Method of checking surrounding condition of vehicle
Disclosed is a method of checking a surrounding condition of a vehicle. The method of checking a surrounding condition of a vehicle may comprise identifying at least one connectable client in the vehicle, communicating with the identified client to verify performance of the client based on a determination criterion of the performance of the client, assigning an algorithm corresponding to the client based on the verified performance of the client, and checking a surrounding condition of the vehicle based on information obtained from the client as a result of processing image data according to the algorithm in the case of acquiring the image data through a sensor of the vehicle. The vehicle of the present invention can be connected to an artificial intelligence module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to 5G services and so on.
1. A method of checking a surrounding condition of a vehicle, the method comprising:
identifying at least one connectable client in the vehicle;
communicating with the identified client to verify performance of the client based on a determination criterion of the performance of the client;
assigning an algorithm corresponding to the client based on the verified performance of the client; and
checking a surrounding condition of the vehicle based on information obtained from the client as a result of processing image data according to the algorithm in the case of acquiring the image data through a sensor of the vehicle.
2. The method of claim 1 , wherein the checking the surrounding condition comprises transmitting the acquired image data to the client and checking the surrounding condition of the vehicle based on a recognition result of the image data by the algorithm assigned to the client.
3. The method of claim 2 , wherein the checking the surrounding condition comprises checking, if the recognition results of the image data by a plurality of algorithms are different from each other, the surrounding condition of the vehicle in further consideration of a recognition result by an algorithm other than the plurality of algorithms for a region of interest in the image data.
4. The method of claim 3 , wherein the plurality of algorithms have different recognition rates for identifying an object appeared in the image data.
5. The method of claim 3 , wherein the region of interest includes a region where the recognition results of the image data by the plurality of algorithms are different from each other.
6. The method of claim 1 , wherein the determination criterion of the performance of the client includes at least one of a transmission delay and a processing time of the client.
7. The method of claim 6 , wherein the checking the surrounding condition comprises checking, if a sum of the transmission delay and the processing time of the client is longer than a sensing period, the surrounding condition of the vehicle by correcting the recognition result of the image data.
8. The method of claim 6 , wherein the checking the surrounding condition comprises:
transmitting information on a region of interest to the client if the performance of the client is equal to or less than a predetermined threshold; and
checking the surrounding condition of the vehicle based on a recognition result of the algorithm corresponding to the client for the region of interest in the image data transmitted to the client.
9. The method of claim 8 , wherein the region of interest is determined based on a traveling direction of the vehicle in the image data.
10. The method of claim 1 , wherein the checking the surrounding condition comprises checking the surrounding condition of the vehicle by applying a weight corresponding to the algorithm to a processing result of the algorithm suitable for an environment around the vehicle.
11. A non transitory computer readable storage medium that stores an instruction for executing the method of claim 1 on a computer.
12. A vehicle comprising:
a sensor configured to acquire image data;
a controller configured to assign a corresponding algorithm to a client based on performance of the client verified based on a determination criterion according to a communication performed with the client in the vehicle; and
a processor configured to check a surrounding condition of the vehicle based on information obtained from the client as a result of processing the image data acquired through the sensor according to the algorithm.
13. The vehicle of claim 12 , wherein, if the image data acquired through the sensor of the vehicle is transmitted to the client, the processor checks the surrounding condition of the vehicle based on a recognition result of the image data by the algorithm of the client.
14. The vehicle of claim 13 , wherein, if the recognition results of the image data by a plurality of algorithms are different from each other, the processor checks the surrounding condition of the vehicle in further consideration of a recognition result by an algorithm other than the plurality of algorithms for a region of interest in the image data.
15. The vehicle of claim 14 , wherein the plurality of algorithms have different recognition rates for identifying an object appeared in the image data.
16. The vehicle of claim 14 , wherein the region of interest includes a region where the recognition results of the image data by the plurality of algorithms are different from each other.
17. The vehicle of claim 12 , wherein the determination criterion of the performance of the client includes at least one of a transmission delay and a processing time of the client.
18. The vehicle of claim 17 , wherein the processor checks, if a sum of the transmission delay and the processing time of the client is longer than a sensing period, the surrounding condition of the vehicle by correcting the recognition result of the image data.
19. The vehicle of claim 17 , wherein the processor checks, if the performance of the client is equal to or less than a predetermined threshold, the surrounding condition of the vehicle based on a recognition result of the algorithm corresponding to the client for the region of interest in the image data transmitted to the client.
20. The vehicle of claim 12 , wherein the processor checks the surrounding condition of the vehicle by applying a weight corresponding to the algorithm to a processing result of the algorithm suitable for an environment around the vehicle.