Segmentation to Detect the Presence of Human during Natural Disasters

Chethana H. T*, Pooja C. A**, P. Vamshika***
*-*** Department of Computer Science and Engineering, Vidyavardhaka College of Engineering, Mysuru, Karnataka, India.
Periodicity:July - September'2019
DOI : https://doi.org/10.26634/jdp.7.3.16934

Abstract

Nowadays, object detection is widely used for various purposes. There is a need for detecting living objects so that various problems like humans getting stuck in an undesirable place, and to find the suspected objects out of a group of other objects. Image segmentation is a process of dividing a digital picture into many segments, which helps in getting meaningful and well analyzed data that can be used in obtaining a well-defined output. Detection of living beings during the natural disasters is the most challenging task. Our proposed system makes use of You Only Look Once (YOLOv3), the quickest and most accurate among object detection system. During natural disasters, objects/living beings are detected using YOLOv3 model and the same information will be sent to the rescue team so that lives of human beings will be saved quickly and effectively.

Keywords

Convolutional Neural Network, Mask-RCNN, Image Segmentation, Feature MAP, Object Detection.

How to Cite this Article?

Chethana, H. T., Pooja, C. A., and Vamshika, P. (2019). Segmentation to Detect the Presence of Human during Natural Disasters. i-manager’s Journal on Digital Signal Processing. 7(3), 21-26. https://doi.org/10.26634/jdp.7.3.16934

References

[1]. Arasanipalai, A. U. (2018). State of the art deep learning: An introduction to Mask R-CNN. University of Illinois, Urbana-Champaign, Urbana, IL. https:// www.freecodecamp.org/news/mask-r-cnn-explained- 7f82bec890e3/
[2]. Baumgart, I., & Mies, S. (2007, December). S/kademlia: A practicable approach towards secure keybased routing. In 2007 International Conference on Parallel and Distributed Systems (pp. 1-8). IEEE. https://doi. org/10.1109/ICPADS.2007.4447808
[3]. Common Objects in Context. (n.d.). SE(3) Computer Vision Group, Cornell Tech. https://vision.cornell.edu/ se3/projects/microsoft-coco/
[4]. Gulli, A., & Pal, S. (2017). Deep Learning with Keras. Packt Publishing Ltd.
[5]. Keras Documentation. (n.d.). The Sequential Model. Retrived from https://keras.io/getting-started/sequentialmodel.
[6]. Patel, P., Bhatt, B., & Patel, B. (2017, February). Human body posture recognition—A survey. In 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) (pp. 473-477). IEEE. https://doi. org/10.1109/ICIMIA.2017.7975660
[7]. Pooja, C. A., Vamshika, P., Jain, R. B., Jain, V. K., & Chethana, H. T. (2018, December). Comprehensive survey on detection of living or dead humans and Animals using different approaches. In International Conference on Computer Networks, Big Data and IoT (pp. 94-100). Springer, Cham. https://doi.org/10.1007/978-3-030-24643- 3_10
[8]. Rosenberg, J. (2010). {i}Interactive connectivity establishment (ICE): A protocol for network address translator (NAT) traversal for offer/answer protocols {i}, Internet Engineering Task Force (IETF), RCF 5245. Retrieved from https://www.hjp.at/doc/rfc/rfc5245.html
[9]. Tensor Flow. (n.d.). Object detection. Retrived fromhttps://www.tensor flow.org/lite/models/object_ detection/overview
[10]. Tutorials Point. (n.d.). System Analysis and Design - Overview. Retrived from https://www.tutorialspoint.com/ system_analysis_and_design/system_analysis_and_ design_overview.htm
[11]. Valchanov, I. (2018). False positive and false negative. Towards Data Science. Retrived from https://towardsdata science.com/false-positive-and-falsenegative- b29df2c60aca
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.