The paper has focussed on the global landcover for the identification of cropland areas. Population growth and rapid industrialization are somehow disturbing the agricultural lands and eventually the food production needed for human survival. Appropriate agricultural land monitoring requires proper management of land resources. The paper has proposed a method for cropland mapping by semantic segmentation of landcover to identify the cropland boundaries and estimate the cropland areas using machine learning techniques. The process has initially applied various filters to identify the features responsible for detecting the land boundaries through the edge detection process. The images are masked or annotated to produce the ground truth for the label identification of croplands, rivers, buildings, and backgrounds. The selected features are transferred to a machine learning model for the semantic segmentation process. The methodology has applied Random Forest, which has compared to two other techniques, Support Vector Machine and Multilayer perceptron, for the semantic segmentation process. Our dataset is composed of satellite images collected from the QGIS application. The paper has derived the conclusion that Random forest has given the best result for segmenting the image into different regions with 99% training accuracy and 90% test accuracy. The results are cross-validated by computing the Mean IoU and kappa coefficient that shows 93% and 69% score value respectively for Random Forest, found maximum among all. The paper has also calculated the area covered under the different segmented regions. Overall, Random Forest has produced promising results for semantic segmentation of landcover for cropland mapping.
Semantic segmentation of landcover for cropland mapping and area estimation using Machine Learning techniques
Ms. Surabhi Lingwal is working as Assistant Professor in Department of Computer Science and Engineering at Govind Ballabh Pant Institute of Engineering and Technology, Uttarakhand, India. She has a work experience of 7 years. She received her B.Tech and M.Tech Degree in 2011 and 2013 respectively. Her research interest includes Artificial Intelligence, Machine learning and Computer Vision.
Dr. Komal Kumar Bhatia is working as Professor in Department of Computer Engineering at J. C. Bose University of Science and Technology has a work experience of 20 years. He received his B.E., M.Tech. and Ph.D. degrees in Computer Engineering in 2001, 2004 and 2009 respectively. He has guided eight Ph.Ds. and guiding seven Ph.D. scholars. He has also guided more than hundred M.Tech. Dissertations. He has published more than hundred research papers in reputed journals and conferences and his areas of interests are Information Retrieval Systems, Hidden Web and Web Mining. Currently, he is also working as Dean, Faculty of Informatics & Computing and Chairman of Department of Computer Engineering. He is also member of several Professional bodies at National/International level.
Dr. Manjeet Singh presently working as Professor at Department of Computer Applications, J C Bose University of Science and Technology, YMCA Faridabad, India. He has completed his Ph.D in 2008 from M. D. University Rohtak India in the field of Natural Language Processing. Earlier he completed his Master Degree in Technology from G. J. University of Science and Technology, Hisar India. He has 20 years of research and teaching experience and has supervised successfully 06 Ph.D and more than 20 M.Tech theses. His current research interest includes Natural Language Processing, Semantic Web, Information Retrieval, Computer Networks, Ad-Hoc Networks. He has been teaching subjects like Artificial Intelligence, Soft Computing, Machine Learning, Computer Networks, Compiler Design, Discrete Structures etc. He has published 66 article in International/National Journals and Conferences.
Ms. Surabhi Lingwal is working as Assistant Professor in Department of Computer Science and Engineering at Govind Ballabh Pant Institute of Engineering and Technology, Uttarakhand, India. She has a work experience of 7 years. She received her B.Tech and M.Tech Degree in 2011 and 2013 respectively. Her research interest includes Artificial Intelligence, Machine learning and Computer Vision.
Dr. Komal Kumar Bhatia is working as Professor in Department of Computer Engineering at J. C. Bose University of Science and Technology has a work experience of 20 years. He received his B.E., M.Tech. and Ph.D. degrees in Computer Engineering in 2001, 2004 and 2009 respectively. He has guided eight Ph.Ds. and guiding seven Ph.D. scholars. He has also guided more than hundred M.Tech. Dissertations. He has published more than hundred research papers in reputed journals and conferences and his areas of interests are Information Retrieval Systems, Hidden Web and Web Mining. Currently, he is also working as Dean, Faculty of Informatics & Computing and Chairman of Department of Computer Engineering. He is also member of several Professional bodies at National/International level.
Dr. Manjeet Singh presently working as Professor at Department of Computer Applications, J C Bose University of Science and Technology, YMCA Faridabad, India. He has completed his Ph.D in 2008 from M. D. University Rohtak India in the field of Natural Language Processing. Earlier he completed his Master Degree in Technology from G. J. University of Science and Technology, Hisar India. He has 20 years of research and teaching experience and has supervised successfully 06 Ph.D and more than 20 M.Tech theses. His current research interest includes Natural Language Processing, Semantic Web, Information Retrieval, Computer Networks, Ad-Hoc Networks. He has been teaching subjects like Artificial Intelligence, Soft Computing, Machine Learning, Computer Networks, Compiler Design, Discrete Structures etc. He has published 66 article in International/National Journals and Conferences.
Surabhi Lmgwal, Komal Kumar Bhatia, Manjeet Singh; Semantic segmentation of landcover for cropland mapping and area estimation using Machine Learning techniques. Data Intelligence 2022; doi: https://doi.org/10.1162/dint_a_00145
Download citation file:
Advertisement