Real-time man-machine interaction system in virtual scene

Abstract

The invention discloses a real-time man-machine interaction system in a virtual scene. The system comprises a visual attention area prediction module used for mutation detection and a behavior prediction module based on visual attention area characteristics. Wherein the visual attention area prediction module receives an input video frame sequence, carries out target information detection, smoothmotion detection and mutation information detection in sequence to obtain a visual saliency map, and carries out visual attention area extraction on the visual saliency map to obtain an attention areamap; and the behavior prediction module is used for predicting user behaviors by utilizing the characteristics after carrying out characteristics on the user visual area and the video content. According to the invention, the feedback behavior of the user after observing the video is predicted by inputting the video content observed by the user, so that the method can better operate and can cope with a smoothly changing scene in the presence of sudden changes in the scene.

Description

technical field [0001] The present invention relates to a technology in the field of human-computer interaction, in particular to a real-time human-computer interaction system in a virtual scene. Background technique [0002] At present, many user behavior prediction algorithms have been proposed in the field of human-computer interaction, but these algorithms are mostly based on the simple repetition of the user's previous operations, ignoring the impact of the scene content observed by the user on user behavior. And the research on the user's visual attention used to detect the user's attention to the scene content is mostly aimed at smooth changes in the scene, which leads to errors in these visual attention models when the scene content suddenly changes. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes a behavior prediction interaction system based on user visual content. By inputting the vid...

AI Technical Summary

Problems solved by technology

[0002] At present, many user behavior prediction algorithms have been proposed in the field of human-computer interaction, but these algorithms are mostly based on the simple repetition of the user's previous operations, ignoring the impact of the scene content observed by the user on user behavior

And the research on the user's visual attention used to detect the user's attention to the scene content is mostly aimed at smooth changes in the scene, which leads to errors in these visual attention models in the case of sudden changes in the scene content.

Images