Method and device for image scene understanding

Abstract

An embodiment of the present invention provides a method for understanding an image scene, comprising: acquiring an original image of the scene; performing a convolution operation on the original image to obtain a convolution output; and processing the convolution output through a global convolution network , to obtain a processing result; and performing boundary refinement on the processing result to obtain an image scene understanding result. The embodiment of the present invention utilizes the global convolutional network to effectively increase the effective receptive field, and further utilizes boundary refinement to increase the discrimination of the boundary, thereby effectively improving the overall performance of the system.

Description

technical field [0001] The present invention relates to the field of video monitoring, and more particularly relates to a method and device for image scene understanding. Background technique [0002] The concept of deep learning originated from the research of artificial neural networks. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. In computer vision and related fields, emerging deep learning methods have made great progress over traditional methods of the past. Convolutional neural network (CNN) is a machine learning model under deep supervised learning. It is the core operation of deep learning. It performs a convolution operation between the convolution kernel (Kernel) and the original image input to obtain an output. [0003] Scene understanding has important applications in the field of video surveillance. Traditional scene understan...

AI Technical Summary

Problems solved by technology

On the other hand, the traditional method has a large misjudgment of the boundary of the object. For example, a part of the person leaning on the car will be understood as the body. It can be seen that the existing method will lead to a decrease in the overall performance of the system.

Images