Abstract
The article describes a method for detecting solar panels in satellite imagery. Due to the growing popularity of this technology, problems associated with the maintenance of solar panels are also becoming relevant. Many service companies are interested in obtaining information about potential customers. Thus, the analysis of photographs in order to identify solar panels and accumulate statistical information on energy production capacities, their territorial distribution is an urgent task. The development of the theory for learning the deep neural networks gave a powerful impact on the development of various versions of convolutional neural networks used to solve recognition and classification issues. The advent of GPU parallelization technology has made such training feasible in a reasonable amount of time. In this article authors solved the two independent problems. A first, the deep convolutional neural network recognizes the presence of solar panels in a photograph. This model was trained using a set of low-resolution photos from low-quality satellite images from Google and showed a high result of detecting the presence of an object in the image. A second, solar panels with obtaining the exact coordinates of their location were detected.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Growth of photovoltaics. https://en.wikipedia.org/wiki/Growth_of_photovoltaics. Accessed 12 Dec 2019
Utility-scale solar in 2018 Still growing thanks to Australia and other later entrants. https://wiki-solar.org/library/public/190314_Utility-scale_solar_in_2018.pdf. Accessed 12 Dec 2019
Clean Energy Investment Exceeded $300 Billion Once Again in 2018. https://about.bnef.com/blog/clean-energy-investment-exceeded-300-billion-2018. Accessed 12 Dec 2019
Trends in photovoltaic applications 2018. http://www.iea-pvps.org/fileadmin/dam/intranet/task1/IEA_PVPS_Trends_2018_in_Photovoltaic_Applications.pdf. Accessed 12 Dec 2019
Transition in energy, transport—10 predictions for 2019—2. Solar additions rise despite China. BNEF—Bloomberg New Energy Finance. https://about.bnef.com/blog/transition-energy-transport-10-predictions-2019. Accessed 12 Dec 2019
International Energy Agency. Technology roadmap: solar photovoltaic energy. http://www.oregonrenewables.com/Publications/Reports/IEA_TechnologyRoadmapSolarPhotovoltaicEnergy_2014.pdf. Accessed 12 Dec 2019
Pozzebon S (2014) One chart shows how solar could dominate electricity in 30 years. https://www.businessinsider.in/one-chart-shows-how-solar-could-dominate-electricity-in-30-years/articleshow/43913904.cms?utm_source=contentofinterest&utm_medium=text&utm_campaign=cppst. Accessed 12 Dec 2019
Solar—fuels & technologies—IEA. https://www.iea.org/fuels-and-technologies/solar. Accessed 12 Dec 2019
Kirichenko L, Radivilova T, Bulakh V (2020) Binary classification of fractal time series by machine learning methods. In: Lytvynenko V, Babichev S, Wójcik W, Vynokurova O, Vyshemyrskaya S, Radetskaya S (eds) Lecture notes in computational intelligence and decision making. ISDMCI 2019. Advances in intelligent systems and computing, vol 1020. Springer, Cham
Hinton G, Osindero S, The Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554. https://doi.org/10.1162/neco.2006.18.7.1527
Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127. https://doi.org/10.1561/2200000006
Erhan D, Bengio Y, Courville A et al (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11:625–660. https://doi.org/10.1145/1756006.1756025
Golovko V, Kroschanka A (2016) The nature of unsupervised learning in deep neural networks: a new understanding and novel approach. Opt Mem Neural Netw 3:127–141. https://doi.org/10.3103/S1060992X16030073
Golovko V (2017) Deep learning: an overview and main paradigms. Opt Mem Neural Netw 26:1–17. https://doi.org/10.3103/S1060992X16040081
Komar M et al (2018) Deep neural network for image recognition based on the Caffe framework. In: Proceedings of the IEEE second international conference on data stream mining & processing (DSMP), Lviv, Ukraine, pp 102–106. https://doi.org/10.1109/dsmp.2018.8478621
Komar M et al (2018) Compression of network traffic parameters for detecting cyber attacks based on deep learning. In: Proceedings of the 9th IEEE international conference on dependable systems, services and technologies (DESSERT). Kyiv, Ukraine, pp 44–48. https://doi.org/10.1109/dessert.2018.8409096
Komar, M. et. al. (2018) Deep neural network for detection of cyber attacks. In: Proceedings of the IEEE first international conference on system analysis & intelligent computing (SAIC). Kyiv, Ukraine, pp 186–189. https://doi.org/10.1109/saic.2018.8516753
Korpała G, Kawalla R (2015) Optimization and application of GPU calculations in material science. https://library.wolfram.com/infocenter/Conferences/9346/1444771976.pdf. Accessed 12 Dec 2019
Dorosh V et al (2018) Parallel deep neural network for detecting computer attacks in information telecommunication systems. In: Proceedings of the 38th IEEE international conference on electronics and nanotechnology (ELNANO), Kyiv, Ukraine: TUU «Kyiv Polytechnic Institute», pp 675–679. https://doi.org/10.1109/elnano.2018.8477530
Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):193–202
LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324. https://doi.org/10.1109/5.726791
Golovko V, Krasnoproshin V (2017) Neural network data processing technologies. Minsk, Republic of Belarus (in Russian)
Huang G et al (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). Honolulu, HI, USA, pp 4700–4708. https://doi.org/10.1109/cvpr.2017.243
Jégou S et al (2017) The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA. https://doi.org/10.1109/cvprw.2017.156. https://arxiv.org/pdf/1611.09326.pdf. Accessed 12 Dec 2019
Zhu Y et al (2017) Densenet for dense flow. In: 2017 IEEE international conference on image processing (ICIP). https://doi.org/10.1109/icip.2017.8296389. https://arxiv.org/pdf/1707.06316v1.pdf. Accessed 12 Dec 2019
Evolution of neural networks for image recognition in Google: Inception-v3. https://habr.com/post/302242. Accessed 12 Dec 2019 (in Russian)
He K et al (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, pp 770–778. https://doi.org/10.1109/cvpr.2016.90
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25(2):1097–1105. https://doi.org/10.1145/3065386
Iandola FN et al (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. https://arxiv.org/pdf/1602.07360.pdf. Accessed 12 Dec 2019
Tsang S-H (2018) Review: SqueezeNet (image classification). https://towardsdatascience.com/review-squeezenet-image-classification-e7414825581a. Accessed 12 Dec 2019
Howard AG, Zhu M, Chen B et al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. https://arxiv.org/pdf/1704.04861.pdf. Accessed 12 Dec 2019
CIFAR-10 and CIFAR-100 dataset. http://www.cs.toronto.edu/~kriz/cifar.html. Accessed 12 Dec 2019
Examples of images from MNIST, CIFAR and SVHN datasets. https://www.researchgate.net/figure/Examples-of-images-from-MNIST-CIFAR-and-SVHN-Datasets_fig1_320564389. Accessed 12 Dec 2019
Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot MultiBox detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision. In: ECCV 2016. Lecture notes in computer science, vol 9905. Springer, Berlin
Tsang S-H (2018) Review: SSD—single shot detector (object detection). https://towardsdatascience.com/review-ssd-single-shot-detector-object-detection-851a94607d11. Accessed 12 Dec 2019
Lin T, Maire M, Belongie S et al (2014) Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision. ECCV 2014. Lecture notes in computer science, vol 8693. Springer, Berlin
Redmon J et al (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV. https://doi.org/10.1109/cvpr.2016.91
Malof J et al (2015) Automatic solar photovoltaic panel detection in satellite imagery. In: 2015 international conference on renewable energy research and applications (ICRERA), Palermo, Italy, pp 1428–1431. https://doi.org/10.1109/icrera.2015.7418643
Malof J, Bradbury K, Collins L et al (2016) Automatic detection of solar photovoltaic arrays in high resolution aerial imagery. Appl Energy 183:229–240. https://doi.org/10.1016/j.apenergy.2016.08.191
Malof J et al (2017) A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery. In: 2017 IEEE international geoscience and remote sensing symposium (IGARSS), Fort Worth, TX. https://doi.org/10.1109/igarss.2017.8127092
Bradbury K, Saboo R, Johnson TL et al (2016) Distributed solar photovoltaic array location and extent dataset for remote sensing object identification. Sci Data 3:160106. https://doi.org/10.1038/sdata.2016.106
Golovko V et al (2017) Convolutional neural network based solar photovoltaic panel detection in satellite photos. In: Proceedings of the 9th IEEE international conference on intelligent data acquisition and advanced computing systems: technology and applications (IDAACS), Bucharest, Romania, pp 14–19. https://doi.org/10.1109/idaacs.2017.8094501
Golovko V et al (2018) Development of solar panels detector. In: Proceedings of the IEEE international scientific-practical conference problems of infocommunications. Science and technology (PIC S&T), Kharkiv, Ukraine, pp 761–764. https://doi.org/10.1109/infocommst.2018.8632132
Jonathan H (2018) mAP (mean average precision) for object detection. https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173. Accessed 12 Dec 2019
Acknowledgements
This work is performed under a grant by the Ministry of Education and Sciences, Ukraine, 2018–2019 as well as it’s supported by the Belarusian State Research Program “Informatics and Space”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Golovko, V., Kroshchanka, A., Mikhno, E., Komar, M., Sachenko, A. (2021). Deep Convolutional Neural Network for Detection of Solar Panels. In: Radivilova, T., Ageyev, D., Kryvinska, N. (eds) Data-Centric Business and Applications. Lecture Notes on Data Engineering and Communications Technologies, vol 48. Springer, Cham. https://doi.org/10.1007/978-3-030-43070-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-43070-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43069-6
Online ISBN: 978-3-030-43070-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)