이동감시 플랫폼을 위한 픽셀 및 GPS 데이터 기반 경량의 실시간 객체추적 알고리즘

다국어 초록 (Multilingual Abstract)

This study proposed a method for detecting moving objects (e.g., people and vehicles) in the images of a lightweight mobile platform, and for the real-time visualization and tracking of the location information on the screen. First, a lightweight cable-driven platform and remote access environment were configured for the experiment. Next, a TensorFlow Lite environment was configured in the control computer, and an object detection algorithm was applied to the images obtained from the camera on the cable-driven platform. Subsequently, the bounding box coordinates of the object and class information were used as the inputs, as well as the camera specifications, GPS information, and the actual size information of the object to estimate the coordinates of the object. However, the significant limitations in the performance of CPU, GPU, and memory restrict the applications of high-performance deep learning models in a mobile platform environment. Therefore, in this study, a lightweight model, such as MobileNet SSD v2 was applied, and Google Edge TPU, which can use TensorFlow Lite environment, was used to facilitate computations, such as real-time object detection and coordinate estimation. In addition, this study presented a method for assigning a unique ID to a detected object and tracking it using the Euclidean distance, and the advantages of a simple algorithm using GPS data and a single moving camera in the surveillance field were presented.

목차 (Table of Contents)

• Abstract
• I. 서론
• II. 실험환경 구성
• III. 객체탐지 알고리즘
• IV. 위치추정 알고리즘
• V. 결론 및 추후 과제
• REFERENCES

참고문헌 (Reference)

1 김상현, "무인 공중 감시 체계를 위한 이동하는 표적 추적 및 식별 기법" 제어·로봇·시스템학회 23 (23): 157-164, 2017

2 박상배, "도심지 자율주행을 위한 머신러닝 기반의 실시간 다 객체 인식 방법" 제어·로봇·시스템학회 26 (26): 499-505, 2020

3 성택영, "단일 카메라와 GPS를 이용한 영상 내객체 위치 좌표 추정 기법" 한국멀티미디어학회 19 (19): 112-121, 2016

4 "https://www.nars.go.kr/fileDownload2.do?doc_id=1Mu3AHX XtCE&fileName="

5 J. Redmon, "You only look once: Unified, real-time object detection" 779-788, 2016

6 J. Redmon, "Yolov3: An incremental improvement"

7 W. Liu, "Ssd: Single shot multibox detector" Springer 21-37, 2016

8 Y. Zhang, "Robust moving object detection at distance in the visible spectrum and beyond using a moving camera" 131-131, 2006

9 R. Girshick, "Rich feature hierarchies for accurate object detection and semantic segmentation" 580-587, 2014

10 B. Jacob, "Quantization and training of neural networks for efficient integer-arithmeticonly inference" 2018

11 Yilmaz, Alper, "Object tracking: A survey" 38 (38): 13-, 2006

12 T. Brox, "Object segmentation by long term analysis of point trajectories" Springer 282-295, 2010

13 M. Yazdi, "New trends on moving object detection in video images captured by a moving camera: A survey" 28 : 157-177, 2018

14 M. Sandler, "Mobilenetv2: Inverted residuals and linear bottlenecks" 2018

15 A. G. Howard, "Mobilenets: Efficient convolutional neural networks for mobile vision applications"

16 Z. Zivkovic, "Improved adaptive gaussian mixture model for background subtraction" 28-31, 2004

17 J. Sengupta, "High-speed, real-time, spike-based object tracking and path prediction on Google Edge TPU" 2020

18 "Google Edge TPU"

19 S. Kwak, "Generalized background subtraction based on hybrid inference by belief propagation and bayesian filtering" 2174-2181, 2011

20 P. Pascal, "Evaluation of deep learning accelerators for object detection at the edge" Springer 2020

21 D. -S. Lee, "Effective gaussian mixture learning for video background subtraction" 27 (27): 827-832, 2005

22 T. Ainsworth, "Buyer beware" 19 : 18-26, 2002

23 Alasdair Allan, "Benchmarking Machine Learning on the New Raspberry Pi 4"

24 Y. Sheikh, "Background subtraction for freely moving cameras" 1219-1225, 2009

25 Xiaoqing Yin, "Background Subtraction for Moving Cameras based on trajectory-controlled segmentation and Label Inference" 한국인터넷정보학회 9 (9): 4092-4107, 2015

26 N. Dadashi, "Automatic surveillance and CCTV operator workload" School of Computer Science University of Nottingham 2008

27 김호연, "AI 딥러닝을 이용한 싸움(다툼) 행동 인식 방법" 제어·로봇·시스템학회 27 (27): 482-489, 2021

28 I. Haritaoglu, "A fast background scene modeling and maintenance for outdoor surveillance" 4 : 179-183, 2000