基于卷积神经网络的嵌入式视觉感知交互系统设计与实现OA

In order to solve the problem that the speech intelligent assistant is unable to provide visual perception of the surrounding environment,a visual perception interaction system is designed and implemented in this paper.The basic structure of the system consists of speech recognition,voice playback,image acquisition,central processing control and other modules,with voice interaction,target detection and other functions.In this system,the special chip for speech recognition is selected,the convolutional neural network technology is used to complete the recognition,and the algorithm based on graph segmentation is used to segment the target.The experimental results show that the system has good performance and can realize visual perception of the surrounding environment and voice interaction.