Method, device, terminal and storage medium for realizing soft photosensitive based on deep learning

Abstract

The present application is applicable to the field of computer vision technology, and provides a method, device, terminal and storage medium for realizing soft light sensitivity based on deep learning. The method for realizing soft light sensitivity based on deep learning includes: acquiring the current work of the image acquisition device The target day and night prediction model corresponding to the mode; based on the N frames of images continuously collected by the image acquisition device in the current working mode, obtain the target input information corresponding to the target day and night prediction model, where N is an integer greater than zero; The target input information is input into the target day and night prediction model, and the current environment of the image acquisition device is obtained; if the current environment does not match the current working mode, the image acquisition device is controlled to switch to and The working mode that matches the current environment. The above solution can reduce hardware cost and labor cost, and improve the switching precision of the working mode of the image capturing device.

Description

technical field [0001] The present application belongs to the technical field of computer vision, and in particular, relates to a method, device, terminal and storage medium for implementing soft photosensitive based on deep learning. Background technique [0002] With the increasingly widespread application of video surveillance, 24-hour uninterrupted monitoring has become a basic requirement for image acquisition devices (such as cameras). When the application environment of the image acquisition device is daytime, the image acquisition device can use visible light to shoot and then Acquire video images, but when the application environment of the image acquisition device is at night, there is no visible light and the environment is dark, and the image acquisition device cannot directly capture the surrounding video images. In this case, infrared lamps are usually used to emit infrared rays to illuminate the surrounding environment. So that the picture formed by infrared r...

AI Technical Summary

Problems solved by technology

[0003] The above-mentioned control of filter switching through photoresistors is usually called a hard photosensitive solution because a photoresistor is added to the camera. This method has high hardware and labor costs, and is prone to factors such as the installation position of the photoresistor and device aging , reducing the switching accuracy of the working mode of the image acquisition device

Images