M.1 Visual perception
For the first two decades in dynamic vision (1980s and 90s), efficient extraction of oriented edges with adjacent regions of gray values was the predominant method used. The idea of [Kuhnert 1988], based on the Prewitt operator for gradient computation, was developed into a very efficient real-time code by [Mysliwetz 1990] in FORTRAN. With translations into the transputer language Occam (dubbed KRONOS) [Dickmanns D 1997] and by S. Fuerst into the programming language C (dubbed CRONOS), each time with some generalizations, this mature code became the standard workhorse in connection with the 4-D approach to dynamic vision using prediction error feedback.
With the increase in computing power around the turn of the century also region-based features have been used [Hofmann 2004]; this also paved the way for a new corner feature extractor [Dickmanns 2006 and 2008].
Edge extraction with oriented masks
Mysliwetz B, Dickmanns ED (1986). A Vision System with Active Gaze Control for
real-time Interpretation of Well Structured Dynamic Scenes. In: Hertzberger LO (ed) (1986)
Proceedings of the First Conference on Intelligent Autonomous Systems
Kuhnert KD (1988). Zur Echtzeit-Bildfolgenanalyse mit Vorwissen. Dissertation, UniBwM / LRT
Mysliwetz B (1990). Parallelrechner-basierte Bildfolgen-Interpretation zur autonomen Fahrzeugsteuerung. Dissertation, UniBwM / LRT. Kurzfassung
Dickmanns D (1997). Rahmensystem für visuelle Wahrnehmung veränderlicher Szenen durch Computer. Dissertation, UniBwM, INF. Also: Shaker Verlag, Aachen, 1998. Zusammenfassung
Dickmanns ED (2007). Dynamic Vision for Perception and Control of Motion. Springer, London, (Section 5.2) Content
· Check planarity of intensity distribution in a rectangular mask by differencing the diagonal and counter-diagonal sums of the mask elements (mels) => ε :
|ε| > thresh => nonplanar
· Determine averaged horizontal and vertical intensity gradients from grouped mels as shown at left. The optimal size of mels depends on the problem to be solved. Determine gradient magnitude and -direction; merge areas with similar parameters.
· Shift mask in row direction with (adaptable) step size δy; determine points with extreme gradient values => edge elements (green edges in figure; red for vertical search).
· After finishing the row, shift mask in column direction by one mel-width and repeat procedure.
The lower picture to the right has been reconstructed purely from feature data extracted (no original image data are shown):
· Linearly shaded intensity regions (in gray),
· regions with nonplanar intensity distribution (white),
· edges detected in row search (green),
· edges detected in column search (red),
· corners determined in nonplanar regions (blue crosses).
Wheel recognition under oblique angles with special
has been investigated by [Hofmann 2004].
Hofmann U (2004). Zur visuellen Umfeldwahrnehmung autonomer Fahrzeuge. Dissertation, UniBwM / LRT. Kurzfassung
Dickmanns ED, Wuensche HJ (2006). Nonplanarity and efficient multiple feature extraction. Proc. Int. Conf. on Vision and Applications (Visapp), Setubal, (8 pages) pdf
Dickmanns ED (2007). Dynamic Vision for Perception and Control of Motion. Springer-Verlag (Section 5.3) Content
Dickmanns ED (2008). Corner Detection with Minimal Effort on Multiple Scales. Proc. Int. Conf. on Vision and Applications (Visapp), Madeira, (8 pages) pdf