3D目标检测技术发展综述  

Overview of the Development of 3D Target Detection Technology

作　　者：梁小芳 余华平[1] LIANG Xiao-fang;YU Hua-ping(Yangtze University,Jingzhou 434000,China)

机构地区：[1]长江大学,湖北荆州434000

出　　处：《电脑知识与技术》2021年第1期231-234,共4页Computer Knowledge and Technology

摘　　要：目标检测是计算机视觉领域的一个重要分支,由于2D目标检测技术自身的发展限制和近年来硬件技术的发展与应用,3D目标检测技术逐步取得了较不错的成绩,并为目标检测技术打开了新的应用领域,如AR/VR、自动驾驶、文化遗产保护等。文中从2个方向,4个分支介绍近年来3D检测技术领域的经典架构以及关键性知识,简要分析了各架构特点,并对3D目标检测技术的发展做出总结与展望。Target detection is an important branch in the field of computer vision,Due to the limitations of the development of 2D target detection technology and the development and application of hardware technology in recent years,3D target detection technol⁃ogy has gradually achieved relatively good results and opened up new possibilities for target detection technology.The application areas of the company,such as AR/VR,autonomous driving,cultural heritage protection,etc.The article introduces the classic ar⁃chitecture and key knowledge in the field of 3D detection technology in recent years from 2 directions and 4 branches,briefly ana⁃lyzes the characteristics of each architecture,and summarizes and prospects the development of 3D target detection technology.

关 键 词：目标检测 深度学习 激光雷达点云 图像数据 神经网络 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]