![](bg6.png)
7 CONCLUSIONS
Here we presented an approach to improve the
performance of image processing tasks on mobile
robots equipped with common fixed focus, low-cost
cameras. The basic idea presented was to improve
the quality of images processed by arbitrary vision
algorithms by estimating the amount of motion
artifacts for every image and rejecting bad ones
while also considering a system load indicator.
Our system is suitable for resource-constrained
robots where the camera’s frame rate usually
exceeds the processing capabilities of the onboard
computer. Based on improvements we have seen in
an example scenario, we are confident that the
performance of a number of different image
processing tasks can be improved through this
approach.
ACKNOWLEDGEMENTS
This work has been funded in part by the German
Federal Ministry of Education and Research under
grant 01IM08002.
REFERENCES
Schiehlen, J., Dickmanns, E. D.: Design and control of a
camera platform for machine vision, In: Proc. of IEEE
Int. Conf. on Intelligent Robots and Systems ’94, pp.
2058-2063, 1994.
Yeom, D., Park, N., Jung, S.: Digital controller of novel
voice coil motor actuator for optical image stabilizer,
In: Proc. of Int. Conf. on Control, Automation and
Systems ‘07, pp. 2201-2206, 2007.
Cardani, B.: Optical image stabilization for digital
cameras, In: IEEE Control Systems Magazine vol. 26
no. 2, pp. 21-22, April 2006.
Chi-Wei Chiu, Chao, P. C. - P., Din-Yuan Wu: Optimal
Design of Magnetically Actuated Optical Image
Stabilizer Mechanism for Cameras in Mobile Phones
via Genetic Algorithm, In: IEEE Transactions on
Magnetics vol. 43 no. 6, pp. 2582-2584, June 2007.
Sato, K., Ishizuka, S., Nikami, A., Sato, M.: Control
techniques for optical image stabilizing system, In:
IEEE Transactions on Consumer Electronics vol. 39
no. 3, June 1993.
Günthner, W., Wagner, P., Ulbrich, H.: An inertially
Stabilised Vehicle Camera System. Hardware,
Algorithms, Test Drives, In: Proc. of IEEE Conf. on
Industrial Electronics ‘06, pp. 3815-3820, 2006.
Ji, H., Liu, C.: Motion blur identification from image
gradients, In: IEEE Conf. on Computer Vision and
pattern Recognition ‘08, pp. 1-8, 2008.
Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T.,
Freeman, W. T.: Removing camera shake from a
single photograph, In: Proc. of ACM SIGGRAPH ’06,
pp. 787-794, 2006.
Cho, W. H., Hong, K.-S.: A fast CIS still image
stabilization method without parallax and moving
object problems, IEEE Transactions on Consumer
Electronics vol. 54 no. 2, May 2008.
Nicklin, S. P., Fisher, R. D., Middleton, R. H.: Rolling
Shutter Image Compensation, In: Lecture Notes in
Computer Science vol. 4434/2007, Springer, 2007.
Chun, J.-B., Jung, H., Kyung, C.-M.: Suppressing rolling-
shutter distortion of CMOS image sensors by motion
vector detection, IEEE Transactions on Consumer
Electronics, vol.54, no.3, 2008.
Choi, B.-D., Jung, S.-W., Ko, S.-J.: Motion-blur-free
camera system splitting exposure time, IEEE
Transactions on Consumer Electronics, vol.54, no.3,
2008.
SCHEME FOR EVALUATION AND REDUCTION OF MOTION ARTIFACTS IN MOBILE VISION SYSTEMS
243