Hierarchical multi-sensor image registration using evolutionary computation

ABSTRACT

Image registration between multi-sensor imagery is a challenging problem due to the difficulties associated with finding a correspondence between pixels from images taken by the two sensors. However, the moving people in a static scene provide cues to address this problem. In this paper, we propose a hierarchical approach to automatically find the correspondence between the preliminary human silhouettes extracted from synchronous color and infrared (IR) image sequences for image registration using evolutionary computation. The proposed approach reduces the overall computational load without decreasing the final estimation accuracy. Experimental results show that the proposed approach achieves good results for image registration between color and IR imagery.

REFERENCES

• 1: Clark, G., Sengupta, S., Buhl, M., Sherwood, R., Schaich, P., Bull, N., Kane, R., Barth, M., Fields, D., Carter, M.: Detecting buried objects by fusing dual-band infrared images. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on Signals, Systems and Computers 1 (1993) 135--143
• 2: J. Perez-Jacome , V. Madisetti, Target Detection from Coregistered Visual-Thermal-Range Images, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4, p.2741, April 21-24, 1997
• 3: Li, H., Manjunath, B., Mitra, S.: A contour-based approach to multisensor image registration. IEEE Transactions on Image Processing 4 (1995) 320--334
• 4: Inglada, J., Adragna, F.: Automatic multi-sensor image registration by edge matching using genetic algorithms. Proc. IEEE International Geoscience and Remote Sensing Symposium 5 (2001) 2313--2315
• 5: Ali, M., Clausi, D.: Automatic registration of SAR and visible band remote sensing images. Proc. IEEE International Geoscience and Remote Sensing Symposium 3 (2002) 1331--1333
• 6: Dare, P., Dowman, I.: Automatic registration of SAR and spot imagery based on multiple feature extraction and matching. Proc. IEEE International Geoscience and Remote Sensing Symposium 7 (2000) 2896--2898
• 7: Zheng, Q., Chellappa, R.: A computational vision approach to image registration. IEEE Transactions on Image Processing 2 (1993) 311--326
• 8: Hui Li , Yi-Tong Zhou, Automatic EO/IR sensor image registration, Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3, p.3240, October 23-26, 1995
• 9: H. Li , Y. T. Zhou , R. Chellappa, SAR/IR sensor image fusion and real-time implementation, Proceedings of the 29th Asilomar Conference on Signals, Systems and Computers (2-Volume Set), p.1121, October 30-November 02, 1995
• 10: Mandava, V., Fitzpatrick, J., Pickens, D.I.: Adaptive search space scaling in digital image registration. IEEE Transactions on Medical Imaging 8 (1989) 251--262
• 11: van den Elsen, P., Pol, E.J., Viergever, M.: Medical image matching - a review with classification. IEEE Engineering in Medicine and Biology Magazine 12 (1993) 26--39
• 12: Yao, J.: Image registration based on both feature and intensity matching. Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing 3 (2001) 1693--1696

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Sensor fusion

General Terms:
Algorithms

Keywords:
IR image sequence, automatic image registration, color image sequence, genetic algorithm, sensor fusion