The week's pick
Random Articles
Reseach Article
A Comparative Assessment between Visual Interpretation and Pixel based Approach for Land Use/ Cover Mapping using IRS LISS-III Imagery
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 11 - Number 11 |
| Year of Publication: 2017 |
| Authors: Parmod Kumar, Raj Setia, D. C. Loshali, Brijendra Pateriya |
10.5120/ijais2017451656
|
Parmod Kumar, Raj Setia, D. C. Loshali, Brijendra Pateriya . A Comparative Assessment between Visual Interpretation and Pixel based Approach for Land Use/ Cover Mapping using IRS LISS-III Imagery. International Journal of Applied Information Systems. 11, 11 ( Mar 2017), 63-67. DOI=10.5120/ijais2017451656
Abstract
The information about land use /cover information is required for urban planning, eco-systems research and developing short and long term plans for the sustainable use, conservation and development of natural resources. A number of techniques have been used for extracting land use/cover information from satellite imagery. The most commonly used techniques are visual interpretation and pixel based classification (unsupervised and supervised classification). In this study, we compared visual interpretation, unsupervised and supervised classification techniques to extract the land use/cover information from Resorcesat-2 Linear Imaging Self Scanning Sensor-III (LISS-III) satellite imagery (Indian Remote Sensing (IRS) Satellite with spatial resolution of 23.5 m) on 1:50,000 scale in the Barnala district of Punjab (India). Ground data was collected from field and accuracy assessments of the three classifications were undertaken. Five land use/cover classes (built-up, agriculture land, forest, wastelands and water bodies) were extracted and the results were compared among these. The overall accuracies showed that visual interpretation (83.6%) performed better results than unsupervised and supervised classification techniques. Between both the pixel based classification techniques, supervised classification (75.5%) was better than unsupervised classification (64.3%). The major variations in accuracy assessment were due to agriculture land and forest extracted using all of the three techniques. These results suggest that visual interpretation technique is better for extracting land use/cover but it takes more time than supervised classification which may be used for getting quick information about land use/cover of an area.
References
- Alqurashi, A., F & Kumar, L. (2013). Investigating the use of remote sensing and GIS techniques to detect land use and land cover change: a review. Advances in Remote Sensing, 2, 193-204
- Chowdhury, P. K. Roy and Maithani S (2010). Monitoring growth of built-up areas in indo-gangetic plain using multi-sensor remote sensing data. Journal of Indian Society of Remote Sensing 38 : 291–300
- Deer, J. P. (1995). Digital change detection techniques: Civilian and Military Applications, Information Technology Division, Defence Science and Technology Organization, Australia.
- Coppin, P., Lambin, E., Inge, J. & Muys, B. (2002). Digital change detection methods in natural ecosystem monitoring: Proceedings of the First International Workshop on Analysis of multi-temporal remote sensing images,Vol. 2, University of Trento, Italy, 13-14 September 2001, eds., Baizzone, L., and Smits, P. World Scientific, N.J.
- Foody, G .M. (2002). Status of land cover classification accuracy assessment. Remote Sensing of Environment 80 :185–201
- Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37, 35-46
- Puig, J., Hyman, G., Bolaños, S., 2002. Digital classification vs. VI: a case study in humid tropical forests of The Peruvian Amazon. In: Proceedings of the 29th International Symposium on Remote Sensing of Environment, Bueno Aires, Argentina, Vol. XXIX, pp. 8-12
- Niemeyer, I., & Canty, M. J., (2003), Pixel-Based and Object-Oriented Change Detection Analysis Using High Resolution Imagery. Proceedings of 25th Symposium on Safeguards and Nuclear Material Managment, 13-15 May, Stockholm.
- Oruc, M., Marangoz, A. M., & Buyuksalih, G., (2004), Comparison of pixel-based and object-oriented classification approaches using Landsat-7 ETM spectral bands. Proceedings of ISPRS Conference, 19-23 July, Istanbul
- Whiteside, T and Ahmad, W (2005). A comparison of object-oriented and pixel-based classification methods for mapping land cover in northern Australia. Proceedings of SSC2005 Spatial intelligence, innovation and praxis: The national biennial Conference of the Spatial Sciences Institute, Melbourne: Spatial Sciences Institute. ISBN 0-9581366-2-9
- Wang, Q., Chen, J., Tian, Y. (2008). Remote sensing image interpretation study serving urban planning based on GIS. In: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing, China,Vol. XXXVII, Part B4, pp. 453-456.
- Bahadur, K.C.K. (2009) Improving Landsat and IRS image classification: evaluation of unsupervised and supervised classification through band ratios and DEM in a mountainous landscape in Nepal. Remote Sensing 1, 1257–1272.
Index Terms
Keywords