-
公开(公告)号：US20210173787A1
公开(公告)日：2021-06-10
申请号：US17048045
申请日：2019-04-09
Applicant: AImotive Kft.
Inventor： Gyula Nagy , Márton Fehér
IPC: G06F12/0875 , G06F13/16
Abstract: An accelerator and a system for accelerating operations are disclosed. A respective apparatus comprises an interface configured to couple the apparatus to an interconnect, a plurality of processing modules, each processing module configured to process data, a control module configured to control processing of each of the plurality of processing modules, and a cache module configured to store at least a portion of data processed by at least one of the plurality of processing modules. Each processing module includes a processing core configured to process data by performing an operation on the data using a plurality of processing elements, an input control unit configured to retrieve data via the interface and data stored in the cache module and to provide the retrieved data to the processing core, and an output control unit configured to provide data processed by the processing core to the interface and the cache module.
-
公开(公告)号：US20200175721A1
公开(公告)日：2020-06-04
申请号：US16208997
申请日：2018-12-04
Applicant: AImotive Kft.
Inventor： Zoltán Fegyver , László Babay
Abstract: The invention is a method for camera misalignment detection by means of processing images of a camera fixed to a vehicle and having a field of view containing a vehicle image area (11) imaging a portion of the vehicle and a remaining area (12), wherein in said processing step a plurality of reference locations (21) within an input image are used, said reference locations (21) being determined as edge locations along a boundary of the vehicle image area (11) in a reference image, and said processing step comprises checking at the reference locations (21) within the input image whether said reference locations (21) are edge locations by ascertaining at each reference location (21) whether a magnitude of an image gradient is above a gradient threshold limit, and alerting misalignment depending on an ascertained subset of the reference locations (21) where the gradient threshold limit is not reached. The invention also relates to a camera system, a computer program product and a computer-readable medium embodying the method.
-
3.发明公开公开(公告)号：US20240343293A1
公开(公告)日：2024-10-17
申请号：US18577835
申请日：2022-06-28
Applicant: aiMotive Kft.
Inventor： Roland Kohári
Abstract: The invention is a steering system for use in test driving of an autonomous vehicle, comprising—a manual steering means configured to manually steer the vehicle, —a steering axle (30) attached to the manual steering means, and—a direct drive motor (35) controllably affecting a torque on the steering axle (30), wherein the direct drive motor (35) has an axis (37) of rotation being coaxial with the steering axle (30). The steering system is characterized in that—it has at least two predefined states characterizing different driving conditions, wherein each predefined state has at least one predefined disengagement limit, and—it further comprises a controller assembly operable based on a control parameter, the controller assembly being configured to detect an actual predefined state of the vehicle, and the controller assembly initiates a disengagement of the direct drive motor (35) if, based on a difference value between a prescribed value of the control parameter and an actual value of the control parameter, the at least one predefined disengagement limit corresponding to the actual predefined state is reached. The invention further relates to a disengagement method, and a data processing system, a computer program product and a computer readable medium carrying out the method.
-
公开(公告)号：US10664997B1
公开(公告)日：2020-05-26
申请号：US16208997
申请日：2018-12-04
Applicant: AImotive Kft.
Inventor： Zoltán Fegyver , László Babay
Abstract: The invention is a method for camera misalignment detection by means of processing images of a camera fixed to a vehicle and having a field of view containing a vehicle image area (11) imaging a portion of the vehicle and a remaining area (12), wherein in said processing step a plurality of reference locations (21) within an input image are used, said reference locations (21) being determined as edge locations along a boundary of the vehicle image area (11) in a reference image, and said processing step comprises checking at the reference locations (21) within the input image whether said reference locations (21) are edge locations by ascertaining at each reference location (21) whether a magnitude of an image gradient is above a gradient threshold limit, and alerting misalignment depending on an ascertained subset of the reference locations (21) where the gradient threshold limit is not reached. The invention also relates to a camera system, a computer program product and a computer-readable medium embodying the method.
-
Patent Agency Ranking
公开(公告)号：US12190226B2
公开(公告)日：2025-01-07
申请号：US17048048
申请日：2019-04-09
Applicant: AImotive Kft.
