Visual assistance method and equipment based on individualized HRTF stereophonic sound

Abstract

The invention provides a visual assistance method based on individualized HRTF stereophonic sound. An inertia measurement unit, a depth camera and a color camera are used for acquiring environmental data. A small computer is used for processing the data to obtain the type, direction and distance of the identified object, and finally an audio describing the type of the object is processed into a spatial sound effect by using the individualized HRTF. The method and equipment can be used for head-mounted games and can also be used for visual assistance of direction guidance for visually impairedpeople. Compared with existing visual assistance equipment, the visual assistance equipment provided by the invention is high in environmental applicability, good in portability, good in object position tracking continuity and high in space sound effect accuracy. Compared with complex voice orientation description, the method and equipment have the advantages that a short single-track voice signaldescribing the object type is directly converted into a stereophonic sound signal with the sense of space; a visual sound source position is generated in the hearing of a user; and the user does notneed to learn complex voice position description rules and is easy to understand.

Description

technical field [0001] The invention relates to a three-dimensional environment perception technology and a spatial sound effect technology, in particular to a visual aid technology of a head-related transfer function HRTF volume sound. Background technique [0002] The visual aid equipment of the binocular camera mainly uses binocular vision technology to image the environment using visible light or infrared bands. Binocular vision technology depends on the complexity of the texture in the environment. For simple scenes, or when the scene has water or mirror interference, it will fail. The principle of binocular vision technology requires that there is a minimum distance limit when dual cameras are installed on the device, and the computing power required for recognition at a high refresh rate is high for the power supply, heat dissipation and battery capacity of existing portable visual aids. It is beneficial to the waterproof sealing and miniaturization and lightweight d...

AI Technical Summary

Problems solved by technology

[0004] Visual aids that use voice prompts to interact with users usually broadcast the orientation, distance, and type of objects, which takes a lot of time and transmits a small amount of information. The content of the broadcast cannot be corrected in time with the user's movement, causing delays and accidents. risk

However, the interactive mode of broadcasting with different timbres and volumes is not intuitive enough, users need to learn and adapt, and the direction of expression is limited

Images