Project Vulture: A Prototype for Using Drones in Search and Rescue Operations

被引：20
作者：
Quan, Andres [1 ]
Herrmann, Charles [1 ]
Soliman, Hamdy [1 ]
机构：
[1] New Mexico Inst Min & Technol, Comp Sci, Socorro, NM 87801 USA
来源：
2019 15TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING IN SENSOR SYSTEMS (DCOSS) | 2019年
关键词：
Machine Learning; Neural Networks; Drone Imagery; Localization; Search and Rescue; YOLO; Object Detection;
D O I：
10.1109/DCOSS.2019.00113
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Unmanned Aircraft Systems (UAS/Drones) are great resources for search and rescue (SAR) operations as they allow for remote examination of vast areas. This paper presents a smart human subject localization system called Project Vulture. Our system utilizes a trained deep learning model to speed up the analysis of obtained drone aerial images for scalable and distributed operations. Given that SAR deals with human lives, our localization model focuses on obtaining higher sensitivity than existing peer models. In this situation, we accept the possibility of a higher false positive rate. Our obtained results are promising and encourage continued research in this field.
引用
收藏
页码：619 / 624
页数：6
相关论文
共 19 条
  • [1] [Anonymous], FLIR DUO PRO R HD DU
  • [2] [Anonymous], MACHINE LEARNING APP
  • [3] [Anonymous], CERT REM PIL INCL CO
  • [4] [Anonymous], EVALUATING IMPACT DR
  • [5] [Anonymous], ADV NEURAL INFORM PR, DOI DOI 10.1109/TPAMI.2016.2577031
  • [6] [Anonymous], 2016, EUR S ART NEUR NETW
  • [7] [Anonymous], SCALE INVARIANT CONV
  • [8] [Anonymous], IMPACT BIASES BIG DA
  • [9] [Anonymous], GEFORCE GTX 1080TI G
  • [10] A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery
    Bejiga, Mesay Belete
    Zeggada, Abdallah
    Nouffidj, Abdelhamid
    Melgani, Farid
    [J]. REMOTE SENSING, 2017, 9 (02)
12