Role of satellite images is increasing in day-to-day life for both civil as well as defence applications. One of the major defence application while troop’s movement is to know about the behaviour of the terrain in advance by which smooth transportation of the troops can be made possible. Therefore, it is important to identify the terrain in advance which is quite possible with the use of satellite images. However, to achieve accurate results, it is essential that the data used should be precise and quite reliable. To achieve this with a satellite image alone is a challenging task. Therefore, in this paper an attempt has been made to fuse the images obtained from drone and satellite, to achieve precise terrain information like bare land, dense vegetation and sparse vegetation. For this purpose, a test area nearby Roorkee, Uttarakhand, India has been selected, and drone and Sentinel-2 data have been taken for the same dates. A neural network based technique has been proposed to obtain precise terrain information from the Sentinel-2 image. A quantitative analysis was carried out to know the terrain information by using change detection. It is observed that the proposed technique has a good potential to identify precisely bare land, dense vegetation, and sparse vegetation which may be quite useful for defence as well as civilian application.
Development of Neural Network Based Adaptive Change Detection Technique for Land Terrain Monitoring with Satellite and Drone Images
