Comparison of Supervised Classification Methods On Remote Sensed Satellite Data: An Application In Chennai, South India
Journal Title: UNKNOWN - Year 2015, Vol 4, Issue 2
Abstract
This paper presents classification of various land cover types from the raw satellite image using supervised classifiers and performance of the classifiers are analyzed. Geo coded and Geo-referenced remote sensed images from Survey of India, Government of India Topographical maps are used. Prior to classification, Training process to assemble a set of statistics describing spectral response pattern of each land cover type is done. The quality of training plays a crucial role in success of classification. Classification is executed based on the spectral features using Minimum distance to mean classifier, Maximum likelihood classifier and Mahalanobis classifier. Efficiency of Classification results are assessed by using accuracy assessment and Confusion matrix. Performance of Maximum likelihood classifier is found to be better than other two. ERDAS IMAGINE 9.2, the world’s leading geospatial data authoring software is used.
Authors and Affiliations
Keywords
Related Articles
- EP ID EP356226
- DOI -
- Views 82
- Downloads 0
Radiographic Pathology Book (Fracture bones and Joints)
Radiographic Pathology Book (Fracture bones and Joints)
Interleaved Voltage Source Converters Based Enhanced Asymmetric Space Vector Modulation for Total Harmonic Distortion Diminution
This paper presents the comparison between improved asymmetric space vector modulation (ASVM) and sinusoidal pulse width modulation (SPWM) for voltage source converters (VSCs) when the switching frequency is as low as 9...
The Adequacy of Instructional Materials and Physical Facilities and their Effects on Quality of Teacher Preparation in Emerging Private Primary Teacher Training Colleges in Bungoma County, Kenya
The research was carried out in eight private teacher training colleges in Western Province in Kenya. The study sample was selected through simple random and purposive sampling techniques. The sample comprised of eight c...
A Successful Treatment of a Child with Clinical Relapse of Visceral Leishmaniasis Complicated with AH1N1
"Abstract: Introduction: Visceral leishmaniasis is associated with poor sanitary conditions in Albania as suggested by clinical relapses and frequency of comorbidities. New lipid formulations are costly and have only b...
Mitigating Hotspot Locating Attack in Wireless Sensor Network
In wireless sensor network monitored objects can be located by using traffic analysis techniques. Whenever sensors are used to monitor sensitive objects, the privacy of monitored objects’ locations becomes an important c...