Image-based vehicle damage determining method and apparatus, and electronic device

Abstract

Methods, systems, and computer-readable storage media for generation of a vehicle repair plan. Implementations include actions of receiving vehicle damage data including an image of a damaged vehicle. The vehicle damage data is processed to determine a damaged area and a damage type of a portion of the damaged vehicle. A repair plan is generated for the damaged vehicle based on the damaged area and the damage type. The repair plan is initiated for the damaged vehicle.

What is claimed is: 
     
         1 . A computer-implemented method for generation of a vehicle repair plan, the method being executed by one or more processors and comprising:
 receiving, by the one or more processors, vehicle damage data comprising at least an image of a damaged vehicle;   processing, by the one or more processors, the vehicle damage data to determine a damaged area and a damage type of at least one portion of the damaged vehicle;   generating, by the one or more processors, a repair plan for the damaged vehicle based on the damaged area and the damage type; and   initiating, by the one or more processors, the repair plan for the damaged vehicle.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the repair plan comprises an estimated repair corresponding to the damaged area and the damage type. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein processing comprises applying at least one of a machine-learning algorithm, a convolutional neural network, and a region proposal network. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein processing comprises determining a plurality of damaged areas. 
     
     
         5 . The computer-implemented method of  claim 4 , further comprising ranking the plurality of damaged areas based on a severity of damage corresponding to each of the plurality of damaged areas. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the image is processed to delete features that are irrelevant for damage identification. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the vehicle damage data comprises data associated to the image. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein the image is processed by a mobile device prior to transmission to minimize transmission bandwidth requirements. 
     
     
         9 . A non-transitory computer-readable storage media coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for generation of a vehicle repair plan, the operations comprising:
 receiving vehicle damage data comprising at least an image of a damaged vehicle;   processing the vehicle damage data to determine a damaged area and a damage type of at least one portion of the damaged vehicle;   generating a repair plan for the damaged vehicle based on the damaged area and the damage type; and   initiating the repair plan for the damaged vehicle.   
     
     
         10 . The non-transitory, computer-readable medium of  claim 9 , wherein the repair plan comprises an estimated repair corresponding to the damaged area and the damage type. 
     
     
         11 . The non-transitory, computer-readable medium of  claim 9 , wherein processing comprises applying at least one of a machine-learning algorithm, a convolutional neural network, and a region proposal network. 
     
     
         12 . The non-transitory, computer-readable medium of  claim 9 , wherein processing comprises determining a plurality of damaged areas. 
     
     
         13 . The non-transitory, computer-readable medium of  claim 12 , further comprising ranking the plurality of damaged areas based on a severity of damage corresponding to each of the plurality of damaged areas. 
     
     
         14 . The non-transitory, computer-readable medium of  claim 9 , wherein the image is processed to delete features that are irrelevant for damage identification. 
     
     
         15 . The non-transitory, computer-readable medium of  claim 9 , wherein the vehicle damage data comprises data associated to the image. 
     
     
         16 . The non-transitory, computer-readable medium of  claim 9 , wherein the image is processed by a mobile device prior to transmission to minimize transmission bandwidth requirements. 
     
     
         17 . A system, comprising:
 one or more processors; and   a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for generation of a vehicle repair plan, the operations comprising:   receiving vehicle damage data comprising at least an image of a damaged vehicle;   processing the vehicle damage data to determine a damaged area and a damage type of at least one portion of the damaged vehicle;   generating a repair plan for the damaged vehicle based on the damaged area and the damage type; and   initiating the repair plan for the damaged vehicle.   
     
     
         18 . The system of  claim 17 , wherein the repair plan comprises an estimated repair corresponding to the damaged area and the damage type. 
     
     
         19 . The system of  claim 17 , wherein processing comprises applying at least one of a machine-learning algorithm, a convolutional neural network, and a region proposal network. 
     
     
         20 . The system of  claim 17 , wherein processing comprises determining a plurality of damaged areas.