Target recognition method, device, equipment and storage medium

Abstract

The present disclosure provides an object recognition method, device, equipment and storage medium, which are applied in the field of image processing. Among them, the image recognition network used for target recognition includes a feature extraction network, a pooling network, an expanded convolution network, and a path aggregation network. The path aggregation network includes a feature pyramid network and a memory network for storing image features. The method includes: in the image recognition network, through the feature extraction network, the pooling network, the dilated convolution network, and the feature pyramid network, the image to be recognized is sequentially subjected to feature extraction, pooling processing, dilated convolution processing, and feature aggregation processing to obtain The recognition result of the target object, wherein the image features stored in the memory network are utilized in the feature aggregation process. Therefore, by introducing an expanded convolutional network that can extract global image information and reduce the computational burden of the model, and a memory network that can store image information, both image recognition accuracy and image recognition speed are achieved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to an object recognition method, device, equipment and storage medium. Background technique [0002] With the development of image processing technology, deep learning networks are gradually applied to many aspects of image processing, including the recognition of targets on images. [0003] Taking coal gangue identification as an example, the traditional manual identification method has low efficiency and poor security, and the accuracy rate varies from person to person, and large-scale coal gangue identification cannot be realized. Therefore, deep learning network can be used to identify coal gangue to solve the above problems . However, in the field of image recognition, deep learning networks with complex structures have slow recognition speeds and a large amount of calculation, which cannot meet the requirements of fast or even real-time recognition. Lightweigh...

AI Technical Summary

Problems solved by technology

[0005] The present disclosure provides a target recognition method, device, equipment and storage medium to solve the problem that the deep learning network is difficult to achieve a compromise between recognition accuracy and speed

Images