| 487 | 1 | 229 |
| 下载次数 | 被引频次 | 阅读次数 |
针对路网兴趣点(point of interest,POI)数据传统获取方法人工依赖高、成本高、效率低等问题，基于遥感影像和车辆轨迹数据融合提出了一种典型路网POI自动识别方法。该方法通过卷积神经网络(convolutional neural network,CNN)提取遥感影像中的道路几何特征，并利用循环神经网络(recurrent neural network, RNN)有效捕捉车辆轨迹隐含的道路交通特征，最后通过神经网络，实现从多模态数据中识别路网中红绿灯路口、加油站、停车场等兴趣点。本研究以2019年重庆市中心城区道路兴趣区域的400张遥感影像数据和40 000条出租车轨迹数据作为训练样本进行了实验验证。结果表明，对比单一使用车辆轨迹数据的算法，该算法识别精度提高了近11.83%；对比单一使用遥感影像数据的算法，该算法识别精度提高了近2.53%。
Abstract：In order to overcome the inefficiencies, high costs and manual dependency associated with traditional data acquisition techniques, this study proposes an automatic recognition method for typical road network POIs based on the fusion of remote sensing imagery and vehicle trajectory data. The method utilizes convolutional neural networks(CNN) to extract road geometric features from remote sensing imagery and recurrent neural networks(RNN) to capture the implicit traffic characteristics in vehicle trajectories. Finally, the method enables the accurate identification of POIs such as traffic lights, gas stations, and parking lots from multimodal data sources through neural network. Experimental validation is conducted through 400 remote sensing images and 40 000 taxi trajectory data recorded in 2019from central Chongqing city. The results indicate that, compared to algorithms using only vehicle trajectory data, this method improves identification accuracy by approximately 11. 83%, and that compared to algorithms using only remote sensing imagery data, accuracy improves by approximately 2. 53%.
[1]寇静行，王汉英，王玉琴，等. POI数据研究热点与趋势分析[J].科技资讯，2023,21(3):135-138
[2]张景奇，史文宝，修春亮. POI数据在中国城市研究中的应用[J].地理科学，2021,41(1):140-148
[3]王帅.城市路网变化信息提取及其对土地利用的影响研究[J].测绘学报，2021,50(8):1 136-1 140
[4] He W, Song H, Yao Y, et al. A Multiscale Method for Road Network Extraction from High-Resolution Sar Images Based on Directional Decomposition and Regional Quality Evaluation[J]. Remote Sensing, 2021,13(8):1476
[5] Yin W, Qian M, Wang L, et al. Road Extraction from Satellite Images with Iterative Cross-Task Feature Enhancement[J]. Neurocomputing, 2022,506:300-310
[6] Qin J, Yang W, Wu T, et al. Incremental Road Network Update Method with Trajectory Data and UAV Remote Sensing Imagery[J]. ISPRS International Journal of Geo-Information, 2022, 11(10):502
[7]张云菲，刘佳，徐鹏，等.基于众源轨迹数据的道路交叉口层次化提取方法[J].测绘地理信息，2023,48(5):123-129
[8]李雅丽，向隆刚，张彩丽，等.车辆轨迹与遥感影像多层次融合的道路交叉口识别[J].测绘学报，2021,50(11):1 546-1 557
[9] Furletti B, Cintia P, Renso C, et al. Inferring Human Activities from GPS Tracks[C]. Proceedings of the2nd ACM SIGKDD International Workshop on Urban Computing, Chicago,USA,2013
[10]张慧杰，王蓉，陈斌，等.基于轨迹和兴趣点数据的城市功能区动态识别与时变规律可视分析[J].计算机辅助设计与图形学学报，2018,30(9):1 728-1 740
[11] Kim J, Mahmassani H S. Spatial and Temporal Characterization of Travel Patterns in a Traffic Network Using Vehicle Trajectories[J]. Transportation Research Procedia, 2015,9:164-184
[12]马书红，张俊杰，陈西芳，等.利用出租车时序数据识别城市功能区[J/OL].吉林大学学报（工学版），2023:1-10[2023-10-17]. doi:10.13229/j. cnki. jdxbgxb.20230447
[13] Wang Z, Lu M, Yuan X, et al. Visual Traffic Jam Analysis Based on Trajectory Data[J]. IEEE Transactions on Visualization and Computer Graphics,2013,19:2 159-2 168
[14] Song Q, Jin C, Wang X, et al. Discovering Underpasses from Walking Trajectories[C]. 2015 31st IEEE International Conference on Data Engineering Workshops, IEEE, Seoul,South Kores,2015
[15] Du J, Liu X, Meng C. Road Intersection Extraction Based on Low-Frequency Vehicle Trajectory Data[J].Sustainability, 2023, 15(19):14299
[16] Liang S, Wang J. Advanced Remote Sensing:Terrestrial Information Extraction and Applications[M]. Amsterdam:Academic Press, 2019
[17] Bittner K, Cui S, Reinartz P. Building Extraction from Remote Sensing Data Using Fully Convolutional Networks[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, 42:481-486
[18] Wang W, Yang N, Zhang Y, et al. A Review of Road Extraction from Remote Sensing Images[J]. Journal of Traffic and Transportation Engineering(English Edition),2016,3(3):271-282
[19] Abdollahi A, Pradhan B, Shukla N, et al. Deep Learning Approaches Applied to Remote Sensing Datasets for Road Extraction:A State-of-the-Art Review[J].Remote Sensing, 2020, 12(9):1444
[20]闫志恒，任超，李毅，等.一种改进的融合不同尺度特征的遥感影像道路提取新方法[J].测绘通报，2022(9):58-62
[21] Lian R, Huang L. Deep Window:Sliding Window Based on Deep Learning for Road Extraction from Remote Sensing Images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:1 905-1 916
[22] Alshehhi R, Marpu P R, Woon W L, et al. Simultaneous Extraction of Roads and Buildings in Remote Sensing Imagery with Convolutional Neural Networks[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130:139-149
[23]胡腾云，解鹏飞，温亚楠，等.基于不同深度学习模型提取建筑轮廓的方法研究[J].遥感技术与应用，2023,38(4):892-902
[24]张用川.基于大规模车辆轨迹的导航地理信息提取方法[D].武汉：武汉大学，2019
基本信息:
DOI：10.14188/j.2095-6045.20230808
中图分类号:P237
引用信息:
[1]刘纪平,王勇,龙彩霞等.基于多模态数据融合的典型路网POI自动识别[J].测绘地理信息,2024,49(03):1-7.DOI:10.14188/j.2095-6045.20230808.
基金信息:
国家重点研发计划（2022YFC3005700）