Inventor： Gyula Nagy , Márton Fehér , István Herman Weimann
IPC: G06N3/063 , G06F12/02 , G06F12/0813 , G06F12/0846
Abstract: A method for accessing and processing data by an accelerator apparatus includes retrieving at least a part of input data to be processed by the accelerator apparatus, segmenting the input data into a plurality of adjacent input tiles, the input tiles having a pre-determined size, storing at least one of the plurality of adjacent input tiles in a data buffer of the accelerator apparatus, accessing data elements of the at least one of the plurality of adjacent input tiles stored in the data buffer by positioning an input window over the data elements stored in the data buffer, to generate a plurality of input areas, wherein the input window is adjustable according to a set of parameters, and sequentially processing at least one of the plurality of input areas to at least partially process the at least one of the plurality of adjacent input tiles by the accelerator apparatus.
-
6.发明公开公开(公告)号：US20240233104A1
公开(公告)日：2024-07-11
申请号：US18559741
申请日：2022-05-09
Applicant: AiMotive Kft.
Inventor： Péter Dániel Kozma , Mátyás Léránt-Nyeste
CPC classification number: G06T7/0002 , G06T7/344 , G06T11/206 , G06T2207/30168
Abstract: The invention is a method for determining whether an input image is sufficiently sharp, comprising the steps of
providing a blur score threshold value,
inputting the input image to an image processing system,
generating, by the image processing system, a two-dimensional frequency spectrum of the input image,
generating a one-dimensional frequency spectrum from the two-dimensional frequency spectrum,
fitting a straight line on the one-dimensional frequency spectrum, and
determining a blur score value based on a residual of the fitting, and considering the input image as sufficiently sharp based on a comparison of the blur score value with the blur score threshold value.
The invention further relates to a data processing system, a computer program product and a computer readable medium carrying out the above method.-
7.发明公开公开(公告)号：US20230298181A1
公开(公告)日：2023-09-21
申请号：US18016495
申请日：2020-12-16
Applicant: aiMotive Kft.
Inventor： Ákosõ Utasi , Ádám Butykai
CPC classification number: G06T7/12 , G06T7/168 , G06T2207/20084
Abstract: The invention is a method for object segmentation in an image, comprising the steps of
inputting the image to a trained machine learning system, and
reconstructing the segmentation contour of the object.
The method is characterized by comprising the steps of
estimating, by the trained machine learning system, a representation of a segmentation contour of an object in the image, wherein the segmentation contour is a closed two-dimensional parametric curve, each point of which is defined by two coordinate components, wherein both coordinate components are parametrized, and
wherein the reconstruction of the segmentation contour of the object is carried out from the estimated representation of the segmentation contour.
The invention further relates to a data processing system, a computer program product and a computer readable medium carrying out the above method.-
公开(公告)号：US20210241082A1
公开(公告)日：2021-08-05
申请号：US17048048
申请日：2019-04-09
Applicant: AIMOTIVE KFT.
Inventor： Gyula NAGY , Márton FEHÉR , István Herman WEIMANN
IPC: G06N3/063 , G06F12/0846 , G06F12/0813 , G06F12/02
Abstract: A method for accessing and processing data by an accelerator apparatus includes retrieving at least a part of input data to be processed by the accelerator apparatus, segmenting the input data into a plurality of adjacent input tiles, the input tiles having a pre-determined size, storing at least one of the plurality of adjacent input tiles in a data buffer of the accelerator apparatus, accessing data elements of the at least one of the plurality of adjacent input tiles stored in the data buffer by positioning an input window over the data elements stored in the data buffer, to generate a plurality of input areas, wherein the input window is adjustable according to a set of parameters, and sequentially processing at least one of the plurality of input areas to at least partially process the at least one of the plurality of adjacent input tiles by the accelerator apparatus.
-
公开(公告)号：US10482003B1
公开(公告)日：2019-11-19
申请号：US16185088
申请日：2018-11-09
Applicant: AImotive Kft.
Inventor： András Bondor , László Kishonti
Abstract: Sensor data is recorded during testing of a control unit of an autonomous car in an autonomous driving mode. In response to being triggered by a disengagement event, recorded sensor data from an analysis time window prior to the disengagement event is logged. The logged sensor data is processed in a simulator using the control unit to control a virtual autonomous car to identify the inadequately operating component of the control unit. The component may be modified and retested until the disengagement event is avoided in the simulator. The control unit with the modified component may then be used to record new sensor data during testing of the control unit in the autonomous driving mode, and the simulation repeated on the new data.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.014 seconds)
