Model training method, domain-adaptive visual position identification method and device

Abstract

The invention discloses a model training method and a domain self-adaptive visual position identification method and device, and belongs to the technical field of computer vision, and the method comprises the steps: building an image feature extraction model based on a deep neural network; constructing a training set according to the standard data set, wherein each training sample in the trainingset comprises a target image, a positive sample and s negative samples; using the training set to train the image feature extraction model; wherein in the image feature extraction model, the feature extraction network comprises a plurality of first networks which are cascaded; wherein the first network is formed by sequentially connecting one or more second networks and a maximum pooling layer, and the maximum pooling layer is used for feature selection; the second network comprises convolution layers which are connected in sequence and used for feature extraction; the batch standardization layer is used for carrying out zero-mean standardization processing; the activation function layer is used for carrying out activation processing; the local feature aggregation network is used for aggregating local features to obtain feature vectors of the image. According to the invention, the robustness of visual position identification can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a model training method, a domain adaptive visual position recognition method and a device. Background technique [0002] Visual location recognition specifically refers to extracting features from an image, and then identifying the geographic location of the image based on the extracted image features. With the development of autonomous driving, the increasing demand for autonomously navigating mobile robots, and the increasing popularity of virtual reality and augmented reality, the research on visual position recognition is widely used in the field of computer vision, the robot community and other related fields. aroused widespread concern. [0003] In the early period of computer vision research, image features were mainly extracted by artificially designed methods of extracting image feature points, such as scale-invariant feature transform (SIFT) fe...

AI Technical Summary

Problems solved by technology

However, the deep neural network needs to be trained before use, and due to the influence of viewing angle, illumination and other factors, the feature distribution of the image used for training is often quite different from the feature distribution of the actual image to be recognized. In this case, The accuracy of visual place recognition is not guaranteed

In general, the robustness of existing visual place recognition methods is low

Images