One of the principal difficulties related to road safety management in Brazil is the lack of data on road projects, especially those on rural roads, which makes it difficult to use road safety studies and models from other countries as a reference. Updating road networks through the use of hyperspectral remote sensing images can be a good alternative. However, accurately recognizing and extracting hyperspectral images from roads has been recognized as a challenging task in the processing of hyperspectral data. In order to solve the aforementioned challenges, Hyperion hyperspectral images were combined with the Optimum Forest Path (OPF) algorithm for supervised classification of rural roads and the effectiveness of the OPF and SVM classifiers when applied to these areas was compared. Both classifiers produced reasonable results, however, the OPF algorithm outperformed SVM. The higher classification accuracy obtained by the OPF was mainly attributed to the ability to better distinguish between regions of exposed soil and unpaved roads.
References
[1]
Organizacao Pan-Americana da Saúde (2016).
[2]
American Association of State Highway and Transportation Officials (2010) A Policy on Geometric Design of Highways and Streets. 5th Edition, AASHTO, Washington, D. C.
[3]
Boffo, G.H. (2011) Formatos e técnicas de modelos de previsao de acidentes de transito. Dissertacao de Mestrado.
Salbego, A.G., Giotto, E. and Madruga, P.R.A. (2006) Geoprocessamento aplicado ao diagnóstico e espacializacao da infra-estrutura viária rural. Ambiência, 2, 179-195.
[6]
Long, H. and Zhao, Z. (2005) Urban Road Extraction from High-Resolution Optical Satellite Images. International Journal of Remote Sensing, 26, 4907-4921.
https://doi.org/10.1080/01431160500258966
[7]
Hormese, J. and Saravanan, C. (2016) Automated Road Extraction from High Resolution Satellite Images. Procedia Technologies, 24, 1460-1467.
https://doi.org/10.1016/j.protcy.2016.05.180
[8]
Li, Y. and Briggs, R. (2009) Automatic Extraction of Roads from High Resolution Aerial and Satellite Images with Heavy Noise. International Journal of Computer and Information Engineering, 3, 1571-1577.
[9]
Xia, W., Zhang, Y., Liu, J., Luo, L. and Yang, K. (2018) Road Extraction from High Resolution Image with Deep Convolution Network—A Case Study of GF-2 Image. Proceedings of the 2nd International Electronic Conference on Remote Sensing, 2, 325. https://doi.org/10.3390/ecrs-2-05138
[10]
Kahraman, I., Karas, I.R. and Akay, A.E. (2018) Road Extraction Techniques from Remote Sensing Images: A Review. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018 International Conference on Geomatics and Geospatial Technology, Kuala Lumpur, Malaysia, 3-5 September 2018, 339-342.
https://doi.org/10.5194/isprs-archives-XLII-4-W9-339-2018
[11]
Wang, W., Yang, N., Zhang, Y., Wang, F., Cao, T. and Eklund, P. (2016) A Review of Road Extraction from Remote Sensing Images. Journal of Traffic and Transportation Engineering, 3, 271-282. https://doi.org/10.1016/j.jtte.2016.05.005
[12]
Shackelford, A. and Davis, C. (2003) Fully Automated Road Network Extraction from High-Resolution Satellite Multispectral Imagery. International Geoscience and Remote Sensing, 1, 461-463. https://doi.org/10.1109/IGARSS.2003.1293809
[13]
Hu, X., Tao, C. and Hu, Y. (2004) Automatic Road Extraction from Dense Urban Area by Integrated Processing of High Imagery and LIDAR Data, Processing of High Resolution Imagery and LIDAR Data. Remote Sensing and Spatial Information Sciences, 35, 288-292.
[14]
Saito, S., Yamashita, T. and Aoki, Y. (2016) Multiple Object Extraction from Aerial Imagery with Convolutional Neural Networks. Journal of Imaging Science Technology, 60, 10402-10402.
https://doi.org/10.2352/J.ImagingSci.Technol.2016.60.1.010402
[15]
Liu, J., Qin, Q., Li, J. and Li, Y.P. (2017) Rural Road Extraction from High-Resolution Remote Sensing Images Based on Geometric Feature Inference. ISPRS International Journal of Geo-Information, 6, 314. https://doi.org/10.3390/ijgi6100314
[16]
Petropoulos, G.P., Arvanitis, K.G., Sigrimis, N.A., Piromalis, D.D. and Boglou, A.K. (2012) Land Use Cartography from Hyperion Hypespectral Imagery Analysis: Results from a Mediterranean Site. 24th International Conference on Tools with Artificial Intelligence, Athens, Greece, 7-9 November 2012, 26-31.
