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。
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.
引文
[1]应申,杨杰,王凯,等.众包模式下室内地图变化发现与更新[J].测绘地理信息,2016,41(2):62-65.(YING S, YANG J, WANG K, et al. Crowdsourcing-based change detection and updating of indoor map[J]. Geomatics of Surveying and Mapping, 2016,41(2):62-65.)
[2]汪永红,张斌,郭黎,等.导航电子地图增量更新方法研究[J].地理信息世界,2011,9(4):40-43.(WANG Y H, ZHANG B, GUO L, et al.Research of incremental updating method for navigation electronic map[J]. Geographic Information World, 2011, 9(4):40-43.)
[3]郭鹏,崔铁军.导航电子地图增量式更新服务模式[J].地理信息世界,2011,9(4):57-61.(GUO P, CUI T J. Incremental updating service mode of navigable electronic maps[J]. Geographic Information World,2011,9(4):57-61.)
[4]李晓斌,李飞,马春红.面向车联网应用的导航电子地图增量更新[J].测绘科学,2016,41(8):161-164.(LI X B, LI F, MA C H. Incremental updating technique of navigation electronic map for telematics[J]. Science of Surveying and Mapping, 2016,41(8):161-164.)
[5]苏旭明,谭建成,陈悦竹,等.支持增量更新的导航电子地图数据模型的研究[J].北京测绘,2016(3):126-128.(SU X M, TAN J C, CHEN Y Z, et al. The research on data model of supportingincremental updating of navigation electronic map[J]. Beijing Surveying and Mapping, 2016(3):126-128.)
[6]张新长,郭泰圣,唐铁.一种自适应的矢量数据增量更新方法研究[J].测绘学报,2012,41(4):613-619.(ZHANG X C, GUO T S, TANG T. An adaptive method for incremental updating of vector data[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(4):613-619.)
[7]张保钢,杨伯钢,张伟松.矢量地理信息更新增量的传播[J].测绘通报,2015(4):53-56.(ZHANG B G, YANG B G, ZHANG W S. Incremental propagation of vector geographic information updating[J]. Bulletin of Surveying and Mapping, 2015(4):53-56.)
[8]LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015IEEE Conference on Computer Vision and Pattern Recognition.Washington, DC:IEEE Computer Society, 2015:3431-3440.
[9]YUAN J, WU Y, YANG M. Discovery of collocation patterns:from visual words to visual phrases[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2007:1-8.
[10]TU S, HUANG Y, LIU G. CSFL:a novel unsupervised convolution neural network approach for visual pattern classification[J]. AI Communications, 2017, 30(5):311-324.
[11]HERRANZ L, JIANG S, LI X. Scene recognition with CNNs:objects, scales and dataset bias[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:571-579.
[12]HE K, ZHANG X, REN S, et al. Delving deep into rectifiers:surpassing human-level performance on Image Net classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1026-1034.
[13]CAGLAYAN A, CAN A B. Volumetric object recognition using3-D CNNs on depth data[J]. IEEE Access, 2018, 6:20058-20066.