Vehicle type recognition method based on CNN and domain adaptive learning

Abstract

The invention relates to a vehicle type recognition method based on a CNN and domain adaptive learning. The method comprises steps of: establishing a CNN-based initial model by adding a rotation-invariant layer in an Alexnet network, distinguishing a discriminant layer and designing a new objective function; separately extracting the feature maps of different-domain sample convolution layers by using the established initial model, calculating the cosine similarity between the sample feature maps, determining the shared convolution kernel or the non-shared convolution kernel of the CNN, retaining the weight and the offset of the shared convolution kernel, and updating the weight and the offset of the non-shared convolution kernel; based on a target-domain training sample, calculating the cosine similarity between respective feature map layers and the average similarity of the entire target domain, and clustering each type of similar feature maps according to the average similarity; expanding source-domain samples with similar distribution characteristics in the target domain to new samples in the target domain, adjusting the entire CNN model by using the new samples in the target domain, and then using a softmax classifier to classify the vehicle types of the test samples in the target domain.

Description

technical field [0001] The invention relates to the technical field of identification, in particular to a vehicle identification method based on CNN and domain adaptive learning. Background technique [0002] Vehicle type recognition in traffic video images, as a key technology of traffic monitoring and management, has been widely concerned by researchers for a long time. Due to the complex and diverse appearance of the vehicle, which is affected by many factors such as background, light intensity, and angle, the stability is greatly disturbed in practical applications. In recent years, deep learning theory has developed rapidly. Unlike traditional feature extraction algorithms that rely on prior knowledge, deep neural networks can adaptively construct feature descriptions driven by training data, which has higher flexibility and applicability. As an important technology to realize deep learning, convolutional neural network has successfully trained the first deep neural ne...

AI Technical Summary

Problems solved by technology

However, with the complexity of classification tasks, such as a large number of categories, category specialization, specialization, etc., the cost of collecting sufficient labeled data for the target category has greatly increased.

Images