Development of a Low-Cost Terrestrial Mobile Mapping System for Urban Vegetation Detection Using Convolutional Neural Networks

Kauê de Moraes Vestena, Daniel Rodrigues dos Santos


Urbanization brought a lot of pollution-related issues that are mitigable by the presence of urban vegetation. Therefore, it is necessary to map vegetation in urban areas, to assist the planning and implementation of public policies. As a technology presented in the last decades, the so-called Terrestrial Mobile Mapping Systems - TMMS, are capable of providing cost and time effective data acquisition, they are composed primarily by a Navigation System and an Imaging System, both mounted on a rigid platform, attachable to the top of
a ground vehicle. In this context, it is proposed the creation of a low-cost TMMS, which has the feature of imaging in the near-infrared (NIR) where the vegetation is highly discriminable. After the image acquisition step, it becomes necessary for the semantic segmentation of vegetation and non-vegetation. The current state of the art algorithms in semantic segmentation scope are the Convolutional Neural Networks - CNNs. In this study, CNNs were trained and tested, reaching a mean value of 83% for the Intersection Over Union (IoU) indicator. From the results obtained, which demonstrated good performance for the trained neural network, it is possible to conclude
that the developed TMMS is suitable to capture data regarding urban vegetation.


Mobile geospatial data acquisition systems; NIR Imaging; Semantic segmentation

Full Text:



Badrinarayanan, V., Kendall, A. & Cipolla, R. 2017, ‘Segnet: A deep convolutional encoder-decoder architecture for image segmentation’, IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 12, pp. 2481-95.

Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K. & Yuille, A.L. 2018, ‘Deep Lab: Semantic image segmentation with deep convolutional nets and fully connected CRFS’, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834-48.

El-Sheimy, N. 2005, ‘An overview of mobile mapping systems’, Proceedings of the FIG Working Week, pp. 16-21.

Fawcett, T. 2006, ‘An introduction to ROC analysis’, Pattern recognition letters, vol. 27, no. 8, pp. 861-74.

Kannojia, S.P. & Jaiswal, G. 2018, ‘Effects of varying resolution on performance of CNN based image classification: An experimental study’, International Journal of Computer Sciences and Engineering, vol. 6, no. 9, pp. 451-6.

Mikołajczyk, A. & Grochowski, M. 2018, ‘Data augmentation for improving deep learning in image classification problem’, 2018 International Interdisciplinary PhD workshop (IIPhDW), pp. 117-22, IEEE.

Mostajabi, M., Yadollahpour, P. & Shakhnarovich, G. 2015, ‘Feedforward semantic segmentation with zoom-out features’, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3376-85.

Myneni, R.B., Hall, F.G., Sellers, P.J. & Marshak, A.L. 1995, ‘The interpretation of spectral vegetation indexes’, IEEE Transactions on Geoscience and Remote Sensing, vol. 33, no. 2, pp. 481-6.

Nicodemo, M.L.F. & Primavesi, O. 2009, ‘Por que manter árvores na área urbana?’, Embrapa Pecuária Sudeste-Documentos (INFOTECA-E).

Pohlen, T., Hermans, A., Mathias, M. & Leibe, B. 2017, ‘Full-resolution residual networks for semantic segmentation in street scenes’, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4151-60.

Sabottke, C.F. & Spieler, B.M. 2020, ‘The effect of image resolution on deep learning in radiography’, Radiology: Artificial Intelligence, vol. 2, no. 1, pp. e190015.



Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Indexers and Bibliographic DatabasesFollow us
SCImago Journal & Country Rank
Google Scholar
All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution-NonCommercial 4.0 International Public License (CC BY-NC 4.0).