CORPORATIONInventors: Norihiro Takai, Akira Takami, Masato Kotake, Seiichi Nakajima
-
Patent number: 11908142Abstract: A method for the computing and memory resource-conserving semantic segmentation of image data of an imaging sensor with the aid of an artificial neural network, in particular, a convolutional neural network, the artificial neural network including an encoder path and a decoder path. The method includes: dividing an input tensor into at least one first slice tensor and at least one second slice tensor as a function of a division function, the input tensor being dependent on the image data; outputting the at least one first slice tensor to the decoder path of the neural network; connecting the at least one first slice tensor to the at least one second slice tensor as a function of a connecting function to obtain an output tensor; and outputting the output tensor to the encoder path of the artificial neural network.Type: GrantFiled: September 26, 2019Date of Patent: February 20, 2024Assignee: ROBERT BOSCH GMBHInventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Patent number: 11875581Abstract: A method for generating a monitoring image. The method includes: providing an image sequence of the surroundings to be monitored with the aid of an imaging system; determining at least one monitoring area and at least one periphery area of at least one image of the image sequence with the aid of a learning-based semantic segmentation method; compressing the monitoring area of the at least one image of the image sequence with a first compression quality; and compressing the periphery area of the at least one image of the image sequence with a second compression quality to generate the compressed monitoring image, the second compression quality being lower than the first compression quality.Type: GrantFiled: July 8, 2021Date of Patent: January 16, 2024Assignee: ROBERT BOSCH GMBHInventors: Fabian Brickwedde, Uwe Brosch, Masato Takami, Gregor Blott
-
Publication number: 20230114524Abstract: The invention relates to a method for determining a noteworthy sub-sequence (114a) of a monitoring image sequence (110) of a monitoring area comprising the following steps: providing an audio signal (S1) from the monitoring area, at least partially including a time period of the monitoring image sequence; providing the monitoring image sequence (S1) of the environment to be monitored, which has been generated by an imaging system; determining at least one segment of the audio signal from the provided audio signal, which has unusual noises (S2); determining at least one segment of the monitoring image sequence having unusual movements within the environment to be monitored (S3); determining a correlation between the at least one segment of the audio signal having unusual noises (114a) and the at least one segment of the monitoring image sequence with unusual movements (114a) in order to determine a noteworthy sub-sequence (114) of the monitoring image sequence (110).Type: ApplicationFiled: June 21, 2021Publication date: April 13, 2023Inventors: Christian Neumann, Christian Stresing, Gregor Blott, Masato Takami
-
Patent number: 11610096Abstract: An evaluation system for processing measured data which include physical measured data detected with the aid of one or multiple sensors, and/or realistic synthetic measured data of the sensor(s), into one or multiple evaluation results. The system includes at least two input stages independent from each other, which are designed to receive measured data and process these measured data into precursors. At least one processing stage, receives the precursors from all input stages as inputs and is designed to process one or multiple input precursor(s) into a shared intermediate product. At least one output stage, which is designed to process the intermediate product into one or multiple evaluation result(s) of the evaluation system. A method for training the evaluation system. A method for operating the evaluation system is also provided.Type: GrantFiled: December 3, 2020Date of Patent: March 21, 2023Assignee: ROBERT BOSCH GMBHInventors: Masato Takami, Uwe Brosch, Dimitrios Bariamis, Emil Schreiber
-
Patent number: 11468687Abstract: A method for training a machine learning system, in which image data are fed into a machine learning system with processing of at least a part of the image data by the machine learning system. The method includes synthetic generation of at least a part of at least one depth map that includes a plurality of depth information values. The at least one depth map is fed into the machine learning system with processing of at least a part of the depth information values of the at least one depth map. The machine learning system is then trained based on the processed image data and based on the processed depth information values of the at least one depth map, with adaptation of a parameter value of at least one parameter of the machine learning system, the adapted parameter value influencing an interpretation of input data by the machine learning system.Type: GrantFiled: October 16, 2018Date of Patent: October 11, 2022Assignee: Robert Bosch GmbHInventors: Masato Takami, Uwe Brosch
-
