Method and system for generating a semantic point cloud map
AssigneeHuawei Technologies Co., Ltd.
InventorKeyvan Golestan Irani
Life of this patent
Estimating the term…
Abstract
A method and system for generating a semantic point cloud map. Voice input is received via a microphone and converted into text via speech-to-text synthesis. The text is decomposed into semantic data comprising a number of words, and it is determined whether keywords of the semantic data are present in an autonomous driving (AD) ontology. In response to the keywords of the semantic data being present in the AD ontology, coordinates of a point cloud map corresponding to the semantic data are determined. An association between a semantic label determined from the words of the semantic data and coordinates in the point cloud map corresponding to the semantic data is generated and stored in a memory of the computer vision system.
Claims20
A computer vision system, comprising:
- a processor system;
- a microphone coupled to the processor system;
- a plurality of sensors coupled to the processor system, the plurality of sensors configured to sense an environment surrounding a vehicle carrying the computer vision system;
- a memory coupled to the processor system, the memory tangibly storing thereon executable instructions that, when executed by the processor system, cause the computer vision system to:
- receive a voice input via the microphone;
- convert the voice input into text via speech-to-text synthesis;
- decompose the text into semantic data comprising a number of words;
- determine whether keywords of the semantic data are present in an autonomous driving (AD) ontology;
- in response to the keywords of the semantic data being present in the AD ontology:
- determine coordinates of a point cloud map corresponding to the semantic data;
- generate an association between a semantic label determined from the words of the semantic data and coordinates in the point cloud map corresponding to the semantic data;
- store the association in a memory of the computer vision system.
A method of generating a semantic point cloud map using a computer vision system of a vehicle, comprising:
- receiving a voice input via a microphone;
- converting the voice input into text via speech-to-text synthesis;
- decomposing the text into semantic data comprising a number of words;
- determining whether keywords of the semantic data are present in an autonomous driving (AD) ontology;
- in response to the keywords of the semantic data being present in the AD ontology:
- determining coordinates of a point cloud map corresponding to the semantic data;
- generating an association between a semantic label determined from the words of the semantic data and coordinates in the point cloud map corresponding to the semantic data;
- storing the association in a memory of the computer vision system.
A non-transitory machine readable medium having tangibly stored thereon executable instructions for execution by a processor system of a computer vision system, the computer vision system comprising a microphone and a plurality of sensors for localizing a vehicle in which the computer vision system is carried coupled to the processor system, wherein the executable instructions, when executed by the processor system, cause the computer vision system to:
- receive a voice input via the microphone;
- convert the voice input into text via speech-to-text synthesis;
- decompose the text into an semantic data comprising a number of words;
- determine whether keywords of the semantic data are present in an autonomous driving (AD) ontology;
- in response to the keywords of the semantic data being present in the AD ontology:
- determine coordinates of a point cloud map corresponding to the observation;
- generate an association between a semantic label determined from the words of the semantic data and coordinates in the point cloud map corresponding to the semantic data;
- store the association in a memory of the computer vision system.
Dependencies are inferred from the claim text.