Deep neural network for fine recognition of vehicle attributes and training method thereof

Abstract

The invention discloses a deep neural network for the fine recognition of vehicle attributes and a training method thereof. The network comprises a depth residual network, a feature migration layer, aplurality of all-connection layers, a plurality of loss calculation units, and a plurality of parameter updating units. The depth residual network is used for carrying out feature extraction on an input image to obtain a feature image. The feature migration layer comprises a plurality of feature migration units and is used for enabling each of all feature migration units to be adapted to specifictasks according to the features shared by all attribute identifying tasks. The plurality of all-connection layers correspond to the branches of all attribute identifying tasks and are connected withthe feature migration layer so as to obtain feature vectors corresponding to all attribute identifying tasks. The plurality of loss calculation units correspond to the branches of all attribute identifying tasks and are respectively connected with the all-connection layers. The plurality of loss calculation units are used for calculating the loss of a loss function by adopting cross entropies as multiple classifiers. The plurality of parameter updating units correspond to the attribute identifying tasks and are connected with the loss calculation units. The parameter updating units are used for returning the loss based on the random gradient descent optimization algorithm, and updating parameters. According to the invention, various fine vehicle attributes can be identified at the same time by adopting only one neural network.

Description

technical field [0001] The invention relates to the technical field of computer vision and pattern recognition, in particular to a deep neural network for finely recognizing vehicle attributes and a training method thereof. Background technique [0002] Vehicle refined attribute recognition technology is a basic technology in the field of intelligent transportation security. Identifying vehicle attributes can improve the computer's understanding of target vehicles and help solve some more difficult problems in the field of traffic security, such as automatic vehicle retrieval and vehicle re-identification. . [0003] Vehicle attribute recognition is a classic problem in computer vision and pattern recognition. The recognized vehicle attributes generally include the color of the vehicle, the type of the vehicle, and the brand of the vehicle. attributes, and classify and label vehicles. The key technology to solve this kind of problem is the image recognition and classificat...

AI Technical Summary

Problems solved by technology

[0008] However, the above-mentioned Chinese patent applications with publication numbers 105678275A, 105787466A, 103500327A, and 105930812A mainly use some low-level features on statistics and gradients to characterize the type of vehicle, and do not use high-level semantic features; publication numbers are 105678275A, 105787466A, The Chinese patent applications 102737221B and 103544480A have data preprocessing or result postprocessing steps, but the process is cumbersome; the Chinese patent application with the publication number 105488517A is a big data vehicle brand recognition method, which uses deep learning technology, but its depth The network is too simple, with only four convolutional layers and two fully connected layers, and the recognizable vehicle perspective is single, limited to the brand recognition of the monitored vehicle pictures of the front face

Images