Adaptive algorithms for change detection in image sequence

Detection of small changes/targets in a pair of images in a low signal to clutter plus noise ratio (SCNR) is a problem of great significance in image sequence analysis. The importance of the problem arises in applications such as remote sensing for monitoring growth patterns of urban areas, diagnosis of disease from medical images, visual industry inspection and nondestructive testing for subsurface flaws detection in industrial materials, land resource management, city planning, traffic monitoring, optical and infrared detection from radar images, and weather prediction from satellite and radar images. In this dissertation we present two adaptive algorithms for the detection of small changes/targets (of the order of one pixel) in a pair of images in a low signal to clutter plus noise ratio (SCNR) environment (of the order of $-$14.5 dB). They both have the ability to track the nonstationary image signals (changes/targets and clutter plus noise) and suppress the clutter plus noise background. Both detectors are based on time varying autoregressive models to model image background and on correlation canceling concept. The first one uses an order recursive least squares (ORLS) lattice filter, while the second one is based on a normalized version of the two dimensional least mean square (TDLMS) algorithm. Analytical expression for the improvement factor of the suggested change detectors is presented. Also, the influence of the order of the detectors and of the algorithm parameters of the TDLMS on their detection performances is studied. In addition, the effect of the local mean of the processed images on the optimal estimate of the detector parameters is deduced. The influence of the crosscorrelation between the pair of images on the performance of the detectors as well as the analysis of the computational loads for the processors are studied. The performance of the two algorithms are evaluated by using an optical satellite image, as a clutter background, with computer generated target and noise added to it.

[1]  Laurence B. Milstein,et al.  Statistical tests for image tracking , 1978 .

[2]  Ramesh C. Jain,et al.  On the Analysis of Accumulative Difference Pictures from Image Sequences of Real World Scenes , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  E. Satorius,et al.  Application of Least Squares Lattice Algorithms to Adaptive Equalization , 1981, IEEE Trans. Commun..

[4]  Robert L. Lillestrand,et al.  Techniques ror Change Detection , 1972, IEEE Transactions on Computers.

[5]  Nasir Ahmed,et al.  Video Compression Using Conditional Replenishment and Motion Prediction , 1984, IEEE Transactions on Electromagnetic Compatibility.

[6]  Leonid G. Kazovsky,et al.  Adaptive filters with individual adaptation of parameters , 1986 .

[7]  S. Kesler,et al.  Comparative Analysis Of Two Adaptive Methods For Image Change Detection , 1988, Twenty-Second Asilomar Conference on Signals, Systems and Computers.

[8]  Manbir Singh,et al.  Digital Image Change Detection , 1980 .

[9]  Peter Strobach.  Pure order recursive least-squares ladder algorithms , 1986, IEEE Trans. Acoust. Speech Signal Process..

[10]  S. B. Kesler,et al.  Adaptive order recursive lattice for optical target detection using correlated frames , 1989, [1989] Proceedings. The Twenty-First Southeastern Symposium on System Theory.

[11]  Sophocles J. Orfanidis,et al.  Optimum Signal Processing: An Introduction , 1988 .

[12]  Hans-Hellmut Nagel,et al.  New likelihood test methods for change detection in image sequences , 1984, Comput. Vis. Graph. Image Process..

[13]  H. T. Kung.  Why systolic architectures? , 1982, Computer.

[14]  Yoram Yakimovsky,et al.  Boundary and Object Detection in Real World Images , 1974, JACM.

[15]  Tzay Y. Young,et al.  A Mathematical Model for Computer Image Tracking , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  S. Alexander,et al.  Optimal gain derivation for the LMS algorithm using a visual fidelity criterion , 1984 .

[17]  Ramesh C. Jain,et al.  Extraction of Motion Information from Peripheral Processes , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Edward J. Delp,et al.  Adaptive gray scale mapping to reduce registration noise in difference images , 1986, Comput. Vis. Graph. Image Process..

[19]  Werner Frei,et al.  A Digital Technique for Accurate Change Detection in Nuclear Medical Images - With Application to Myocardial Perfusion Studies Using Thallium-201 , 1979, IEEE Transactions on Nuclear Science.

[20]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[21]  S. Kesler,et al.  CHANGE-DETECTION IN IMAGE SEQUENCES , 1988 .

[22]  S. Dikshit.  A recursive Kalman window approach to image restoration , 1982 .

[23]  I. Reed,et al.  A Detection Algorithm for Optical Targets in Clutter , 1987, IEEE Transactions on Aerospace and Electronic Systems.

[24]  Yair Barniv,et al.  Dynamic Programming Solution for Detecting Dim Moving Targets , 1985, IEEE Transactions on Aerospace and Electronic Systems.

[25]  Wesley E. Snyder,et al.  The detection of unresolved targets using the Hough Transform , 1982, Comput. Vis. Graph. Image Process..

[26]  Steven D. Blostein,et al.  Detection of small moving objects in image sequences using multistage hypothesis testing , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[27]  Richard W. Harris,et al.  A variable step (VS) adaptive filter algorithm , 1986, IEEE Trans. Acoust. Speech Signal Process..

[28]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[29]  I. Reed,et al.  Adaptive Optical Target Detection Using Correlated Images , 1985, IEEE Transactions on Aerospace and Electronic Systems.

[30]  M. Leonard Bryan,et al.  Potentials for change detection using seasat synthetic aperture radar data , 1984 .

[31]  David W. Thomas,et al.  The two-dimensional adaptive LMS (TDLMS) algorithm , 1988 .

[32]  FATHY F. YASSA,et al.  Optimality in the choice of the convergence factor for gradient-based adaptive algorithms , 1987, IEEE Trans. Acoust. Speech Signal Process..