Vehicle type identification device and method for realizing cross-scene cold start based on transfer learning

Abstract

The invention discloses a vehicle type identification device and method for realizing cross-scene cold start based on transfer learning. The vehicle type recognition device is provided with three components, namely a first component, a second component and a third component, Data processing unit, a network training unit and an identification application unit, According to the invention, only a small amount of vehicle image data marked with vehicle type information exists in a target domain; A domain adaptation method of transfer learning is adopted. The parameter difference of the vehicle typerecognition convolutional neural network model between the source domain of the old vehicle type recognition scene and the target domain of the new vehicle type recognition scene is reduced, parameter migration of the vehicle type recognition convolutional neural network model from the old vehicle type recognition scene to the new vehicle type recognition scene is achieved, and cross-scene cold start vehicle type recognition is achieved. The method can be used for the initial stage of actual intelligent traffic engineering, enables the convolutional neural network model to achieve a high accuracy rate on a vehicle model identification task under the condition of lacking vehicle image data with marked vehicle model information in an actual vehicle model identification scene, and has a goodapplication prospect.

Description

technical field [0001] The invention relates to a vehicle type recognition device and method for realizing cross-scenario cold start based on transfer learning, and belongs to the technical field of computer vision and image processing. Background technique [0002] At first introduce and illustrate the meaning of the following technical terms involved in the present invention: [0003] Fine-tune is a method of transfer learning: continue to train a model for a new task on the basis of an already trained model. It is generally considered that the first few layers of the convolutional neural network CNN (Convolutional Neural Network) (if not specified, the network of the present invention is a convolutional neural network) only extract the general underlying features, so when training the model of a new task, only need The parameters of the last few layers of training are to extract the unique features of the new task. Fine-tuning can speed up the training of convolutional ...

AI Technical Summary

Problems solved by technology

However, the labeled image data in the actual model recognition scene is relatively small, and it is difficult to achieve a high recognition accuracy.

Images