Skip to main content
Top

2021 | OriginalPaper | Chapter

Road Segmentation from Satellite Images Using Custom DNN

Authors : Harshal Trivedi, Dhrumil Sheth, Ritu Barot, Rainam Shah

Published in: Proceedings of Second International Conference on Computing, Communications, and Cyber-Security

Publisher: Springer Singapore

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Recently, with the enhancement in the field of remote sensing and computation techniques, road detection from satellite images is getting possible. In these days, precise extraction of the lane from satellite images has become one of the major important fields of research in both remote sensing and transportation. The road network performs an imperative role in the traffic system, urban planning, route planning, and self-driving. In this paper, technique for road segmentation from the satellite images has been introduced. In the proposed method, a custom deep neural network (DNN) has been used for the detection of the road from satellite images. We have used a simple and custom neural network which is computationally faster and as accurate as a traditional deep neural network like Inception, YOLO, and ResNet-50 for road detection in the satellite images. In the initial stage, images are preprocessed with the help of OpenCV and morphology. We have annotated each pixel value as 0 for non-lane pixels and 1 for lane pixels. With this annotated data, we have trained our custom DNN model. The road region is denoted by white pixels, and black pixel denotes a non-road region. In the final result, the noise removal technique is used to remove distorted white pixels to improve the accuracy further.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Pannu A (2015) Artificial intelligence and its application in different areas. Artif Intell 4(10):79–84 Pannu A (2015) Artificial intelligence and its application in different areas. Artif Intell 4(10):79–84
2.
go back to reference Jiang Y (2019) Research on road extraction of remote sensing image based on convolutional neural network. EURASIP J Image Video Process 2019(1):31CrossRef Jiang Y (2019) Research on road extraction of remote sensing image based on convolutional neural network. EURASIP J Image Video Process 2019(1):31CrossRef
3.
go back to reference Xia W et al (2018) Road extraction from high resolution image with deep convolution network—a case study of GF-2 image. Multi Dig Publishing Inst Proc 2(7) Xia W et al (2018) Road extraction from high resolution image with deep convolution network—a case study of GF-2 image. Multi Dig Publishing Inst Proc 2(7)
4.
go back to reference Henry C, Azimi SM, Merkle N (2018) Road segmentation in SAR satellite images with deep fully convolutional neural networks. IEEE Geosci Rem Sens Lett 15(12):1867–1871 Henry C, Azimi SM, Merkle N (2018) Road segmentation in SAR satellite images with deep fully convolutional neural networks. IEEE Geosci Rem Sens Lett 15(12):1867–1871
5.
go back to reference Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
6.
go back to reference Yao W, Marmanis D, Datcu M (2017) Semantic segmentation using deep neural networks for SAR and optical image pairs. 1–4 Yao W, Marmanis D, Datcu M (2017) Semantic segmentation using deep neural networks for SAR and optical image pairs. 1–4
7.
go back to reference Kumar A, Srivastava S (2020) Object detection system based on convolution neural networks using single shot multi-box detector. Procedia Comput Sci 171:2610–2617CrossRef Kumar A, Srivastava S (2020) Object detection system based on convolution neural networks using single shot multi-box detector. Procedia Comput Sci 171:2610–2617CrossRef
8.
go back to reference Kumar A, Reddy SSSS, Kulkarni V (2019) An object detection technique for blind people in real-time using deep neural network. In: 2019 fifth international conference on image information processing (ICIIP). IEEE Kumar A, Reddy SSSS, Kulkarni V (2019) An object detection technique for blind people in real-time using deep neural network. In: 2019 fifth international conference on image information processing (ICIIP). IEEE
9.
go back to reference Sandeep Reddy D, Padmaja M (2016) Extraction of roads from high resolution satellite images by means of adaptive global thresholding and morphological operations. Int J Sci Eng Res 7(10) Sandeep Reddy D, Padmaja M (2016) Extraction of roads from high resolution satellite images by means of adaptive global thresholding and morphological operations. Int J Sci Eng Res 7(10)
10.
go back to reference Yadav P, Agrawal S (2018) Road network identification and extraction in satellite imagery using Otsu’s method and connected component analysis. Int Arch Photogrammetry Rem Sens Spat Inform Sci Yadav P, Agrawal S (2018) Road network identification and extraction in satellite imagery using Otsu’s method and connected component analysis. Int Arch Photogrammetry Rem Sens Spat Inform Sci
11.
go back to reference Wang W et al (2016) A review of road extraction from remote sensing images. J Traffic Transp Eng (English edition) 3(3):271–282 Wang W et al (2016) A review of road extraction from remote sensing images. J Traffic Transp Eng (English edition) 3(3):271–282
12.
go back to reference Xu Y et al (2018) Road extraction from high-resolution remote sensing imagery using deep learning. Rem Sens 10(9):1461 Xu Y et al (2018) Road extraction from high-resolution remote sensing imagery using deep learning. Rem Sens 10(9):1461
