Change Detection Using Neural Network with Improvement Factor in Satellite Images

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.

Download Full-text

Multitemporal distribution analysis of Dodonaea viscosa (L.) Jacq. by remote sensing in Durango, Mexico

RECUBRIMIENTO COMESTIBLE CON BASE DE PIÑON MEXICANO (Jatropha curcas) SOBRE LA CALIDAD DE CHAYOTE MINIMAMENTE PROCESADO ◽

10.32854/agrop.vi.1685 ◽

2020 ◽

Vol 13 (8) ◽

Author(s):

Marco, A. Márquez-Linares ◽

Jonathan G. Escobar--Flores ◽

Sarahi Sandoval- Espinosa ◽

Gustavo Pérez-Verdín

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Design Methodology ◽

Supervised Classification ◽

Satellite Images ◽

Ground Cover ◽

Distribution Analysis ◽

Dodonaea Viscosa ◽

Artificial Neural ◽

Landsat Satellite

Objective: to determine the distribution of D. viscosa in the vicinity of the Guadalupe Victoria Dam in Durango, Mexico, for the years 1990, 2010 and 2017.Design/Methodology/Approach: Landsat satellite images were processed in order to carry out supervised classifications using an artificial neural network. Images from the years 1990, 2010 and 2017 were used to estimate ground cover of D. viscosa, pastures, crops, shrubs, and oak forest. This data was used to calculate the expansion of D. viscosa in the study area.Results/Study Limitations/Implications: the supervised classification with the artificial neural network was optimal after 400 iterations, obtaining the best overall precision of 84.5 % for 2017. This contrasted with the year 1990, when overall accuracy was low at 45 % due to less training sites (fewer than 100) recorded for each of the land cover classes.Findings/Conclusions: in 1990, D. viscosa was found on only five hectares, while by 2017 it had increased to 147 hectares. If the disturbance caused by overgrazing continues, and based on the distribution of D. viscosa, it is likely that in a few years it will have the ability to invade half the study area, occupying agricultural, forested, and shrub areas

Download Full-text