https://doi.org/10.1109/ICTAI.2012.184
[17]
Papa, J.P., Falcao, A.X. and Suzuki, C.T.N. (2009) Supervised Pattern Classification Based Optimum-Path Forest. International Journal of Imaging Systems and Technology, 19, 120-131. https://doi.org/10.1002/ima.20188
[18]
Papa, J.P., Nachif Fernandes, S.E. and Falcao, A.X. (2017) Optimum-Path Forest based on k-Connectivity: Theory and Applications. Pattern Recognition Letters, 87, 117-126. https://doi.org/10.1016/j.patrec.2016.07.026
[19]
Amorim, W.A., Falcao, A.X. and Papa, J.P. (2018) Multi-Label Semi-Supervised Classification through Optimum-Path Forest. Information Sciences, 465, 86-104.
https://doi.org/10.1016/j.ins.2018.06.067
[20]
Melgani, F. and Bruzzone, L. (2004) Classification of Hyperspectral Remote Sensing Images with Support Vector Machine. IEEE Transactions on Geoscience & Remote Sensing, 42, 1778-1790. https://doi.org/10.1109/TGRS.2004.831865
[21]
Kruse, F.A., Lefkoff, A.B., Boardam, J.W., Heidebrecht, K.B., Shapiro, A.T., Barloon, J.P. and Goetz, A.F.H. (1993) The Spectral Image Processing System (SIPS)—Interactive Visualization and Analysis of Imaging Spectrometer Data. Remote Sensing of Environment, 44, 145-165. https://doi.org/10.1016/0034-4257(93)90013-N
[22]
Li, S., Wu, H., Wan, D. and Zhu, J. (2011) An Effective Feature Selection Method for Hyperspectral Image Classification Based on Genetic Algorithm and Support Vector Machine. Knowledge-Based Systems, 24, 140-148.
https://doi.org/10.1016/j.knosys.2010.07.003
[23]
Taherzadeh, E. and Shafri, H.Z.M. (2011) Using Hyperspectral Remote Sensing Data in Urban Mapping over Kuala Lumpur. 2011 Joint Urban Remote Sensing Event, Munich, Germany, 11-13 April 2011, 405-408.
https://doi.org/10.1109/JURSE.2011.5764805
[24]
Tong, X., Xie, H. and Weng, Q. (2014) Urban Land Cover Classification with Airborne Hyperspectral Data: What Features to Use? IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7, 3998-4009.
https://doi.org/10.1109/JSTARS.2013.2272212
[25]
Eslami, M. and Mohammadzadeh, A. (2016) Developing a Spectral-Based Strategy for Urban Object Detection from Airborne Hyperspectral TIR and Visible Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9, 1808-1816. https://doi.org/10.1109/JSTARS.2015.2489838
[26]
Weismiller, R.A., Van Scoyoc, G.E., Pazar, S.E., Latz, K. and Baumgardner, M.F. (1985) Use of Soil Spectral Properties for Monitoring Soil Erosion. Soil Erosion and Conservation. Soil and Water Conservation Society of America.
[27]
Wang, Y.Y. and Li, J. (2008) Feature-Selection Ability of the Decision-Tree Algorithm and the Impact of Feature-Selection/Extraction on Decision-Tree Results Based on Hyperspectral Data. International Journal of Remote Sensing, 29, 2993-3010.
https://doi.org/10.1080/01431160701442070
[28]
Herold, M., Roberts, D.A., Gardner, E.M. and Dennison, P.E. (2004) Spectrometry for Urban Area Remote Sensing—Development and Analysis of a Spectral Library from 350 to 2400 nm. Remote Sensing of Environment, 91, 304-319.
https://doi.org/10.1016/j.rse.2004.02.013
[29]
Chen, Y., Jiang, H., Li, C., Jia, X. and Ghamisi, P. (2016) Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks. IEEE Transactions on Geosciences and Remote Sensing, 54, 6232-6251.
https://doi.org/10.1109/TGRS.2016.2584107
[30]
Yuan, Y., Lin, J. and Wang, Q. (2016) Hyperspectral Image Classification via Multi-Task Joint Sparse Representation and Stepwise MRF Optimization. IEEE Transactions on Cybernetics, 46, 2966-2977. https://doi.org/10.1109/TCYB.2015.2484324
[31]
Souza, R., Lotufo, R. and Rittner. L. (2012) A Comparison between Optimum-Path Forest and k-Nearest Neighbors Classifiers. 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, Brazil, 22-25 August 2012, 260-267.
