Computer Vision
N. Rahimpour; A. Azadbakht; M. Tahmasbi; H. Farahani; S.R. Kheradpishe; A. Javaheri
Abstract
Background and Objectives: Cadastral boundary detection deals with locating the boundary of the ownership and use of land. Recently, there has been high demand for accelerating and improving the automatic detection of cadastral mapping. As this problem is in its starting point, there are few researches ...
Read More
Background and Objectives: Cadastral boundary detection deals with locating the boundary of the ownership and use of land. Recently, there has been high demand for accelerating and improving the automatic detection of cadastral mapping. As this problem is in its starting point, there are few researches using deep learning algorithms. Methods: In this paper, we develop an algorithm with a Mask R-CNN core followed with geometric post-processing methods that improve the quality of the output. Many researches use classification or semantic segmentation but our algorithm employs instance segmentation. Our algorithm includes two parts, each of which consists of a few phases. In the first part, we use Mask R-CNN with the backbone of a pre-trained ResNet-50 on the ImageNet dataset. In the second part, we apply three geometric post-processing methods to the output of the first part to get better overall output. Here, we also use computational geometry to introduce a new method for simplifying lines which we call pocket-based simplification algorithm.Results: We used 3 google map images with sizes 4963 × 2819, 3999 × 3999, and 5520 × 3776 pixels. And divide them to overlapping and non-overlapping 400×400 patches used for training the algorithm. Then we tested it on a google map image from Famenin region in Iran. To evaluate the performance of our algorithm, we use popular metrics Recall, Precision, and F-score. The highest Recall is 95%, which also maintains a high precision of 72%. This results in an F-score of 82%.Conclusion: The idea of semantic segmentation to derive boundary of regions, is new. We used Mask R-CNN as the core of our algorithm, that is known as a very suitable tools for semantic segmentation. Our algorithm performs geometric post-process improves the f-score by almost 10 percent. The scores for a region in Iran containing many small farms is very good.
Geographic Information System
E. Norouzi; S. Behzadi
Abstract
Background and Objectives: Climate phenomena such as quantity of surface evaporation are affected by many environmental factors and parameters, which makes modeling and data mining difficult. On the other hand, the estimation of surface evaporation for a target station can be difficult as a result of ...
Read More
Background and Objectives: Climate phenomena such as quantity of surface evaporation are affected by many environmental factors and parameters, which makes modeling and data mining difficult. On the other hand, the estimation of surface evaporation for a target station can be difficult as a result of partial or complete lack of local meteorological data under many conditions. In this regard, satellite imagery can play a special role in modeling and data mining of climatic phenomena, because of their significant advantages, including availability and their potential analysis. Therefore, addressing the improvement and expansion of machine learning methods and modeling algorithms along with remote sensing data is inevitable.Methods: In this research, we intend to study the ability of 11 machine-learning modeling algorithms to model data and surface evaporation phenomena using satellite imagery. We used two methods to prepare the database: PCA and its opposite method using standard deviation and correlation.Results: The calculation of the Root Mean Squared Error (RMSE) indicated that, in general, the use of the PCA method has a better result in preparing and reducing the dimensions of large databases for all methods of machine learning. The SEGPR model was ranked first with the least error (93.49%) in the Principal Component Analysis (PCA) method, and the Artificial Neural Network (ANN) model performed well in both data preparation methods (93.42, 93.38), and the Classification-Tree-Coarse model had the highest error in both methods (92.66, 92.67).Conclusion: Consequently, it can be said that by changing the methods of database preparation in order to train models, the modeling results can be changed effectively.
Image Processing
A. Sharifi
Abstract
Background and Objectives: High resolution multi-spectral (HRMS) images are essential for most of the practical remote sensing applications. Pan-sharpening is an effective mechanism to produce HRMS image by integrating the significant structural details of panchromatic (PAN) image and rich spectral ...
Read More
Background and Objectives: High resolution multi-spectral (HRMS) images are essential for most of the practical remote sensing applications. Pan-sharpening is an effective mechanism to produce HRMS image by integrating the significant structural details of panchromatic (PAN) image and rich spectral features of multi-spectral (MS) images.Methods: The traditional pan-sharpening methods incur disadvantages like spectral distortion, spatial artifacts and lack of details preservation in the fused image. The pan-sharpening approach proposed in this paper is based on integrating wavelet decomposition and convolutional sparse representation (CSR). The wavelet decomposition is performed on PAN and MS images to obtain low-frequency and high-frequency bands. The low-frequency bands are fused by exploring the CSR based activity level measurement.Results: The HRMS image is restored by implementing the inverse transform on fused bands. The fusion rules are constructed, thus to transfer the crucial details from source images to the fused image effectively.Conclusion: The proposed method produces HRMS images with rational spatial and spectral qualities. The visual outcomes and quantitative measures approve the eminence of the proposed fusion framework.