Vikas Saxena

Madhu Khurana, Vikas Saxena

With the advent of remote sensing satellites, a huge repository of remotely sensed images is available. Change detection in remotely sensed images has been an active research area as it helps us understand the transitions that are taking place on the Earths surface. This paper discusses the methods and their classifications proposed by various researchers for change detection. Since use of soft computing based techniques are now very popular among research community, this paper also presents a classification based on learning techniques used in soft-computing methods for change detection.

Suma Dawn, Vikas Saxena, Bhu Dev Sharma

Digital Elevation Model (DEM), while providing a bare earth look, is heavily used in many applications including construction modeling, visualization, and GIS. Their registration techniques have not been explored much. Methods like Coarse-to-fine or pyramid making are common in DEM-to-image or DEM-to-map registration. Self-consistency measure is used to detect any change in terrain elevation and hence was used for DEM-to-DEM registration. But these methods apart from being time and complexity intensive, lack in error matrix evaluation. This paper gives a method of registration of DEMs using specified height values as control points by initially converting these DEMs to ASCII files. These control points may be found by two mannerisms - either by direct detection of appropriate height data in ASCII files or by edge matching along congruous quadrangle of the control point, followed by sub-graph matching. Error analysis for the same has also been done.

Manish K Thakur, Vikas Saxena, J P Gupta

In last decade, ever growing internet technologies provided platform to share the multimedia data among different communities. As the ultimate users are human subjects who are concerned about quality of visual information, it is often desired to have good resumed perceptual quality of videos, thus arises the need of quality assessment. This paper presents a full reference hybrid video quality metric which is capable to analyse the video quality for spatially or temporally (frame drop) or spatio-temporally distorted video sequences. Simulated results show that the metric efficiently analyses the quality degradation and more closer to the developed human visual system

Suma Dawn, Vikas Saxena, Bhudev Sharma

Digital Elevation models (DEM) are images having terrain information embedded into them. Using cognitive mapping concepts for DEM registration, has evolved from this basic idea of using the mapping between the space to objects and defining their relationships to form the basic landmarks that need to be marked, stored and manipulated in and about the environment or other candidate environments, namely, in our case, the DEMs. The progressive two-level encapsulation of methods of geo-spatial cognition includes landmark knowledge and layout knowledge and can be useful for DEM registration. Space-based approach, that emphasizes on explicit extent of the environment under consideration, and object-based approach, that emphasizes on the relationships between objects in the local environment being the two paradigms of cognitive mapping can be methodically integrated in this three-architecture for DEM registration. Initially, P-model based segmentation is performed followed by landmark formation for contextual mapping that uses contextual pyramid formation. Apart from landmarks being used for registration key-point finding, Euclidean distance based deformation calculation has been used for transformation and change detection. Landmarks have been categorized to belong to either being flat-plain areas without much variation in the land heights; peaks that can be found when there is gradual increase in height as compared to the flat areas; valleys, marked with gradual decrease in the height seen in DEM; and finally, ripple areas with very shallow crests and nadirs. Fractal based compression was used for storage of co-registered DEMs. This method may further be extended for DEM-topographic map and DEM-to-remote sensed image registration. Experimental results further cement the fact that DEM registration may be effectively done using the proposed method.