13.
go back to reference Mnih V, Hinton GE (2010) Learning to detect roads in high-resolution aerial images. In: Daniilidis K, Maragos P, Paragios N (eds) Computer vision ECCV 2010. Number 6316 in lecture notes in computer science. Springer, Berlin/Heidelberg, Germany, pp 210–223 Mnih V, Hinton GE (2010) Learning to detect roads in high-resolution aerial images. In: Daniilidis K, Maragos P, Paragios N (eds) Computer vision ECCV 2010. Number 6316 in lecture notes in computer science. Springer, Berlin/Heidelberg, Germany, pp 210–223
14.
go back to reference Alex DM, Bindu KR, Reemamol PK (2013) Resolution enhancement and roadextraction for urban and sub-urban management. Int J Sci Eng Res 4(8):1640. ISSN 2229-5518 Alex DM, Bindu KR, Reemamol PK (2013) Resolution enhancement and roadextraction for urban and sub-urban management. Int J Sci Eng Res 4(8):1640. ISSN 2229-5518
15.
go back to reference Buslaev A et al (2018) Fully convolutional network for automatic road extraction from satellite imagery. In: CVPR Workshops Buslaev A et al (2018) Fully convolutional network for automatic road extraction from satellite imagery. In: CVPR Workshops
16.
go back to reference Liu X, Deng Z (2018) Segmentation of drivable road using deep fully convolutional residual network with pyramid pooling. Cogn Comput Springer 10(2):272–281MathSciNetCrossRef Liu X, Deng Z (2018) Segmentation of drivable road using deep fully convolutional residual network with pyramid pooling. Cogn Comput Springer 10(2):272–281MathSciNetCrossRef
17.
go back to reference Khryashchev V, Ivanovsky L, Pavlov V, Ostrovskaya A, Rubtsov A (2018) Comparison of different convolutional neural network architectures for satellite image segmentation. In: 2018 23rd conference of open innovations association (FRUCT), 13 November 2018. IEEE, pp 172–179 Khryashchev V, Ivanovsky L, Pavlov V, Ostrovskaya A, Rubtsov A (2018) Comparison of different convolutional neural network architectures for satellite image segmentation. In: 2018 23rd conference of open innovations association (FRUCT), 13 November 2018. IEEE, pp 172–179
18.
go back to reference Wei Y, Zhang K, Ji S (2019) Road network extraction from satellite images using CNN based segmentation and tracing. In: IGARSS 2019-2019 IEEE international geoscience and remote sensing symposium. 28 July 2019. IEEE, pp 3923-3926 Wei Y, Zhang K, Ji S (2019) Road network extraction from satellite images using CNN based segmentation and tracing. In: IGARSS 2019-2019 IEEE international geoscience and remote sensing symposium. 28 July 2019. IEEE, pp 3923-3926
19.
go back to reference Fan R et al (2019) PT-ResNet: perspective transformation-based residual network for semantic road image segmentation. arXiv preprint arXiv:1910.13055 Fan R et al (2019) PT-ResNet: perspective transformation-based residual network for semantic road image segmentation. arXiv preprint arXiv:​1910.​13055
20.
go back to reference Kim J, Kim J, Cho J (2019) An advanced object classification strategy using YOLO through camera and LiDAR sensor fusion. In: 2019 13th international conference on signal processing and communication systems (ICSPCS). IEEE Kim J, Kim J, Cho J (2019) An advanced object classification strategy using YOLO through camera and LiDAR sensor fusion. In: 2019 13th international conference on signal processing and communication systems (ICSPCS). IEEE
21.
go back to reference Sun Z et al (2020) Exploiting deeply supervised inception networks for automatically detecting traffic congestion on freeway in china using ultra-low frame rate videos. IEEE Access 8:21226-21235 Sun Z et al (2020) Exploiting deeply supervised inception networks for automatically detecting traffic congestion on freeway in china using ultra-low frame rate videos. IEEE Access 8:21226-21235
22.
go back to reference Fatima SA et al (2020) Object recognition and detection in remote sensing images: a comparative study. In: 2020 international conference on artificial intelligence and signal processing (AISP). IEEE Fatima SA et al (2020) Object recognition and detection in remote sensing images: a comparative study. In: 2020 international conference on artificial intelligence and signal processing (AISP). IEEE
23.
go back to reference Bhardwaj N, Kaur G, Singh PK (2018) A systematic review on image enhancement techniques. In: Sensors and Image Processing. Springer, Singapore, pp 227-235 Bhardwaj N, Kaur G, Singh PK (2018) A systematic review on image enhancement techniques. In: Sensors and Image Processing. Springer, Singapore, pp 227-235
24.
go back to reference Chen Q et al (2018) Aerial imagery for roof segmentation: a large-scale dataset towards automatic mapping of buildings. arXiv preprint arXiv:1807.09532 Chen Q et al (2018) Aerial imagery for roof segmentation: a large-scale dataset towards automatic mapping of buildings. arXiv preprint arXiv:​1807.​09532
25.
go back to reference Tan L, Jiang J (2018) Digital signal processing: fundamentals and applications. Academic Press Tan L, Jiang J (2018) Digital signal processing: fundamentals and applications. Academic Press
Metadata
Title
Road Segmentation from Satellite Images Using Custom DNN
Authors
Harshal Trivedi
Dhrumil Sheth
Ritu Barot
Rainam Shah
Copyright Year
2021
Publisher
Springer Singapore
DOI
https://doi.org/10.1007/978-981-16-0733-2_66