Publication number: 20220019821Abstract: A method for generating a monitoring image. The method includes: providing an image sequence of the surroundings to be monitored with the aid of an imaging system; determining at least one monitoring area and at least one periphery area of at least one image of the image sequence with the aid of a learning-based semantic segmentation method; compressing the monitoring area of the at least one image of the image sequence with a first compression quality; and compressing the periphery area of the at least one image of the image sequence with a second compression quality to generate the compressed monitoring image, the second compression quality being lower than the first compression quality.Type: ApplicationFiled: July 8, 2021Publication date: January 20, 2022Inventors: Fabian Brickwedde, Uwe Brosch, Masato Takami, Gregor Blott
-
Publication number: 20210343019Abstract: A method for the computing and memory resource-conserving semantic segmentation of image data of an imaging sensor with the aid of an artificial neural network, in particular, a convolutional neural network, the artificial neural network including an encoder path and a decoder path. The method includes: dividing an input tensor into at least one first slice tensor and at least one second slice tensor as a function of a division function, the input tensor being dependent on the image data; outputting the at least one first slice tensor to the decoder path of the neural network; connecting the at least one first slice tensor to the at least one second slice tensor as a function of a connecting function to obtain an output tensor; and outputting the output tensor to the encoder path of the artificial neural network.Type: ApplicationFiled: September 26, 2019Publication date: November 4, 2021Inventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Patent number: 11113561Abstract: Method for the calculation resource-saving semantic segmentation of image data of an imaging sensor with the aid of an artificial neural network, in particular, of a convolutional neural network, the artificial neural network including an encoder path, a decoder path, the encoder path transitioning into the decoder path, the transition taking place via a discriminative path, the following steps taking place in the discriminative path: dividing an input tensor as a function of a division function into at least one first slice tensor and at least one second slice tensor, the input tensor originating from the encoder path; connecting the at least one first slice tensor to the at least one second slice tensor as a function of a connection function in order to obtain a class tensor; and outputting the class tensor to the decoder path of the neural network.Type: GrantFiled: October 2, 2019Date of Patent: September 7, 2021Assignee: Robert Bosch GmbHInventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Patent number: 11100358Abstract: A method for the calculation resource-saving semantic segmentation of image data of an imaging sensor with an artificial neural network, in particular, of a convolutional neural network, the artificial neural network including an encoder path, a decoder path (and a skip component), including: initial connection (merge) of an input tensor to a skip tensor with an initial connection (merge) function/connection instruction to obtain a merged tensor, the input tensor and the skip tensor being dependent on the image data; application of a function of a neural network, in particular, of a convolution to the merged tensor to obtain a proof reader tensor; second connection (merge) of the proof reader tensor to the input tensor with a second connection (merge) function/connection instruction to obtain an output tensor; outputting the output tensor to the decoder path of the artificial neural network.Type: GrantFiled: October 2, 2019Date of Patent: August 24, 2021Assignee: Robert Bosch GmbHInventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Publication number: 20210182652Abstract: An evaluation system for processing measured data which include physical measured data detected with the aid of one or multiple sensors, and/or realistic synthetic measured data of the sensor(s), into one or multiple evaluation results. The system includes at least two input stages independent from each other, which are designed to receive measured data and process these measured data into precursors. At least one processing stage, receives the precursors from all input stages as inputs and is designed to process one or multiple input precursor(s) into a shared intermediate product. At least one output stage, which is designed to process the intermediate product into one or multiple evaluation result(s) of the evaluation system. A method for training the evaluation system. A method for operating the evaluation system is also provided.Type: ApplicationFiled: December 3, 2020Publication date: June 17, 2021Inventors: Masato Takami, Uwe Brosch, Dimitrios Bariamis, Emil Schreiber
-
Publication number: 20210182577Abstract: A method for training a machine learning system, in which image data are fed into a machine learning system with processing of at least a part of the image data by the machine learning system. The method includes synthetic generation of at least a part of at least one depth map that includes a plurality of depth information values. The at least one depth map is fed into the machine learning system with processing of at least a part of the depth information values of the at least one depth map. The machine learning system is then trained based on the processed image data and based on the processed depth information values of the at least one depth map, with adaptation of a parameter value of at least one parameter of the machine learning system, the adapted parameter value influencing an interpretation of input data by the machine learning system.Type: ApplicationFiled: October 16, 2018Publication date: June 17, 2021Inventors: Masato Takami, Uwe Brosch
