Image Mosaicing from Video Sequences

Abstract

The task of assembling individual frames from a video stream into a single giant sized image is known as image mosaicing. The present scenario deals with a real world situation where the video frames and the digital flight data are obtained from a sensor mounted on an aircraft. The paper describes different approaches of automatic image mosaicing suitable for the present application.

The analytical method finds out matching points between the successive image pairs using some sort of similarity measures and use generalized transformation equation to calculate translation, rotation and scaling. The Fourier method uses Fourier transform to calculate the translation and rotation between successive image frames and assemble the images on a large geo-referenced canvas. In both the cases, perspective distortion in the image due to forward-looking sensor is eliminated.

The algorithms, implemented in a SGI workstation, are used to generate mosaics of terrain from the stream of video imagery obtained during actual flight trial of an aircraft and results presented.

Indexing terms:

• Image mosaicing
• Reconnaissance platform
• Change detection
• Activity tracking
• Airborne video surveillance

Additional information

Notes on contributors

Jharna Majumdar

Jharna Majumdar received her B Tech (Hons) in Electronics and Electrical Engineering and Post Graduate Diploma in Computer Technology from Indian Institute of Technology, Kharagpur In 1969 and 1970 respectively. She received her PhD (Electrical Engineering) in 1980. Dr Majumdar worked as Research Scientist at the Institute of Real Time Computer Systems and Robotics, Karlsruhe, Germany during 1983–1989. She joined DRDO at the Centre for Artificial Intelligence & Robotics (CAIR), Bangalore in 1990 and worked in research areas related to Robot Vision. She joined Aeronautical Development Establishment (ADE), Bangalore in 1995 and since then working in the area of aerial Image exploitation for the UAV programs. She has developed an image exploitation system which has undergone a number of actual flight trials. She has guided a number of undergraduate and postgraduate students in India and abroad and presented several papers in national/International conferences. She has about 50 reviewed technical papers published in national/international journals and conference proceedings. She was a member of the International Institution of Pattern Recognition (1983–89) and IEEE (1982–98) and is a life member of the Aeronautical Society of India.

B Vanathy

B Vanathy received her BE in Electronics and Communication Engineering and ME in Computer Science and Engineering from Manomaniam Sundarnar University in 1997 and 1999 respectively. Ms Vanathy joined Aeronautical Development Establishment (ADE), Bangalore as scientist in the year 2000 and since then is working in the area of aerial image exploitation.

Navneet Varshney

Navneet Varshney received his BTech in Computer Engineering from Aligarh Muslim University (AMU). He was awarded the Gold Medal for academic excellence by AMU in 1999. His varied interest include Image processing and Broadcasting technologies. He has worked in an MNC for a year before joining DRDO. He joined Aeronautical Development Establishment (ADE), Bangalore as scientist in the year 2000 and since then is working in the area of aerial image exploitation.