Genetic Graph Programming for Object Detection
In this paper, we present a novel approach to learning from visual information given in a form of raster images. The proposed learning method uses genetic programming to synthesize an image processing procedure that performs the desired vision task. The evolutionary algorithm maintains a population of individuals, initially populated with random solutions to the problem. Each individual encodes a directed acyclic graph, with graph nodes corresponding to elementary image processing operations (like image arithmetic, convolution filtering, morphological operations, etc.), and graph edges representing the data flow. Each graph contains a single input node to feed in the input image and an output node that yields the final processing result. This genetic learning process is driven by a fitness function that rewards individuals for producing output that conforms the task-specific objectives. This evaluation is carried out with respect to the training set of images. Thanks to such formulation, the fitness function is the only application-dependent component of our approach, which is thus applicable to a wide range of vision tasks (image enhancement, object detection, object tracking, etc.). The paper presents the approach in detail and describes the computational experiment concerning the task of object tracking in a real-world video sequence.
KeywordsObject Detection Object Tracking Tennis Ball Symbolic Regression Raster Image
Unable to display preview. Download preview PDF.
- 3.Johnson, M.P., Maes, P., Darrell, T.: Evolving visual routines. In: Brooks, R.A., Maes, P. (eds.) Artificial Life IV: proceedings of the fourth international workshop on the synthesis and simulation of living systems, pp. 373–390. MIT Press, Cambridge (1994)Google Scholar
- 6.Lijewski, P.: Automatic Decomposition of the Problem Representation in Coevolutionary Algorithms, Master’s Thesis, Poznań University of Technology, Poznań, Poland (2005)Google Scholar
- 7.Luke, S.: ECJ Evolutionary Computation System (2002), http://www.cs.umd.edu/projects/plus/ec/ecj/
- 9.Marek, A., Smart, W.D., Martin, M.C.: Learning Visual Feature Detectors for Obstacle Avoidance using Genetic Programming. In: Proceedings of the IEEE Workshop on Learning in Computer Vision and Pattern Recognition, Madison, WI (2003)Google Scholar
- 10.Ohio State University repository of motion imagery repository (2004), http://sampl.ece.ohio-state.edu/data/motion/tennis/index.htm
- 12.Segen, J.: GEST: A learning computer vision system that recognizes hand gestures. In: Michalski, R.S., Tecuci, G. (eds.) Machine learning. A Multistrategy Approach, vol. IV, pp. 621–634. Morgan Kaufmann, San Francisco (1994)Google Scholar
- 13.Sun Microsystems, Inc.: Java Advanced Imaging API Specification, Version 1.2 (2001)Google Scholar
- 14.Teller, A., Veloso, M.M.: PADO: A new learning architecture for object recognition. In: Ikeuchi, K., Veloso, M. (eds.) Symbolic Visual Learning, pp. 77–112. Oxford Press (1997)Google Scholar