Soochow University

Bangjun Wang

Li Zhang

Zhao Zhang

Tingwei Pei

Lei Zhao

Fanzhang Li

Qiang Dai

The invention provides a channel attention (CA)-based Swin-Transformer image denoising method and system. A noisy image is inputted into a trained and optimized denoising network model. A shallow layer feature extraction network in the denoising network model first extracts shallow layer feature information such as noise and channels in the noisy image. The extracted shallow layer feature information is then inputted into a deep layer feature extraction network in the denoising network model to acquire deep layer feature information. Subsequently, the shallow layer feature information and the deep layer feature information are inputted into a reconstruction network of the denoising network model to perform feature fusion, so that a clear image can be obtained, thereby overcoming problems that an image denoising method based on a deep convolutional neural network is prone to a loss of details in an inputted noisy image and high computing memory and time consumption.

Channel attention-based swin-transformer image denoising method and system

A moving object detection method and a moving object detection system are provided. The method includes: predetermining a background image corresponding to a scene monitored by a video monitoring device; performing a subtraction processing on a grayscale image to be detected and the background image to acquire a difference image; and binarizing the difference image and determining a moving object in the grayscale image to be detected, where the determining the background image includes: dividing a first grayscale image frame and a second grayscale image frame in a grayscale image frame sequence captured by the video monitoring device into image blocks to acquire a first image block set and a second image block set respectively, and determining the background image using a difference between the first image block set and the second image block set.

Moving object detection method and system

Growing community of inventors

Suzhou, China

Bangjun Wang