Remote sensing plays an important role in assessing temporal changes in land features. The challenge often resides in the conversion of large quantities of raw data into actionable information in a timely and cost-effective fashion. To address this issue, research was undertaken to develop an innovative methodology integrating biologically-inspired algorithms with standard image classification algorithms to improve information extraction from multitemporal imagery. Genetic programming was used as the optimization engine to evolve feature-specific candidate solutions in the form of nonlinear mathematical expressions of the image spectral channels (spectral indices). The temporal generalization capability of the proposed system was evaluated by addressing the task of building rooftop identification from a set of images acquired at different dates in a cross-validation approach. The proposed system generates robust solutions (kappa values > 0.75 for stage 1 and > 0.4 for stage 2) despite the statistical differences between the scenes caused by land use and land cover changes coupled with variable environmental conditions, and the lack of radiometric calibration between images. Based on our results, the use of nonlinear spectral indices enhanced the spectral differences between features improving the clustering capability of standard classifiers and providing an alternative solution for multitemporal information extraction.
Information extraction from high spatial resolution imagery is sometimes hampered by the limited number of
spectral channels available from these systems. Standard supervised classification algorithms found in commercial
software packages may misclassify different features with similar spectral characteristics; leading to a high
occurrence of false positives. An additional step in the information extraction process was developed incorporating
the concept of object geometry. Objects are defined as a contiguous group of pixels identified as belonging to
a single class in the spectral classification. Using results from the spectral classification, a supervised approach
was developed using genetic programming to select and mathematically combine feature-specific shape descriptors from a larger set of shape descriptors, to form a new classifier. This investigation focused on extraction of residential housing from QuickBird and IKONOS imagery of the Mississippi Gulf Coast before and immediately after hurricane Katrina. Use of genetic programming significantly reduced false positives caused by asphalt pavement and isolated roofing material scattered throughout the image.
The need for information extracted from remotely sensed data has increased in recent decades. To address this issue,
research is being conducted to develop a complete multi-stage supervised object recognition system. The first stage of
this system couples genetic programming with standard unsupervised clustering algorithms to search for the optimal
preprocessing function. This manuscript addresses the quantification and the characterization of the uncertainty involved
in the random creation of the first set of candidate solutions from which the algorithm begins. We used a Monte Carlo
type simulation involving 800 independent realizations and then analyzed the distribution of the final results. Two
independent convergence approaches were investigated:  convergence based solely on genetic operations (standard)
and  convergence based on genetic operations with subsequent insertion of new genetic material (restarting). Results
indicate that the introduction of new genetic material should be incorporated into the preprocessing framework to
enhance convergence and to reduce variability.