https://doi.org/10.1109/SIBGRAPI.2012.43
[32]
Freitas, G.M., ávila, A.M.H., Papa, J.P. and Falcao, A.X. (2009) Optimum-Path Forest Based Rainfall Estimation. 16th International Conference on Systems, Signals and Image Processing, Chalkida, Greece, 18-20 June 2009, 1-4.
https://doi.org/10.1109/IWSSIP.2009.5367753
[33]
Pisani, R., Riedel, P., Costa, K., Nakamura, R., Pereira, C., Rosa, G. and Papa, J.P. (2012) Automatic Landslide Recognition through Optimum-Path Forest. 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany, 22-27 July 2012, 6228-6231. https://doi.org/10.1109/IGARSS.2012.6352681
[34]
Jia, S., Hu, J., Xie, Y., Shen, L., Jia, X. and Li, Q. (2016) Gabor Cube Selection Based Multitask Joint Sparse Representation for Hyperspectral Image Classification. IEEE Transactions on Geosciences and Remote Sensing, 54, 3174-3187.
https://doi.org/10.1109/TGRS.2015.2513082
[35]
Benediktsson, J., Palmason, J. and Sveinsson, J. (2005) Classification of Hyperspectral Data from Urban Areas Based on Extended Morphological Profiles. IEEE Transactions on Geosciences and Remote Sensing, 43, 480-490.
https://doi.org/10.1109/TGRS.2004.842478
[36]
Tarbalka, Y., Fauvel, M., Chanussot, J. and Benediktsson, J.A. (2010) SVM and MRF-Based Method for Accurate Classification of Hyperspectral Images. IEEE Geosciences and Remote Sensing Letters, 7, 736-740.
https://doi.org/10.1109/LGRS.2010.2047711
[37]
Santos, A., Araujo, A. and Menotti, D. (2013) Combining Multiple Classification Methods for Hyperspectral Data Interpretation. IEEE Journal of Selected Topics in Applied Earth Obsavations and Remote Sensing, 6, 1450-1459.
https://doi.org/10.1109/JSTARS.2013.2251969
[38]
Qi, C., Zhou, Z., Sun, Y., Song, H., Hu, L. and Wang, Q. (2017) Feature Selection and Multiple Kernel Boosting Framework Based on PSO with Mutation Mechanism for Hyperspectral Classification. Neurocomputing, 220, 181-190.
https://doi.org/10.1016/j.neucom.2016.05.103
[39]
Zg, E., Zhang, X., Jiao, L., Li, L. and Hou, B. (2016) Spectral-Spatial Hyperspectral Image Ensemble Classification via Joint Sparse Representation. Pattern Recognition, 59, 42-54. https://doi.org/10.1016/j.patcog.2016.01.033
[40]
Ding, C., Li, Y., Xia, Y., Wei, W., Zhang, L. and Zhang, Y. (2017) Convolutional Neural Networks Based Hyperspectral Image Classification Method with Adaptive Kernels. Remote Sensing, 9, 618. https://doi.org/10.3390/rs9060618
[41]
Wu, H. and Prasad, S. (2017) Convolutional Recurrent Neural Networks for Hyperspectral Data Classification. Remote Sensing, 9, 298.
https://doi.org/10.3390/rs9030298
[42]
Li, W., Wu, G., Zhang, F. and Du, Q. (2017) Hyperspectral Image Classification Using Deep Pixel-Pair Features. IEEE Transactions on Geosciences and Remote Sensing, 55, 844-853. https://doi.org/10.1109/TGRS.2016.2616355
[43]
Macedo, M.R.O.B.C., Times, V.C., Cavalcanti, G.D.C. and Kohlman Rabbani, E.R. (2015) An Architecture to Classify Desertification Areas Using Hyperspectral Images and the Optimum Path Forest Algorithm. Electronic Journal of Geotechnical Engineering, 20, 1881-1895.
