Back to results
US 12,743,894 B2Granted
Computing apparatus and method for inspecting learning data
AssigneesHyundai Motor Company, Kia Corporation
InventorsDeuk Hyeon Kim, Min Sung Son, Sin Hyun Jeon
Life of this patent
Estimating the term…
Abstract
A computing device includes a parking space recognition device that recognizes a parking space using at least one parking space recognition model for recognizing the parking space based on training data for the parking space and a data inspection device that inspects information about a parking line and a parking slot based on parking space recognition data recognized by the parking space recognition device.
Claims18
A computing device, comprising:
- a memory storing computer-executable instructions;
- and
- a processor configured to access the memory and execute the instructions, wherein the processor is configured to:
- recognize a parking space using at least one parking space recognition model configured to recognize the parking space based on training data for the parking space;
- inspect information about a parking line and a parking slot based on parking space recognition data recognized by a parking space recognition device;
- combine results recognized from the at least one parking space recognition model to recognize the parking space and output the parking space recognition data;
- determine position accuracy of the parking space recognition data based on position information of the parking line and the parking slot;
- determine type accuracy of the parking space recognition data based on type information of the parking line and the parking slot;
- and
- calculate a probability value of a probability that there will be the parking line and the parking slot for each cell obtained by dividing the parking space and determines the position accuracy of the parking space recognition data based on the number of cells in which the probability value is within a reference range;
- wherein the at least one parking space recognition model configured to divide an input image for the parking space into cells with a predetermined size and number, and to recognize a position and a type of the parking line and the parking slot for each divided cell;
- and
- wherein the parking space recognition data includes parking line information about a position of the parking line and a type of the parking line and parking slot information about a position of the parking slot and a type of the parking slot.
10 more elements
A method for inspecting training data, the method comprising:
- recognizing, by a parking space recognition device, a parking space using at least one parking space recognition model configured to recognize the parking space based on training data for the parking space;
- and
- inspecting information about a parking line and a parking slot based on the recognized parking space recognition data;
- wherein the recognizing of the parking space includes:
- dividing, by the at least one parking space recognition model, an input image for the parking space into cells with a predetermined size and number and recognizing, by the at least one parking space recognition model, a position and a type of the parking line and the parking slot for each divided cell;
- and
- combining results recognized from the at least one parking space recognition model to recognize the parking space and outputting the parking space recognition data;
- and
- wherein the inspecting includes:
- determining position accuracy of the parking space recognition data based on position information of the parking line and the parking slot;
- and
- determining type accuracy of the parking space recognition data based on type information of the parking line and the parking slot;
- wherein the determining of the position accuracy includes:
- calculating a probability value of a probability that there will be the parking line and the parking slot for each cell obtained by dividing the parking space and determining the position accuracy of the parking space recognition data based on the number of cells in which the probability value is within a reference range;
- and
- wherein the parking space recognition data includes parking line information about a position of the parking line and a type of the parking line and parking slot information about a position of the parking slot and a type of the parking slot.
13 more elements
Dependencies are inferred from the claim text.