-
Publication number: 20200110961Abstract: A method for the calculation resource-saving semantic segmentation of image data of an imaging sensor with an artificial neural network, in particular, of a convolutional neural network, the artificial neural network including an encoder path, a decoder path (and a skip component), including: initial connection (merge) of an input tensor to a skip tensor with an initial connection (merge) function/connection instruction to obtain a merged tensor, the input tensor and the skip tensor being dependent on the image data; application of a function of a neural network, in particular, of a convolution to the merged tensor to obtain a proof reader tensor; second connection (merge) of the proof reader tensor to the input tensor with a second connection (merge) function/connection instruction to obtain an output tensor; outputting the output tensor to the decoder path of the artificial neural network.Type: ApplicationFiled: October 2, 2019Publication date: April 9, 2020Inventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Publication number: 20200110960Abstract: Method for the calculation resource-saving semantic segmentation of image data of an imaging sensor with the aid of an artificial neural network, in particular, of a convolutional neural network, the artificial neural network including an encoder path, a decoder path, the encoder path transitioning into the decoder path, the transition taking place via a discriminative path, the following steps taking place in the discriminative path: dividing an input tensor as a function of a division function into at least one first slice tensor and at least one second slice tensor, the input tensor originating from the encoder path; connecting the at least one first slice tensor to the at least one second slice tensor as a function of a connection function in order to obtain a class tensor; and outputting the class tensor to the decoder path of the neural networkType: ApplicationFiled: October 2, 2019Publication date: April 9, 2020Inventors: Ferran Diego Andilla, Dimitrios Bariamis, Masato Takami, Uwe Brosch
-
Patent number: 10482347Abstract: A method for providing an image of a contoured surface includes: a) recording images of one or a plurality of regions of the surface using different light exposure and/or illumination; b) generating an optimized image for each of the regions from the plurality of recorded images; and c) assembling the optimized images generated for the individual regions of the surface to form an optimized total image of the surface.Type: GrantFiled: June 20, 2014Date of Patent: November 19, 2019Assignee: BEISSBARTH GMBHInventors: Volker Uffenkamp, Masato Takami, Guenter Nobis
-
Patent number: 9846031Abstract: A method for testing a vehicle underbody of a motor vehicle includes: recording at least one image of at least one region of the vehicle underbody of the motor vehicle using a camera device; producing a three-dimensional depth image with the aid of the at least one recorded image of the at least one region of the vehicle underbody of the motor vehicle; and testing the at least one region of the vehicle underbody of the motor vehicle with the aid of the produced three-dimensional depth image of the vehicle underbody using optical image recognition.Type: GrantFiled: June 11, 2013Date of Patent: December 19, 2017Assignee: ROBERT BOSCH GMBHInventors: Guenter Nobis, Volker Uffenkamp, Masato Takami
-
Patent number: 9580018Abstract: A recording device for recording images of an underbody of a vehicle includes: at least one camera recording images of areas of the underbody; and mirrors situated to project images of the underbody into the at least one camera. The mirrors are situated in such a way that the mirrors project adjoining areas of the underbody transversely to the driving direction of the vehicle into the camera as image areas situated one above the other.Type: GrantFiled: May 14, 2013Date of Patent: February 28, 2017Assignee: ROBERT BOSCH GMBHInventor: Masato Takami
-
Publication number: 20160148073Abstract: A method for providing an image of a contoured surface includes: a) recording images of one or a plurality of regions of the surface using different light exposure and/or illumination; b) generating s an optimized image for each of the regions from the plurality of recorded images; and c) assembling the optimized images generated for the individual regions of the surface to form an optimized total image of the surface.Type: ApplicationFiled: June 20, 2014Publication date: May 26, 2016Inventors: Volker Uffenkamp, Masato Takami, Guenter Nobis
-
Publication number: 20150260511Abstract: A method for testing a vehicle underbody of a motor vehicle includes: recording at least one image of at least one region of the vehicle underbody of the motor vehicle using a camera device; producing a three-dimensional depth image with the aid of the at least one recorded image of the at least one region of the vehicle underbody of the motor vehicle; and testing the at least one region of the vehicle underbody of the motor vehicle with the aid of the produced three-dimensional depth image of the vehicle underbody using optical image recognition.Type: ApplicationFiled: June 11, 2013Publication date: September 17, 2015Inventors: Guenter Nobis, Volker Uffenkamp, Masato Takami