[44]
Gao, F., Wang, Q., Dong, J. and Xu, Q. (2018) Spectral and Spatial Classification of Hyperspectral Images Based on Random Multi-Graphs. Remote Sensing, 10, 1271.
https://doi.org/10.3390/rs10081271
[45]
Sujatha, C. and Selvathi, D. (2015) Connected Component-Based Technique for Automatic Extraction of Road Centerline in High Resolution Satellite Images. Image and Video Processing, 2015, Article No. 8.
https://doi.org/10.1186/s13640-015-0062-9
[46]
Shi, W., Miao, Z., Wang, Q. and Zhang, H. (2014) Spectral-Spatial Classification and Shape Features for Urban Road Centerline Extraction. IEEE Geoscience and Remote Sensing Letters, 11, 788-792. https://doi.org/10.1109/LGRS.2013.2279034
[47]
Li, M., Stein, A., Bijker, W. and Zhan, Q. (2016) Region-Based Urban Road Extraction from VHR Satellite Images Using Binary Partition Tree. International Journal of Applied Earth Observation and Geoinformation, 44, 217-225.
https://doi.org/10.1016/j.jag.2015.09.005
[48]
Kamangir, H., Momeni, M. and Satari, M. (2017) Automatic Centerline Extraction of Covered Roads by Surrounding Objects from High Resolution Satellite Images. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W4, 111-116.
https://doi.org/10.5194/isprs-archives-XLII-4-W4-111-2017
[49]
Abdollahi, A., Bakhtiari, H.R.R. and Nejad, M.P. (2017) Investigation of SVM and Level Set Interactive Methods for Road Extraction from Google Earth Images. Journal of the Indian Society of Remote Sensing, 46, 423-430.
[50]
Abdollahi A., Biswajeet, P. and Nagesh, S. (2019) Extraction of Road Features from UAV Images Using a Novel Level Set Segmentation Approach. International Journal of Urban Sciences, 23, 391-405. https://doi.org/10.1080/12265934.2019.1596040
[51]
Alpaydin, E. (2010) Introduction to Machine, Massachusetts—USA. The Massachusetts Institute of Technology Press, Cambridge, MA.
[52]
Fernandes, S.E.N. and Papa, J.P. (2019) Improving Optimum-Path Forest Learning using Bag-of-Classifiers and Confidence Measures. Pattern Analysis and Applications, 22, 703-716. https://doi.org/10.1007/s10044-017-0677-9
[53]
Fernandes, S.E.N., Pereira, C.R., Ramos, C.C.O., Souza, A.N., Gastaldello, D.S. and Papa, J.P. (2019) A Probabilistic Optimum-Path Forest Classifier for Non-Technical Losses Detection. IEEE Transactions on Smart Grid, 10, 3226-3235.
https://doi.org/10.1109/TSG.2018.2821765
[54]
Papa, J.P., Falcao, A.X., de Albuquerque, V.H.C. and Tavares, J.M.R. (2012) Efficient Supervised Optimum-Path Forest Classification for Large Datasets. Pattern Recognition, 45, 512-520. https://doi.org/10.1016/j.patcog.2011.07.013
[55]
Barros, W.K., Kohlman Rabbani, E.R., Santana, C.V., Oliveira, D.M.G. and Macedo, M.R.O.B.C. (2015) Seguranca Viária: Estudo Piloto na BR-101 no Estado de Pernambuco. XI CNEG—Congresso Nacional de Excelência em Gestao, 1.
[56]
da Costa, T.C.C., de Oliveira, M.A.J., Accioly, L.J. de O. and da Silva, F.H.B.B. (2009) Análise da degradacao da caatinga no núcleo de desertificacao do Seridó (RN/PB). Revista Brasileira de Engenharia Agrícola e Ambiental, 13, 961-974.
https://doi.org/10.1590/S1415-43662009000700020
[57]
Rocha, L.M., Cappabianco, F.A.M. and Falcao, A.X. (2009) Data Clustering as an Optimum-Path Forest Problem with Applications in Image Analysis. International Journal of Imaging Systems and Technology, 19, 50-68.
https://doi.org/10.1002/ima.20191
[58]
Hudson, W.D. and Ramm, C.W. (1987) Correct Formulation of the Kappa Coefficient of Agreement. Photogrammetric Engineering & Remote Sensing, 53, 421-422.
[59]
Figueiredo, S.M. de M., Cavalcante, L.M., Valentim, J.F. and Figueiredo, E.O. (2009) Avaliacao da acurácia de classificacao digital de imagens no mapeamento de áreas de pastagens degradadas em Rio Branco, Acre. Anais XIV Simpósio Brasileiro de Sensoriamento Remoto, 5789-5796.
[60]
Thenkabail, P., Gamage, M. and Smakhtin, V. (2004) The Use of Remote Sensing Data for Drought Assessment and Monitoring in Southwest Asia. Research Report.
