Motion and Structure using Multi Estimation Technique

Abstract

A novel approach for Structure from Motion (SFM) problem has been suggested. A recursive framework has been used to find error in measurement of motion and structure parameters. Using feature correspondence it has been suggested that instead of using a single Extended Kalman Filter (EKF) to estimate the state vector an Interactive Multiple Model (IMM) Filter can be used which divides the state vector and estimates it in two steps. A set of three EKFs have been used to track the motion of an object and another set of N EKFs have been used to find structure parameters. The whole arrangement of two stage filters works in an interleaved manner. The first stage estimates motion parameters while second stage estimates structure. The proposed scheme requires 3 + N small EKFs in contrast to N x N used by other researchers. This reduces time complexity from quadratic to linear compared to approaches which use a single full covariance EKF. The technique results in lower error than existing algorithms.

Indexing terms:

• Structure from motion
• Feature correspondence
• Extended Kalman filter
• IMM filter
• Tracking
• Covariance

Additional information

Notes on contributors

Sarita S Bhadauria

Sarita Singh Bhadauria did her BE (Electronics) MTech and PhD (Computer Science). Presently working as Reader and Head, School of Information Technology (a university teaching department), RGPV, Bhopal, on deputation. She has published 10 papers in international journals and many in national and international conferences. She is life member of ISTE, IE, IETE, CSI and HAM RADIO. Her areas of interest are computer vision, image processing, microprocessors and computer network.

N C Goyal

Nemi Chand Goyal (born 1943) did his BE, ME and PhD in 1966, 1972 and 1982 respectively. He worked at MITS, Gwalior in various capacities from 1966 to 2003 and retired as Professor in Electronics from MITS, Gwalior. He has five books to his credit and about 20 research papers in journals of international repute. He has been member of several academic committees of different universities. He was chairman of Jabalpur and Gwalior centres of IETE. He is senior member of IEEE, CSI and fellow of IETE and IE (I). His field of Interest are microprocessors, Digital signal processing and digital image processing. Presently, he is Director (Academics), MPCT, Gwalior.

Gulab Singh

Gulab Singh did his PhD from IIT Delhi and has worked as Head, Computer Science Department, MNNIT Allahabad and is presently working at Dehradun Institute of Technology, Dehradun. His research interests are in Robotics, Al, Neural networks and Computer vision.