面向户外增强现实的地理实体目标检测  

Geographic Object Detection for Outdoor Augmented Reality

作　　者：乔延军[1] 饶锦蒙 王骏星[1] 杜清运[1] 任福[1] 

机构地区：[1]武汉大学资源与环境科学学院,湖北武汉430079

出　　处：《地理信息世界》2017年第5期51-55,85,共6页Geomatics World

基　　金：国家自然科学基金项目(41371427);国家重点研发计划资助项目(2016YFC0803106)资助

摘　　要：本文研究了多种计算机视觉领域中用于图像分类和目标检测的卷积神经网络模型,在一种目标检测模型的基础上进行了修改,并结合了残差神经网络结构,旨在解决户外增强现实中地理实体目标检测的问题。我们根据这一模型开发了一款户外增强现实原型系统,通过将训练好的模型作为目标检测引擎,达到了较好的近实时性和准确性。This paper studies the convolutional neural network model for image classification and object detection in the field of computer vision, and modifies an object detection model which combines Res Net structures to solve the problem of geographic object detection in outdoor augmented reality. An outdoor augmented reality system is developed with the use of the proposed model trained as an object detection engine, which achieves the near-real-time performance and high accuracy.

关 键 词：目标检测 增强现实 卷积神经网络 计算机视觉 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]