Method and apparatus for vehicle damage assessment, electronic device, and computer storage medium

An apparatus for vehicle damage assessment, the apparatus comprising:

• at least one processor;
• and
• a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
• extracting a first feature characterizing a part of a vehicle and a second feature characterizing a damage type of the vehicle from an input image;
• integrating the first feature and the second feature to generate a third feature which characterizes a corresponding relation between the part and the damage type;
• converting the third feature into a characteristic vector;
• and
• determining a damage recognition result of the vehicle based on the characteristic vector, wherein the operations are performed by a neural network comprising a first convolutional neural network, a second convolutional neural network, and a given post convolutional neural network, wherein the neural network is trained by:
• collecting a set of images of damaged vehicles from a database;
• training the first convolutional neural network by using first images in the set of images to obtain a first parameter of the first convolutional neural network, the first convolutional neural network being trained to have a mapping relation between the input image and the first feature characterizing the part of the vehicle;
• training the second convolutional neural network by using second images in the set of images to obtain a second parameter of the second convolutional neural network, the second convolutional neural network being trained to have a mapping relation between the input image and the second feature characterizing the damage type;
• and
• training the post convolutional neural network, wherein during training the post convolutional neural network:
• the first parameter of the first convolutional neural network and the second parameter of the second convolutional neural network are fixed, third images in the set of image are used as inputs of the first convolutional neural network and the second convolutional neural network, and a first output of the first convolutional neural network and a second output of the second convolutional neural network are used as inputs of the given post convolutional neural network, wherein the third convolutional neural network being trained to have a mapping relation between a combination of the first feature characterizing the part and the second feature characterizing the damage type, and the damage recognition result.

A non-transitory computer-readable storage medium, having a computer program stored therein, wherein the computer program, when executed by a processor, causes the processor to perform operations, the operation comprising:

• extracting, from an input image, a first feature characterizing a part of a vehicle and a second feature characterizing a damage type of the vehicle;
• integrating the first feature and the second feature to generate a third feature characterizing a corresponding relation between the part and the damage type;
• converting the third feature into a characteristic vector;
• and
• determining a damage recognition result of the vehicle based on the characteristic vector, wherein the method is performed by a neural network comprising a first convolutional neural network, a second convolutional neural network, and a given post convolutional neural network, wherein the neural network is trained by:
• collecting a set of images of damaged vehicles from a database;
• training the first convolutional neural network by using first images in the set of images to obtain a first parameter of the first convolutional neural network, the first convolutional neural network being trained to have a mapping relation between the input image and the first feature characterizing the part of the vehicle;
• training the second convolutional neural network by using second images in the set of images to obtain a second parameter of the second convolutional neural network, the second convolutional neural network being trained to have a mapping relation between the input image and the second feature characterizing the damage type;
• and
• training the post convolutional neural network, wherein during training the post convolutional neural network:
• the first parameter of the first convolutional neural network and the second parameter of the second convolutional neural network are fixed, third images in the set of image are used as inputs of the first convolutional neural network and the second convolutional neural network, and a first output of the first convolutional neural network and a second output of the second convolutional neural network are used as inputs of the given post convolutional neural network, wherein the third convolutional neural network being trained to have a mapping relation between a combination of the first feature characterizing the part and the second feature characterizing the damage type, and the damage recognition result.