基于深度学习的计算机视觉创新实验平台设计与实现

Design and Implementation of Computer Vision Innovation Practical Platform Based on Deep Learning

为满足智能制造背景下高校计算机视觉课程实践教学与时俱进的需求,研制了“边-云”互动计算机视觉创新实验平台。该平台包含基于嵌入式GPU的计算机视觉计算装置和云端实践教学管理系统,使得面向深度学习的计算机视觉创新实验可以在实验室规模配置。结合智慧矿山科研成果,在平台上设计了应用于矿石块度分布检测的教学案例,并在自动化、人工智能、计算机科学与技术和机械工程4个本科专业中进行了实践教学。实践表明,该平台有效提升了学生创新思维和解决计算机视觉领域复杂工程问题的能力。

Under the background of intelligent manufacturing,an“Edge-Cloud”interactive computer vision innovation practical platform is developed to meet the needs of practical teaching of computer vision courses in colleges and universities.This platform includes computer vision computing device based on embedded GPU and cloud practical teaching management system,so the computer vision innovation experiment for deep learning can be configured on the scale of the laboratory.Combined with the scientific research achievements of smart mine,a teaching case of ore block size distribution detection is designed on the platform and applied to the practical teaching of four undergraduate majors,automation,artificial intelligence,mechanical,and computer.The application results show that students’ability to innovation,and solving complex engineering problems in the field of computer vision have been improved effectively.