Back to results
US 11,027,727 B2Granted
Apparatus for responding to vehicle water splashing, system having the same and method thereof
AssigneesHyundai Motor Company, Kia Motors Corporation
InventorJung Ho Lim
Life of this patent
Estimating the term…
Abstract
An apparatus for responding to vehicle water splashing includes a processor determining the vehicle water splashing based on image data of a nearby vehicle and determining dangerousness caused by the vehicle water splashing to perform vehicle control and storage storing information determined by the processor and the image data of the nearby vehicle.
Claims15
An apparatus for responding to vehicle water splashing, the apparatus comprising:
- a processor, wherein the processor is configured to:
- determine, based on image data of a nearby vehicle, whether vehicle water splashing occurs, and
- determine dangerousness caused by the vehicle water splashing to perform vehicle control when the processor determines that the vehicle water splashing occurs;
- and
- a storage configured to store information determined by the processor and the image data of the nearby vehicle,
- wherein the processor is configured to:
- accumulate image data of the vehicle water splashing of a front vehicle as the nearby vehicle;
- extract a plurality of waveforms of the vehicle water splashing occurring when the front vehicle is driving, based on the accumulated image data of the front vehicle, each waveform of the plurality of waveforms of the vehicle water splashing representing a size or shape of splashing water caused by the front vehicle;
- operate a learning network that learns the vehicle water splashing, based on the plurality of waveforms of the vehicle water splashing from the accumulated image data of the front vehicle, the operation of the learning network comprising generation and storage of dangerousness information for each waveform of the plurality of waveforms of the vehicle water splashing;
- input a newly extracted waveform of the vehicle water splashing to the learning network;
- output dangerousness information corresponding to the inputted newly extracted waveform as a learning result based on the stored dangerousness information;
- determine whether the vehicle water splashing occurs based on the outputted dangerousness information;
- and
- determine the dangerousness.
11 more elements
A vehicle system comprising:
- at least a sensor module configured to obtain image data and driving information of a nearby vehicle;
- and
- an apparatus for responding to vehicle water splashing, wherein the apparatus for responding to the vehicle water splashing is configured to:
- determine, based on the image data of the nearby vehicle, whether vehicle water splashing occurs;
- and
- determine dangerousness caused by the vehicle water splashing to perform vehicle control when the apparatus determines that the vehicle water splashing occurs,
- wherein the apparatus for responding to the vehicle water splashing is further configured to accumulate image data of the vehicle water splashing of a front vehicle as the nearby vehicle and extract a plurality of waveforms of the vehicle water splashing occurring when the front vehicle is driving, based on the accumulated image data of the front vehicle, each waveform of the plurality of waveforms of the vehicle water splashing representing a size or shape of splashing water caused by the front vehicle,
- wherein the apparatus for responding to the vehicle water splashing includes a learning network that learns the vehicle water splashing, based on the plurality of waveforms of the vehicle water splashing from the accumulated image data of the front vehicle, the learning network being configured to generate and store dangerousness information for each waveform of the plurality of waveforms of the vehicle water splashing, and
- wherein the apparatus for responding to the vehicle water splashing is configured to:
- input a newly extracted waveform of the vehicle water splashing to the learning network;
- output dangerousness information corresponding to the inputted newly extracted waveform as a learning result based on the stored dangerousness information;
- determine whether the vehicle water splashing occurs based on the outputted dangerousness information;
- and
- determine the dangerousness.
11 more elements
A method for responding to vehicle water splashing, the method comprising:
- obtaining image data and driving information of a nearby vehicle;
- determining, based on the image data of the nearby vehicle, whether vehicle water splashing occurs;
- and
- determining dangerousness caused by the vehicle water splashing to perform vehicle control when determining that the vehicle water splashing occurs,
- wherein the determining of the vehicle water splashing includes accumulating image data of the vehicle water splashing of a front vehicle as the nearby vehicle and extracting a plurality of waveforms of the vehicle water splashing occurring when the front vehicle is driving, based on the accumulated image data of the front vehicle, each waveform of the plurality of waveforms of the vehicle water splashing representing a size or shape of splashing water caused by the front vehicle,
- wherein the method for responding to the vehicle water splashing includes operating a learning network that learns the vehicle water splashing, based on the plurality of waveforms of the vehicle water splashing from the accumulated image data of the front vehicle, the learning network being configured to generate and store dangerousness information for each waveform of the plurality of waveforms of the vehicle water splashing, and
- wherein the determining of the dangerousness includes:
- inputting a newly extracted waveform of the vehicle water splashing to the learning network;
- outputting dangerousness information corresponding to the inputted newly extracted waveform as a learning result based on the stored dangerousness information;
- determining whether the vehicle water splashing occurs based on the outputted dangerousness information;
- and
- determining the dangerousness.
9 more elements
Dependencies are inferred from the claim text.