GROUND IMAGE EXPLOITATION SYSTEM
established an advanced research facility for exploitation of aerial
imagery. Military and intelligence analysts can view live video imagery from
UAVs. Powerful tools are also available for further exploitation of the
UAVs have promising applications in weather research,
communications, disaster management, pollution monitoring, and law enforcement.
Extraction and exploitation of imagery intelligence from aerial surveillance and reconnaissance platforms enhance understanding and interpretation of scene contents, allow military units to see distant targets, enhance surveillance capabilities and develop cutting edge technologies in the areas of image exploitation.
DRDO has developed and successfully commissioned a Ground Image Exploitation System (GIES) with state-of-the-art hardware and image exploitation software to acquire, store, retrieve, process, analyse, interpret, display and disseminate information from imagery during a UAV mission. Aided by intelligent software tools, GIES software can perform major tasks like target acquisition, calculation of geo-reinforced target location, distance and area computation, real-time enhancement of low contrast imagery, image-to-map registration and firing correction. The calculation of geo-location of targets is achieved from different sensors (DAYTV and FLIR) mounted on a UAV.
The main modules of the GIES are Image Mosaicing, Target Identification, and Terrain Classification.
The task of assembling individual frames from a video stream into a single giant sized image is known as image mosaicing. The current scenario DEALs with a real-world situation where the video frames and the digital flight data are obtained from a sensor mounted on UAV. The work involves developing different approaches of image mosaicing suitable for the present application.
The algorithms, are being used to generate mosaics of terrain from the stream of video imagery obtained during actual flight of the UAV.
The objective of this work is to identify a target region by reconstructing a high resolution image using multiple low resolution images of the same region. The two basic steps of target identification are registration and reconstruction. Registration comprises registration of number of low resolution frames spatially translated and rotated with respect to each other, while reconstruction comprises interpolating a initial high resolution image and minimising the cost function to arrive at a desired high resolution version of the same image.
A wide variety of image processing applications require segmentation and classification of image. The problem becomes complex when the images are obtained in an uncontrolled environment without uniform illumination. The selection of a suitable feature is a critical part of an image segmentation and classification process where the basic objective is to identify the image regions that are homogeneous but dissimilar to all spatially adjacent regions.