计算机应用 ›› 2019, Vol. 39 ›› Issue (1): 78-81.DOI: 10.11772/j.issn.1001-9081.2018071657

• 2018年全国开放式分布与并行计算学术年会(DPCS 2018)论文 • 上一篇    下一篇

分层式三维室内地图分类方法及更新机制

冯光升1, 张晓雪1, 王慧强1, 李冰洋1, 袁泉2, 陈诗军2, 陈大伟2   

  1. 1. 哈尔滨工程大学 计算机与科学技术学院, 哈尔滨 150001;
    2. 中兴通讯股份有限公司, 广东 深圳 518055
  • 收稿日期:2018-07-19 修回日期:2018-08-28 出版日期:2019-01-10 发布日期:2019-01-21
  • 通讯作者: 张晓雪
  • 作者简介:冯光升(1980-),男,山东禹城人,副教授,博士,CCF会员,主要研究方向:网络安全、认知网络;张晓雪(1993-),女,黑龙江哈尔滨人,硕士研究生,主要研究方向:分布式与并行计算、体系结构、神经网络;王慧强(1960-),男,黑龙江哈尔滨人,教授,博士,CCF会员,主要研究方向:网络安全、未来网络;李冰洋(1978-),男,黑龙江哈尔滨人,副教授,博士,主要研究方向:可信计算、网络可靠性;袁泉(1962-),男,江西赣州人,高级工程师,博士,主要研究方向:工业自动化;陈诗军(1972-),男,山东烟台人,高级工程师,硕士,主要研究方向:无线定位、MIMO、信道仿真;陈大伟(1984-),男,黑龙江绥化人,高级工程师,硕士,主要研究方向:无线铁路集群、铁路综合数字移动通信系统(GSM-R)、铁路通用移动通信技术的长期演进(LTE-R)。
  • 基金资助:
    国家科技重大专项(2016ZX03001023-005);中央高校基本科研业务费专项(HEUCF100601);中兴产学研合作项目(2016ZTE01-03-06);中兴通讯产学研合作论坛项目(2018ZTE)。

Classification method and updating mechanism of hierarchical 3D indoor map

FENG Guangsheng1, ZHANG Xiaoxue1, WANG Huiqiang1, LI Bingyang1, YUAN Quan2, CHEN Shijun2, CHEN Dawei2   

  1. 1. College of Computer Science and Technology, Harbin Engineering University, Harbin Heilongjiang 150001, China;
    2. Zhongxing Telecommunication Equipment Corporation, Shenzhen Guangdong 518055, China
  • Received:2018-07-19 Revised:2018-08-28 Online:2019-01-10 Published:2019-01-21
  • Supported by:
    This work is partially supported by the National Science and Technology Major Project (2016ZX03001023-005), the Fundamental Research Funds for the Central Universities (HEUCF100601), the ZTE Industry, University and Research Cooperation Project (2016ZTE01-03-06), the ZTE Industry, University and Research Cooperation Forum Project (2018ZTE).

摘要: 针对现有的地图更新方法,在室内地图环境下的效果并不理想的问题,提出了一种分层式的室内地图更新方法。首先以室内物体的活动性为参数,然后进行层次的划分来减少更新数据的数量,最后利用卷积神经网络(CNN)对室内数据进行归属层次的判定。实验结果表明,与版本式更新方法相比,所提算法的更新时间降低了27个百分点;与增量式更新方法相比,其更新时间在更新项大于100后逐渐降低。与增量式更新方法相比更新包大小降低了6.2个百分点,且在数据项小于200之前其更新包一直小于版本式更新方法。所提方法可以显著提高室内地图的更新效率。

关键词: 室内地图, 地图更新方法, 分层式更新, 卷积神经网络, 增量式更新, 版本式更新

Abstract: For the fact that existing map updating methods are not good at map updating in indoor map environments, a hierarchical indoor map updating method was proposed. Firstly, the activity of indoor objects was taken as a parameter. Then, the division of hierarchy was performed to reduce the amount of updated data. Finally, a Convolutional Neural Network (CNN) was used to determine the attribution level of indoor data in network. The experimental results show that compared with the version update method, the update time of the proposed method is reduced by 27 percentage points, and the update time is gradually reduced compared with the incremental update method after the update item number is greater than 100. Compared with the incremental update method, the update package size of the proposed method is reduced by 6.2 percentage points, and its update package is always smaller than that of the version update method before the data item number is less than 200. Therefore, the proposed method can significantly improve the updating efficiency of indoor maps.

Key words: indoor map, map updating method, hierarchical updating, Convolutional Neural Network (CNN), incremental update, version update

中图分类号: