Video to information (V2I) system enabling old commercial cockpit instruments to participate in the advanced information retrieval and safety services

Many nonmodernized aircraft lack the ability to capture, in a computer readable medium, information related to cockpit display instruments, such as airspeed indicators and barometric altimeters. Most of these old cockpit instruments consist of a mechanical or pneumatically operated analog device without an electronic interface. In this work, we present a new video to information (V2I) system to enable these old instruments to output digital readouts by using a camera system and embodiments of image processing algorithms to interpret video data streams. A camera system is trained across the instruments and captures image frames. An image processing system then extracts graphical symbols such as needle position, alphanumeric readout, bar position, color, and similar informative cues. The data are then interpreted and information is extracted, recorded and transmitted to a responsive system, which may then act upon the data as desired for data collection and analysis.

[1]  Uwe D. Hanebeck,et al.  Template matching using fast normalized cross correlation , 2001, SPIE Defense + Commercial Sensing.

[2]  Samuel S. Blackman,et al.  Multiple-Target Tracking with Radar Applications , 1986 .

[3]  Ernest L. Hall,et al.  Computer Image Processing and Recognition , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Haim H. Permuter,et al.  Parametric estimation of the orientation of textured planar surfaces , 2001, IEEE Trans. Image Process..

[5]  Esko Ukkonen,et al.  Faster template matching without FFT , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[6]  Mohammad Gharavi-Alkhansari,et al.  A fast globally optimal algorithm for template matching using low-resolution pruning , 2001, IEEE Trans. Image Process..

[7]  Mikhail J. Atallah Faster image template matching in the sum of the absolute value of differences measure , 2001, IEEE Trans. Image Process..

[8]  Françoise Dibos Projective analysis of 2-D images , 1998, IEEE Trans. Image Process..