Abstract
Postclassification Comparison (PCC) has been widely used as a change-detection method. The PCC algorithm is straightforward and easily applicable to all satellite images, regardless of whether they are acquired from the same sensor or in the same environmental conditions. However, PCC is prone to cumulative error, which results from classification errors. Alternatively, Change Vector Analysis in Posterior Probability Space (CVAPS), which interprets change based on comparing the posterior probability vectors of a pixel, can alleviate the classification error accumulation present in PCC. CVAPS identifies the type of change based on the direction of a change vector. However, a change vector can be translated to a new position within the feature space; consequently, it is not inconceivable that identical measures of direction may be used by CVAPS to describe multiple types of change. Our proposed method identifies land-cover transitions by using a fusion of CVAPS and PCC. In the proposed algorithm, contrary to CVAPS, a threshold does not need to be specified in order to extract change. Moreover, the proposed method uses a Random Forest as a trainable fusion method in order to obtain a change map directly in a feature space which is obtained from CVAPS and PCC. In other words, there is no need to specify a threshold to obtain a change map through the CVAPS method and then combine it with the change map obtained from the PCC method. This is an advantage over other change-detection methods focused on fusing multiple change-detection approaches. In addition, the proposed method identifies different types of land-cover transitions, based on the fusion of CVAPS and PCC, to improve the results of change-type determination. The proposed method is applied to images acquired by Landsat and Quickbird. The resultant maps confirm the utility of the proposed method as a change-detection/labeling tool. For example, the new method has an overall accuracy and a kappa coefficient relative improvement of 7% and 9%, respectively, on average, over CVAPS and PCC in determining different types of change.
Highlights
Remote sensing can be used to detect ‘land-use/land-cover’ (LULC) changes [1]
Change-detection methods based on classification results, such as Postclassification Comparison (PCC) [4] and Change Vector Analysis in Posterior Probability Space (CVAPS) [5], do not need the remotely sensed data to be acquired in the same season or from the same remote sensor [2], an improvement over the latter methods, such as Change Vector Analysis (CVA) [6,7]
The proposed method uses Random Forest (RF) as a trainable fusion method to obtain a change map directly in a feature space which is obtained from CVAPS and PCC
Summary
Remote sensing can be used to detect ‘land-use/land-cover’ (LULC) changes [1]. Generally, digital remote sensing change-detection methods can be classified into two types [2,3]: (1). Luo et al detected urban change by first obtaining multiple change maps using different change-detection methods, and applied Dempster–Shafer theory to fuse the results, based on a segmentation object map [14] These examples demonstrate how the fusion of change-detection methods may be an effective way to improve the results of LULC change detection. This is an advantage over other change-detection methods focused on fusing multiple change-detection approaches. Since both CVAPS and PCC are based on classification results, the proposed method makes the best use of the information that is available at present to improve the performance of CVAPS and PCC in change-type recognition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
