실내 환경에서 Chirp Emission과 Echo Signal을 이용한 심층신경망 기반 객체 감지 기법 = DECODE: A Novel Method of DEep CNN-based Object DEtection using Chirps Emission and Echo Signals in Indoor Environment

다국어 초록 (Multilingual Abstract)

Humans mainly recognize surrounding objects using visual and auditory information among the five senses (sight, hearing, smell, touch, taste). Major research related to the latest object recognition mainly focuses on analysis using image sensor information. In this paper, after emitting various chirp audio signals into the observation space, collecting echoes through a 2-channel receiving sensor, converting them into spectral images, an object recognition experiment in 3D space was conducted using an image learning algorithm based on deep learning. Through this experiment, the experiment was conducted in a situation where there is noise and echo generated in a general indoor environment, not in the ideal condition of an anechoic room, and the object recognition through echo was able to estimate the position of the object with 83% accuracy. In addition, it was possible to obtain visual information through sound through learning of 3D sound by mapping the inference result to the observation space and the 3D sound spatial signal and outputting it as sound. This means that the use of various echo information along with image information is required for object recognition research, and it is thought that this technology can be used for augmented reality through 3D sound.

참고문헌 (Reference)

1 조영준, "딥러닝 모델을 이용한 비전이미지 내의 대상체 분류에 관한 연구" 한국산학기술학회 22 (22): 20-25, 2021

2 J. Redmon, "You Only Look Once: Unified, Real-Time Object Detection" 779-788, 2016

3 Santani Teng, "Ultrafine spatial acuity of blind expert human echolocators" 216 : 483-488, 2012

4 D. M. Gavrila, "Real-time object detection for "smart" vehicles" 1 : 87-93, 1999

5 Nenad GUCUNSKI, "Rapid Bridge Deck Condition Assessment Using Three Dimensional Visualization of Impact Echo Data" 2009

6 김진수, "RGB 영상 및 LiDAR 포인트 클라우드 합성을 통한 YOLO 기반 실시간 객체 탐지" 한국정보기술학회 17 (17): 93-105, 2019

7 M. F. Haque, "Object Detection Based on VGG with ResNet Network" 1-3, 2019

8 R. Mur-Artal, "ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras" 33 (33): 1255-1262, 2017

9 J. N. Kutz, "Multi-resolution Dynamic Mode Decomposition for Foreground/Background Separation and Object Tracking" 921-929, 2015

10 Li Wang, "Multi-Channel Convolutional Neural Network Based 3D Object Detection for Indoor Robot Environmental Perception" MDPI AG 19 (19): 893-, 2019

11 J. Zhang, "Local Deep-Feature Alignment for Unsupervised Dimension Reduction" 27 (27): 2420-2432, 2018

12 A. Mandal, "Beep: 3D indoor positioning using audible sound" 348-353, 2005

13 J. H. Christensen, "BatVision: Learning to See 3D Spatial Layout with Two Ears" 1581-1587, 2020

14 M. M. MOORE JACKSON, "Analyzing Trends in Brain Interface Technology: A Method to Compare Studies" 34 (34): 859-878, 2006

15 R. A. Jarvis, "A Perspective on Range Finding Techniques for Computer Vision" PAMI-5 (PAMI-5): 122-139, 1983

16 Yangyang Guo, "A Machine Vision-Based Method for Monitoring Scene-Interactive Behaviors of Dairy Calf" MDPI AG 10 (10): 190-, 2020

17 Y. Lian, "A Dense Pointnet++Architecture for 3D Point Cloud Semantic Segmentation" 5061-5064, 2019