Scene detection method and device, and mobile terminal

Abstract

The invention discloses a scene detection method and device, and a mobile terminal. The method comprises steps that a to-be-detected image is obtained; the image is detected through utilizing a trained first convolutional neural network model to obtain the first detection result, and the first detection result is used for determining whether the image contains a first scene and the position information of the first scene in the image; if the image is determined to contain at least one first scene based on the first detection result, according to the position information of the first scene in the image, the first scene is detected through utilizing a trained second convolutional neural network model to acquire the second detection result, and the second detection result is used for determining whether the first scene contains a second scene and the position information of the second scene in the image; according to the first detection result and the second detection result, the scene detection result information of the image is outputted.

Description

technical field [0001] The present application belongs to the technical field of image processing, and in particular relates to a scene detection method, device, mobile terminal and computer-readable storage medium. Background technique [0002] In the current image processing process, performing scene detection on the image can provide a good basis for the subsequent post-processing of the image, thereby improving the display effect of the image. Existing scene detection methods mainly use large-scale network models of deep learning to detect all scenes in the image. Although large-scale network models can achieve high detection accuracy, they require a large amount of calculation and require high performance of equipment. It is difficult to adopt on devices with relatively limited computing power, such as mobile phones. Contents of the invention [0003] In view of this, the present application provides a method and device for scene detection, a mobile terminal and a co...

AI Technical Summary

Problems solved by technology

Existing scene detection methods mainly use large-scale network models of deep learning to detect all scenes in the image. Although large-scale network models can achieve high detection accuracy, they require a large amount of calculation and require high performance of equipment. Difficult to adopt on devices with relatively limited computing power, such as mobile phones

Images