Hierarchical front face bayonet vehicle model recognition method

Abstract

The invention discloses a hierarchical front face bayonet vehicle model recognition method. The hierarchical front face bayonet vehicle model recognition method regards a vehicle front face detectionand positioning technology and a vehicle logo positioning technology as the basis, adopts a plurality of deep convolutional neural networks for integrated learning, realizes the recognition of three tasks including brand vehicle logo, vehicle model and vehicle model year of a vehicle respectively (wherein the vehicle model year contains the vehicle logo and the vehicle model, and the vehicle modelcontains the vehicle logo), then combines output confidence of learning classifiers at different levels, a similar vehicle model confusion matrix obtained through prior statistics and an inclusion relationship of the three levels, and outputs a robust vehicle model recognition result. The vehicle model identified by adopting the hierarchical front face bayonet vehicle model recognition method canbe specific to the brand, model and year of the vehicle; and the vehicle model precision of the vehicle can be further improved through the integration of the three classifiers.

Description

technical field [0001] The invention belongs to the technical field of video surveillance and relates to a method for identifying vehicle types with graded front face bayonets. Background technique [0002] With the continuous development of our national economy, traffic management has become more and more important in people's economic and social activities. People also put forward more and more new requirements on the level and quality of traffic management. Therefore, in-depth research on intelligent transportation becomes more and more meaningful. [0003] Searching for specific target vehicles in a large amount of traffic checkpoint video data is of great significance for traffic management and video surveillance. Traditional technical means search and locate by identifying the vehicle plate number. Although the accuracy of license plate recognition is high, such technology is basically not practical under conditions such as decked plates, no license plates, and licen...

AI Technical Summary

Problems solved by technology

[0006] Some of these technologies use artificial feature extraction methods, but such features are very dependent on human prior knowledge and have poor robustness; some extract robust features through deep learning, and then use template matching to identify vehicle models. There are template limitations, poor matching accuracy, and low efficiency in the method; some use convolutional neural network to learn offline training, but they can only recognize existing brands and models in the training library, and are helpless for new models that are constantly on the market

Images