Noise removal for surveillance camera image by means of AI-based object recognition

A device for processing a camera image, the device comprising:

• an image capture device configured to obtain an image;
• and
• a processor configured to linearly control a noise removal intensity according to an amount of sensor gain amplification in the image in a low-illumination environment, and to dynamically control the noise removal intensity according to a moving speed of an object recognized in the image,
• wherein the processor is configured to set the image as input data, to set object recognition as output data, and to recognize the object by applying a previously trained neural network model.

A method for processing a camera image, the method comprising:

• linearly controlling a first noise removal intensity according to an amount of sensor gain amplification in an image obtained through an image capture device;
• based on an object in the image being recognized, calculating a moving speed of the object;
• and
• dynamically controlling a noise removal intensity between the first noise removal intensity and a second noise removal intensity lower than the first noise removal intensity according to the moving speed.