Firefly optimization algorithm for change detection in urban areas using remote sensing images

Urban areas experience rapid changes due to natural and manmade factors. Monitoring these changes is essential for urban planning, resource management, and updating geospatial information systems. Therefore, change detection is an interesting topic for researchers in the remote sensing field, especially with the availability of high spatial resolution images in recent years. However, the use of high-resolution imagery increases the variability within homogenous land-cover classes and leads to low-accuracy change detection results. To overcome this problem and to generate a more accurate change mask, several features have been used to extract spatial information from images. The firefly algorithm (FA), as one of the recently developed optimization algorithms is evaluated for finding the optimum subspace. The urban areas under study are Azadshahr (in Tehran province, Iran) and Shiraz (Iran). Two high-resolution images at two different time points were captured from each study area. To detect intra-class changes, a two-class classification of differential features was used, which also helps with the poor radiometric condition of the images (especially in Azadshahr images). The performance of FA was then compared with a particle swarm optimization (PSO) algorithm and a genetic algorithm (GA). The results show that FA outperformed both PSO and GA algorithms with an overall accuracy and kappa coefficient of [95.17%, 0.90] versus [93.45%, 0.87] and [91.03%, 0.82] in the Azadshahr study area, and [94.87%, 0.90] versus [94.44%, 0.89] and [93.16%, 0.86] in the Shiraz study area, respectively. The proposed methodology was also compared with the results of two other studies conducted on the Azadshahr area and outperformed them as well. To analyze the contribution and importance of each feature type in change detection results, three indices, i.e. Effectiveness, Partial Effectiveness and Overall Effectiveness, were introduced in this paper. The result shows that the features extracted from a grey level co-occurrence matrix and the features of other color spaces are the most effective features selected by FA to be used in change detection of high-resolution images. Moreover, these indices revealed the weakness of using only spectral information for change detection of high-resolution images.