DCRN: An Optimized Deep Convolutional Regression Network for Building Orientation Angle Estimation in High-Resolution Satellite Images

Abstract

Recently, remote sensing satellite image analysis has received significant attention from geo-information scientists. However, the current geo-information systems lack automatic detection of several building characteristics inside the high-resolution satellite images. The accurate extraction of buildings characteristics helps the decision-makers to optimize urban planning and achieve better decisions. Furthermore, Building orientation angle is a very critical parameter in the accuracy of automated building detection algorithms. However, the traditional computer vision techniques lack accuracy, scalability, and robustness for building orientation angle detection. This paper proposes two different approaches to deep building orientation angle estimation in the high-resolution satellite image. Firstly, we propose a transfer deep learning approach for our estimation task. Secondly, we propose a novel optimized DCRN network consisting of pre-processing, scaled gradient layer, deep convolutional units, dropout layers, and regression end layer. The early proposed gradient layer helps the DCRN network to extract more helpful information and increase its performance. We have collected a building benchmark dataset that consists of building images in Riyadh city. The images used in the experiments are 15,190 buildings images. In our experiments, we have compared our proposed approaches and the other approaches in the literature. The proposed system has achieved the lowest root mean square error (RMSE) value of 1.24, the lowest mean absolute error (MAE) of 0.16, and the highest adjusted R-squared value of 0.99 using the RMS optimizer. The cost of processing time of our proposed DCRN architecture is 0.0113 ± 0.0141 s. Our proposed approach has proven its stability with the input building image contrast variation for all orientation angles. Our experimental results are promising, and it is suggested to be utilized in other building characteristics estimation tasks in high-resolution satellite images.

Gaze Estimation via Strip Pooling and Multi-Criss-Cross Attention Networks

“…SPMCCA-Net clearly outperforms other current mainstream methods on the Gaze360 dataset. Although SPMCCA-Net does not achieve a lower mean angular error on the front 180 • compared to the DAM method [34] under the field of gaze target detection, it achieves a lower mean angular error on the front facing when compared to DAM. More specifically, it produces a mean angular error reduction of 0.28 • in comparison with the baseline method on front 180 • and a mean angular error reduction of 0.64 • in comparison with the baseline method on front 180 • on front facing, which achieves gaze performance with 10.13 • (mean angular error) on front 180 • and 8.40 • (mean angular error) on front facing when β = 2.…”

“…The proposed SPMCCA-Net achieves better performance with a 6.61 • mean angular error when β = 2, which produces a mean angular error reduction of 0.07 • in comparison with the baseline method within 40 • . As an estimation task, gaze estimation has some similarities with other estimation tasks, such as the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) used in [34]. As shown in Table 3, we calculated the MSE, RMSE, and MAPE values for each gaze direction in L2CS-Net and SPMCCA-Net in Gaze360 and RT-Gene, where P denotes pitch direction and Y denotes yaw direction.…”

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review

“…In the context of accurate extraction of building characteristics in high-resolution satellite images, Shahin et al Shahin and Almotairi (2021) propose a novel approach for estimating the building orientation angle. Their proposed deep convolutional regression network (DCRN) architecture outperforms existing methods, achieving the lowest root mean square error (RMSE) and mean absolute error (MAE) values, as well as the highest adjusted R-squared value.…”

Infrared Image Super-Resolution via Progressive Compact Distillation Network

“…For limited training datasets in the target field, transfer learning [17] can effectively apply learned knowledge in a previous field to a novel domain. Shahin [18] et al proposed the transfer deep learning approach for examination tasks and designed the lightweight DCRN to estimate building orientation angle. Zhang [19] et al improved the accuracy of spectrum classification and enhanced the robustness of the model using a multistep training strategy applying different datasets.…”