Land Cover Change Detection using M-Siamese Network
G. Charan Dinesh1, MD. Razzaq2, A. Raghavendra Rao3, K. Srinivas4

1G.Charan Dinesh, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
2MD.Razzaq, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
3A.Raghavendra Rao, Department of CSE, VR Siddhartha Engineering college, Vijayawada, India.
4K.srinivas, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.

Manuscript received on May 02, 2020. | Revised Manuscript received on May 21, 2020. | Manuscript published on May 30, 2020. | PP: 2800-2803 | Volume-9 Issue-1, May 2020. | Retrieval Number: A3031059120/2020©BEIESP | DOI: 10.35940/ijrte.A3031.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Land cover change detection has been a topic of active research in the remote sensing community. Due to enormous amount of data available from satellites. The land cover change detection has often been performed by comparing two or more satellite snapshot images acquired on different time period. The image comparison techniques have a number of limitations. The traditional Convolution Neural Network (CNN) method has several problems, such as the weak generalization ability of the model and the difficulty of automating the construction of a training database. These methods generally have high land mapping accuracy but they are time-consuming, laborious, poor repeatability. When compared to the previous models such as U net, we will get more accuracy and also time consumption is minimum, by using this proposed approach. In this paper we will be Siamese so it is named as M-Siamese. To overcome the problem, we had used Siamese network in M-Siamese. The Siamese network is improved Accuracy and Enhanced Flexibility. In this paper we are using M-Siamese network which is effective than the previous Siamese networks. By using this type we will acquire more accuracy than that of previous networks. Finally, we had concluded the change of land cover in percentage.
Keywords: Land Cover Change detection; Convolution Neural Network (CNN); M-Siamese; U net.
Scope of the Article: Convolution Neural Network