Abstract
A computer-vision system to assist pilots during low-altitude flight has been developed in this research study. During this critical section of flight, a system that can detect various objects on the ground would be very useful both for enhancing the safety of navigation and for relieving pilots of a part of their workload in flight control. Such tasks can generally be automated by computer-vision-based methods, which provide the ability for object detection and tracking. This paper describes the algorithms developed for accomplishing such tasks. There are two main stages in the vision system. First, independently moving objects in the scene are detected and segmented from the background. Then, they are tracked from frame to frame, and their 3D motion parameters are recursively estimated with Kalman filtering techniques. Experiments using real-world image sequences have been carried out, and the results show that tracking moving objects is successful and the estimation of object's motion parameters are quite accurate.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bach RE Jr., Wingrove RC (1985) Applications of state estimation applications in aircraft flight-data analysis, J Aircraft 22:547–554
Barren JL, Fleet DJ, Beauchemin SS, Burkitt TA (1992) Performance of optical flow techniques, IEEE Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, IEEE Computer Society Press, Los Alamitos, Calif., USA, pp 236–242
Brown RG, Hwang PYC (1992) Introduction to random signals and applied Kalman filtering, 2nd edn. Wiley, New York
Cheng VHL, Sridhar B (1990) Integration of active and passive sensors for obstacle avoidance, IEEE Control Sys Magazine 10:43–50
Haynes AS, Jain R (1983) Time-varying edge detection, Comput Vis Graph Image Processing 21:345–367
Huttenlocher DP, Noh JJ, Rucklidge WJ (1993) Tracking non-rigid objects in complex scenes, International Conference on Computer Vision, Berlin, Germany, IEEE Computer Society Press, Los Alamitos, Calif., USA, pp 93–101
Jain AR, Nagel H.-H (1979) On the analysis of accumulative difference pictures from image sequences of real world scenes, IEEE Trans Patt Anal Machine Intell 1:206–214
Jain RC (1984) Segmentation of frame sequences obtained by a moving observer, IEEE Trans Patt Anal Machine Intell 6:624–629
Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision, DARPA Image Understanding Workshop, Washington, D.C., Defense Supply Service, Washinton D.C., USA, pp 121–130
Matthies L, Kanade T, Szeliski R (1989) Kalman filter-based algorithms for estimating depth from image sequences, Int J Comput Vis 3:209–236
Nelson RC (1991) Qualitative Detection of Motion by a Moving Observer, IEEE Conference on Computer Vision and Pattern Recognition, Maui, Hawaii, IEEE Computer Society Press, Los Alamitos, Calif., USA, pp 173–178
Pekelsma N.J. Denton RV (1987) Pilot oriented aids for helicopter automatic nap-of-the-earth flight, AHS National Specialists' Meeting in Flight Control and Avionics, American Helicopter Society, New York, USA, pp 13–15
Smith PN (1990) NASA Image data base user's guide Version 1, NASA Ames Research Center, Moffett Field, Calif
Smith PN, Sridhar B, Hussien B (1992) Vision-based range estima-tion using helicopter flight data, IEEE Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, IEEE Computer Society Press, Los Alamitos, Calif., USA, pp 202–208
Sridhar B, Suorsa R (1991) Integration of motion and stereo sensors in passive ranging systems, IEEE Trans Aerospace Electronic Syst 27:741–746
Tang Y-L, Kasturi R (1994) Accurate estimation of object location in an image sequence using helicopter flight data, Int J Robotics ComputerIntegrated Manufacturing 11:65–72
Tang Y-L, Kasturi R (1995) Runway detection in an image sequence, Proceedings of the IS&T/SPIE Symposium on Electronic Imaging Science & Technology 2421:65–72
Thomson WB, Pong T-C (1990) Detecting moving objects, Int J Comput Vis 4:39–57
Wu JJ, Rink RE, Caelli TM, Gourishankar VG (1988) Recovery of the 3-d location and motion of a rigid object through camera image (an extended Kalman filter approach), Int J Comput Vis 3:373–394
Zhang Z, Faugeras OD (1992) Three-dimensional motion computation and object segmentation in a long sequence of Stereo Frames, Int J Comput Vis 7:211–241
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tang, YL., Kasturi, R. Tracking moving objects during low altitude flight. Machine Vis. Apps. 9, 20–31 (1996). https://doi.org/10.1007/BF01246636
Issue Date:
DOI: https://doi.org/10.1007/BF01246636