Image scene understanding method and device

Abstract

The embodiment of the invention provides an image scene understanding method. The method comprises the steps of obtaining an original image of a scene; performing convolution on the original image andobtaining convolution outputs; processing the convolution outputs through fully convolutional networks and obtaining processing results; and performing boundary refining on the processing results andobtaining an image scene understanding result. According to the embodiment, the effective receptive field is greatly increased through the fully convolutional networks and further boundary discrimination is improved through boundary refining, so the overall performance of a system is improved effectively.

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