Quantity Measurement by CAFFE Model and Distance and Width Measurement by Stereo Vision

CAFFE 모델을 이용한 수량 측정 및 스테레오 비전을 이용한 거리 및 너비측정

  • Received : 2019.07.21
  • Accepted : 2019.08.15
  • Published : 2019.08.31


We propose a method to measure the number of specific species of class using CAFFE model and a method to measure length and width of object using stereo vision. To obtain the width of an object, the location coordinates of objects appearing on the left and right sensor is compared and the distance from the sensor to the object is obtained. Then the length of the object in the image by using the distance and the approximate value of the actual length of the object is calculated.

KCTSAD_2019_v14n4_679_f0001.png 이미지

그림 1. 시스템 흐름도 Fig. 1 System flowchart

KCTSAD_2019_v14n4_679_f0002.png 이미지

그림 2. 수량 측정 흐름도 Fig. 2 Quantity measurement flowchart

KCTSAD_2019_v14n4_679_f0003.png 이미지

그림 3. 스테레오 비전 시스템 구상도 Fig. 3 Stereo vision system concept

KCTSAD_2019_v14n4_679_f0004.png 이미지

그림 4. 너비 및 거리 측정 도식화 Fig. 4 Schematic of width and distance measurement

KCTSAD_2019_v14n4_679_f0005.png 이미지

그림 5. 스테레오 비전 시스템 흐름도 Fig. 5 Stereo vision system flowchart

KCTSAD_2019_v14n4_679_f0006.png 이미지

그림 6. 실험 환경 Fig 6. Experiment environment

표 1. 장치 사양 Table. 1 Device Specifications

KCTSAD_2019_v14n4_679_t0001.png 이미지

표 2. 보정상수 계산 Table. 2 Calibration constant calculation

KCTSAD_2019_v14n4_679_t0002.png 이미지

표 3. 거리 및 너비측정 Table. 3 Measure distance and witdh

KCTSAD_2019_v14n4_679_t0003.png 이미지


Supported by : 한국산업기술진흥원


  1. J. Kim and E. Kim, "Design of Drone for Underwater Monitoring and Net Cleaning for Net Cleaning for Aquaculture Farm," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 6, 2018, pp. 1379-1386.
  2. N. Kugou, Y. Chio, D. Lee, T. Kim, and Y. Kim, "A Study on the Development of a Fish Measuring System," J. Institute Control, Robotics and Systems, vol. 2018, no. 5, 2018, pp. 281-282.
  3. J. Kim, "An Efficient Algorithm for 3-D Range Measurement using Disparity of Stereoscopic Camera," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 6, 2001, pp. 1163-1168.
  4. G. Jang and J. Park, "Visual Object Recognition Based On Deep Neural Networks Implemented by CAFFE," Communications of Korean Institute of Information Scientists and Engineer vol. 33, no. 8, 2015, pp. 49-54
  5. S. Yang and J. Beak, "Distance Detection between Vehicles using Stereo Vision," J. Korea Navigation Institute, vol. 6, no. 1, 2002, pp. 27-36.
  6. S. Yoon, "Distance and Speed Measurements of Moving Object Using Difference Image in Stereo Vision System," J. Natural Science in Pyongtaek University, vol. 12, no. 6, 2006, pp. 37-55.
  7. W. Son and E. Kim, "A Distance and Width Measurement System Using Stereo Vision Sensors," J. of the of the Korea Institute of Electronic Communication Sciences, Busan, South Korea, 2019.
  8. Liu, Wei , Anguelov, Dragomir , Erhan, Dumitru , Szegedy, Christian , Reed, Scott , Fu, Cheng-Yang and Berg, Alexander C. "SSD: Single Shot MultiBox Detector," Lecture Notes in Computer Science, vol. 2016. no. 9905, 2016, pp. 21-37.
  9. K. Kim, S. Han, and J. Park, "A Distortion Correction Method of Wide-Angle Camera Images through the Estimation and Validation of a Camera Model," J. of the Korea Institute of Electronic Communication Sciences, vol. 8. no. 12, 2013, pp. 1923-1932262-268.
  10. H. Seo and W. Yim, "A Compensation for Distortion of Stereo-scopic Camera Image Using Neuro-Fuzzy Inference System," J. of the Korea Institute of Electronic Communication Sciences, vol. 5. no. 3, 2010, pp. 262-268
  11. D. Lee, D. Lee, S. Kim, T. Kim, and J. Yoo, "Real-time moving object tracking and distance measurement system using stereo camera," J. Broadcast Engineering, vol. 14, no. 3, 2009, pp. 366-377.