Interactive blind guiding system and method based on improved Yolov2 target detection and voice recognition

Abstract

The invention belongs to the technical field of computer vision and voice recognition, and relates to an interactive blind guiding system and method based on improved Yolov2 target detection and voicerecognition. The interactive blind guiding system comprises a central processing unit as well as a depth camera, a high-end voice synthesis device, a microphone and a power supply which are connectedwith the central processing unit, the central processing unit is used for system control, data processing and signal transmission, and control software of the interactive blind guiding system is deployed on the central processing unit and comprises a target detection unit, a voice recognition unit and a road planning unit; the depth camera is used for performing image acquisition on the current scene to generate an RGB image and a depth map; the high-end voice synthesis device is used for synthesizing the voice information output by the central processing unit and playing an object searchingresult or a road planning condition; the microphone is used for collecting user voice information and transmitting the user voice information to the central processing unit; and the power supply is used for supplying power to the central processing unit. The garment can assist the blind in living better, and the living quality of the blind is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision and speech recognition, and relates to an interactive blind guiding system and method based on improved Yolov2 target detection and speech recognition. Background technique [0002] In recent years, with the development of computer science and technology, under the huge impetus of deep learning, a new intelligent technology method, various technologies of artificial intelligence, such as speech recognition technology, image recognition technology, data mining technology, etc., have made substantial progress. Developed and successfully applied in many products. Deep learning is the current focus and hotspot in the field of computer vision research, and it is also one of the commonly used methods to solve complex environmental problems. As a milestone in the history of human science and technology development, computer vision plays a pivotal role in the development of intelligent technology...

AI Technical Summary

Problems solved by technology

[0003] At present, the intelligent blind guide systems that appear on the market are mainly based on infrared ray assistance and guide rods to help blind people travel. They have not realized intelligent interactivity, and their safety is low. They basically rely on the blind people's own judgment to make decisions. The accident rate higher

The recently emerging smart glasses for the blind need to be equipped with human customer service to realize remote interaction, which is difficult to achieve universal promotion and use, and is costly, consumes a lot of resources, and is greatly restricted by the network

[0004] At present, the intelligent system that uses deep learning technology to help blind people find objects is not yet mature. The main reason is that the accuracy and accuracy required to find objects is too large, and portable devices cannot support such a huge computing power.

At present, some low-power target detection networks have achieved similar accuracy and precision to common target detection networks, but the required computing resources have been greatly reduced, which makes it possible to deploy deep neural networks in portable devices.

Images