A Comprehensive Evaluation of Approaches for Built-Up Area Extraction from Landsat OLI Images Using Massive Samples
Round 1
Reviewer 1 Report
see the attached comment file
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer 1,
Thank you for your suggestions. This manuscript is a revised version of the manuscript ID remotesensing-410868 titled “A Comprehensive Evaluation of Approaches for Built-up Area Extraction from Landsat OLI Images Using Massive Samples”. Your comments have been responded in a point-by-point way, which is attached in this PDF.
Best wishes,
Hong TANG
Author Response File: Author Response.pdf
Reviewer 2 Report
1. The English of this paper must be improved. Please send it to a native speaker to make corrections.
2. Add also the computational cost of each system.
3. In Eq. 3, in the two sums you may remove D_N and S_N, since they confuse (only keep d_i and s_j). Check carefully all equations again.
4. The four equations after Eq. 8, may need corrections. Check again the indexes of the sum for the m2 and s2 computation.
5. Provide at least a reference for any feature that you use, e.g. Entropy, homogeneity, etc.
6. Please, provide a webpage (in the paper) that will include the used dataset and your results for people that are interesting for comparisons.
7. If it is possible, apply your method on public datasets with at least 100 building and to get more accurate results concerning the performances and you may add more comparisons with state-of-the-art methods. So, you can use SZTAKI-INRIA building detection dataset (see Benedek et al. (2012)). http://web.eee.sztaki.hu/remotesensing/building_benchmark.html
8. In addition, in order to improve your related work, you can cite the following related works.
[1] Benedek, C., Descombes, X., Zerubia, J., 2012. Building development monitoring in multitemporal remotely sensed image pairs with stochastic birth-death dynamics. IEEE Trans. Pattern Anal. Mach. Intell. 34, 33–50.
[2] I. Grinias , C. Panagiotakis and G. Tziritas, MRF-based Segmentation and Unsupervised Classification for Building and Road Detection in Peri-urban Areas of High-resolution, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 122, pp. 145-166, 2016.
[3] Pelletier, C., Valero, S., Inglada, J., Champion, N., & Dedieu, G. (2016). Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas. Remote Sensing of Environment, 187, 156-168.
[4] Inglada, J., 2007. Automatic recognition of man-made objects in high resolution optical remote sensing images by SVM classification of geometric image features. ISPRS J. Photogramm. Remote Sens. 62, 236–248.
[5] C. Panagiotakis, E. Kokinou and A. Sarris, Curvilinear Structure Enhancement and Detection in Geophysical Images, IEEE Trans. on Geoscience and Remote Sensing, vol. 49, no. 6, pp. 2040-2048, 2011.
Author Response
Dear Reviewer 2,
Thank you for your suggestions. This manuscript is a revised version of the manuscript ID remotesensing-410868 titled “A Comprehensive Evaluation of Approaches for Built-up Area Extraction from Landsat OLI Images Using Massive Samples”. Your comments have been responded in a point-by-point way, which is attached in this PDF.
Best wishes,
Hong TANG
Author Response File: Author Response.pdf
