CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References
id ecaade2020_222
authors Ikeno, Kazunosuke, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year 2020
title Automatic Generation of Horizontal Building Mask Images by Using a 3D Model with Aerial Photographs for Deep Learning
source Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 271-278
summary Information extracted from aerial photographs is widely used in urban planning and design. An effective method for detecting buildings in aerial photographs is to use deep learning for understanding the current state of a target region. However, the building mask images used to train the deep learning model are manually generated in many cases. To solve this challenge, a method has been proposed for automatically generating mask images by using virtual reality 3D models for deep learning. Because normal virtual models do not have the realism of a photograph, it is difficult to obtain highly accurate detection results in the real world even if the images are used for deep learning training. Therefore, the objective of this research is to propose a method for automatically generating building mask images by using 3D models with textured aerial photographs for deep learning. The model trained on datasets generated by the proposed method could detect buildings in aerial photographs with an accuracy of IoU = 0.622. Work left for the future includes changing the size and type of mask images, training the model, and evaluating the accuracy of the trained model.
keywords Urban planning and design; Deep learning; Semantic segmentation; Mask image; Training data; Automatic design
series eCAADe
email ikeno@it.see.eng.osaka-u.ac.jp
full text file.pdf (14,647,690 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Bittner, K, Adam, F, Cui, S, K├Ârner, M and Reinartz, P (2018) Find in CUMINCAD Building Footprint Extraction From VHR Remote Sensing Images Combined With Normalized DSMs Using Fused Fully Convolutional Networks , IEEE Journal of Selected Topics in Applied EarthObservations and Remote Sensing, 11, p. 2615-2629

100%; open Cao, R, Fukuda, T and Yabuki, N (2019) Find in CUMINCAD Quantifying Visual Environment by Semantic Segmentation Using Deep Learning , Proceedings of the 24th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2019), p. 623-632

100%; open Chen, Y, Gao, W, Widyaningrum, E, Zheng, M and Zhou, K (2018) Find in CUMINCAD Building classification of VHR airborne stereo images using fully convolutional networks and free training samples , Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., p. 87-92

100%; open Dai, J, He, K and Sun, J (2016) Find in CUMINCAD Instance-Aware Semantic Segmentation via Multi-Task Network Cascades , The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 3150-3158

100%; open Everingham, M, Eslami, S. M. A, Gool, L. V, Williams, C. K. I., Winn, J and Zisserman, A (2015) Find in CUMINCAD The PASCAL Visual Object Classes Challenge: A Retrospective , International Journal of Computer Vision, 111, p. 98-136

100%; open Fukuda, T, Novak, M and Fujii, H (2019) Find in CUMINCAD Development of Segmentation-Rendering on Virtual Reality for Training Deep-learning, Simulating Landscapes and Advanced User Experience , Proceedings of the 37th eCAADe and 23rd SIGraDi Conference, pp. 433-440

100%; open Jabbar, A, Farrawell, L, Fountain, J and Chalup, S (2017) Find in CUMINCAD Training Deep Neural Networks for Detecting Drinking Glasses Using Synthetic Images , Neural Information Processing: 24th International Conference, ICONIP 2017, p. 354-363

100%; open Krizhevsky, A, Sutskever, I and Hinton, G. E. (2012) Find in CUMINCAD ImageNet classification with deep convolutional neural networks , Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS 2012), p. 1097-1105

100%; open Long, J, Shelhamer, E and Darrell, T (2015) Find in CUMINCAD Fully Convolutional Networks for Semantic Segmentation , The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 3431-3440

100%; open Redmon, J, Divvala, S, Girshick, R and Farhadi, A (2016) Find in CUMINCAD You Only Look Once: Unified, Real-Time Object Detection , The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 779-788

100%; open Ronneberger, O, Fischer, P and Brox, T (2015) Find in CUMINCAD U-Net: Convolutional Networks for Biomedical Image Segmentation , International Conference on Medical Image Computing and Computer-Assisted Intervention, p. 234-241

100%; open Zhang, Q, Wang, Y, Liu, Q, Liu, X and Wang, W (2016) Find in CUMINCAD CNN based suburban building detection using monocular high resolution Google Earth images , Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), pp. 661-664

100%; open Zhao, K, Kang, J, Jung, J and Sohn, G (2018) Find in CUMINCAD Building Extraction from Satellite Images Using Mask R-CNN with Building Boundary Regularization , Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), p. 247-251

100%; open Zhou, K, Chen, Y, Smal, I and Lindenbergh, R (2019) Find in CUMINCAD Building segmentation from Airborne VHR Images Using mask R-CNN , Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., p. 155-161

last changed 2020/09/09 09:54
pick and add to favorite papersHOMELOGIN (you are user _anon_367526 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002