Pet recognition method, device and equipment and computer readable storage medium

Abstract

The invention relates to a pet identification method, device and equipment and a computer readable storage medium. The pet identification method comprises the steps: carrying out the enhancement of a pet marking image according to a generative adversarial network, and obtaining an enhanced training image; training the enhanced training image to obtain a lightweight target detection model YOLO and an image classification model based on an addition network AdderNet; detecting the pet in the acquired image according to the YOLO model to obtain a target image only containing the pet; and inputting the target image into an AdderNet-based image classification model to obtain the category of the pet in the target image, thereby reducing the training cost of the neural network model, reducing the hardware cost through YOLO and AdderNet, accelerating the reasoning speed, and ensuring the real-time performance and accuracy of smart community pet identification.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a pet identification method, device, equipment and computer-readable storage medium. Background technique [0002] In recent years, deep neural networks have promoted the rapid development of artificial intelligence, and have achieved great success in areas such as image classification, face recognition, and object detection. The accuracy of these technologies has met the needs of practical applications, but because the existing advanced neural network models require a large number of training images for training to achieve satisfactory performance, and the parameters and calculations of the trained neural network models are very large. Large, high requirements for equipment configuration. [0003] At present, the smart community mainly recognizes cats, dogs and other pets based on smart cameras distributed in various areas of the community. The memory and computing power...

AI Technical Summary

Problems solved by technology

The accuracy of these technologies has met the needs of practical applications, but because the existing advanced neural network models require a large number of training images for training to achieve satisfactory performance, and the parameters and calculations of the trained neural network models are very large. Large, high requirements for equipment configuration

[0003] At present, the smart community mainly recognizes cats, dogs and other pets based on smart cameras distributed in various areas of the community. The memory and computing power of these devices are too low to meet the requirements of existing advanced technologies; There are more than 120 types of pet dogs alone. It is costly and difficult to collect enough pet images as training data. It is difficult to train a neural network model that can meet the needs of smart communities.

Images