Abstract

Automatic object extraction from urban areas using high resolution satellite images remains an open research area. High variability in object features like color, shape and scale makes the urban scene classification challenging. Though significant amount of work has been done on detecting buildings, roads and other objects individually, not much work is present for complete urban scene classification. This paper proposes an algorithm that makes use of color as an important cue along with geometry and shadow information for complete urban scene classification.

Abstract

We solve instances of a general class of problems de- ned as follows: Preprocess a set S of possibly weighted colored geometric objects (e.g. points/orthogonal seg- ments/rectangles) in Rd, d  1 such that given a query orthogonal range q, we can report eciently for each dis- tinct color c of the points in S \q, the tuple < c;F(c) > where F(c) is a function (e.g. weighted sum, bounding box etc.) of the objects of color c in q.

Abstract

Water bodies, the aquatic systems on land, are one of the important store houses for variety of wildlife as well as nesting and breeding sites for different kind of avifauna. Currently these water bodies are under tremendous human pressure due to rapid urbanization. The lakes and reservoirs, across the country, are in varying degrees of environmental degradation due to various anthropogenic activities. In this context a study was carried out in and around the city, covering an area of about 7800 km2 to identify the impact of expanding urbanization process on water bodies of the Hyderabad city using 1989 and 2001 satellite data. The results of the study showed reduction in water bodies both in the area (19%) as well as in number. A negative change was observed in the status of water bodies towards NE and NW directions of the city. Most of the water bodies either were encroached by urban expansion or reduced in size due to eutrophication process. The expanding IT sector and developments in real estate, acted as major driving forces that converted agricultural lands into residential plots and there by exerting pressure on the nearby water bodies. The change study here provides us with vital clues towards understanding the change in water bodies’ vis-à-vis the urban needs, economic growth, and its location characteristics within a rapidly urbanization region.

Abstract

Forests are depleted drastically at higher rates to cope up the needs of increasing population. The present study was carried out to assess the impact of anthropogenic and natural disturbances (tsunami) on the vegetation of North Andaman islands using three different satellite images of different time period by visual image interpretation technique. A higher proportion of land cover and vegetation converted into agriculture, settlement, sand and water. Assessment of overall forest change from 1976 to 2005 is 117 Km 2 , with forest loss at the rate of 3.8 Km 2 / year. Simulation study for future forest scenario predicted an increase in agriculture / settlement area to be 196, 296, 392 and 492 Km 2 for the next 25, 50, 75 and 100 years, coupled with the conversion of forest areas of 131, 227, 320 and 427 Km 2 . Finally by the end of 100 years the estimated forest area of 1271 Km 2 (1999 data) reduces to 846 Km 2 if proper conservative actions are not taken.

Abstract

The present study outlines an approach to classify forest density and to estimate canopy closure of the forest of the Andaman and Nicobar archipelago. The vector layers generated for the study area using satellite data was validated with the field knowledge of the surveyed ground control points. The methodology adopted in this present analysis is three-tiered. First, the density stratification into five zones using visual

Abstract

A Special Economic Zone (SEZ) is a geographical region that has economic laws more liberal than a country's typical economic laws. In the recent years, India has witnessed a confrontation between farmers and the state, the reason being use of highly productive land for setting up SEZs with some of the cases occupying a centre stage in the World fora (Nandigram violence). In this paper, we propose an integrated solution for identifying nonagricultural lands for setting up SEZs using MODIS NDVI product and remote sensing techniques. The study also identifies multi- cropping practices and reinforces the potential of time-series MODIS data for mapping and land cover classification at regional scales.