Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Volume Measurement Method for Object on Pixel Area Basis through Depth Image

깊이 영상을 통한 화소 단위 물체 부피 측정 방법

  • 김지환 (동의대학교 컴퓨터소프트웨어공학과) ;
  • 권순각 (동의대학교 컴퓨터소프트웨어공학과)
  • Received : 2024.01.25
  • Accepted : 2024.01.29
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a volume measurement method for an object based on depth image. The object volume is measured by calculating the object height and width in actual units through the depth image. The object area is detected through differences between the captured and background depth images. The volume of the 2×2 pixel area, formed by four adjacent pixels using the depth information associated with each pixel, is measured. The object volume is measured as the sum of the volumes for whole 2×2 areas in the object area. In simulation results, the average measurement error for the object volume is 2.1% when the distance from the camera is 60cm.

본 논문에서는 깊이 카메라에 의해 촬영된 깊이 영상을 이용하여 객체의 부피를 측정하는 방법을 제안한다. 제안하는 방법은 깊이 정보를 활용하여 물체의 영역의 실제 거리 단위의 폭과 높이를 계산하여 물체의 부피를 측정한다. 배경 깊이 영상과 촬영된 깊이 영상에서 화소 값의 차이를 통해 영상을 이진화하여 물체 영역을 구한다. 이진화된 영상으로부터 검출된 물체 영역에 해당하는 화소의 3차원 좌표를 이용하여 실제 단위의 거리를 계산한다. 각 화소가 가지는 깊이 정보를 이용하여 인접한 4개의 화소로 이루어진 2×2화소 영역 사각형에 대한 부피를 계산한다. 모든 2×2화소 영역들에 대한 부피를 더하여 물체의 부피를 계산한다. 부피를 계산하였을 때 60cm의 측정거리에서 평균 2.1%의 오차가 측정된다.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부)의 재원으로 정보통신기획평과원의 지원을 받아 수행된 지역지능화혁신인재양성사업(IITP-2024-2020-0-01791, 90%)과 부산광역시 및 (재)부산테크노파크의 BB21plus 사업(10%)임.

References

  1. Andalo, F.A., Taubin, G., Goldenstein, G. (2015) Efficient height measurements in single images based on the detection of vanishing points, Comput. Vis. Image Underst. 138(5), 51-60, doi:10.1016/j.cviu.2015.03.017.
  2. Criminisi, A., Reid, I., Zisserman, A. (2000) Single view metrology. Int. J . Comput. Vis. 40(2), 123-148, doi:10.1007/978-0-85729-327-5_5.
  3. Chang, W., Wu, C., Tsai, Y., Chiu, W. (2017) Object volume estimation based on 3D point cloud. 2017 International Automatic Control Conference, DOI: 10.1109/CACS.2017.8284244.
  4. Cho, W., Shin, M., Jang, J., Paik, J. (2018) Robust pedestrian height estimation using principal component analysis and its application to automatic camera calibration. Proceedings of the International Conference on Electronics, Information, and Communication, Jan. 24-27, Honolulu, HI, pp. 1-2.
  5. Choi, E.S., Kwon, S.K. (2019) Implementation of Vehicle Plate Recognition Using Depth Camera, Journal of Multimedia Information System, 6(3), 119-124. https://doi.org/10.33851/JMIS.2019.6.3.119
  6. Chang, W., Chen, L., Nadia, Michael, L. (2023) 3D Surface Reconstruction with Polynomial Regression for Multistage Stamping Die using Depth Camera. IEEE 5th Eurasia Conference on IOT, Communication and Engineering, Oct. 27-29, Yunlin, Taiwan, DOI: 10.1109/ECICE59523.2023.10383079.
  7. Gallup, D., Frahm, J.M., Mordohai, P., Yang, Q., Pollefeys, Marc. (2007) Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions. IEEE Conference on Computer Vision and Pattern Recognition, June. 17-22, Minneapolis, MN, USA, DOI: 10.1109/CVPR.2007.383245.
  8. Hippocrate, E., Suwa, H., Arakawa, Y., Yasumoto, K. (2016) Food Weight Estimation Using Smartphone and Cutlery. Proceeding of the Annual International Conference on Mobile Systems, Applications, and Services, June. 25-30, Singapore.
  9. Jung, J., Kim, H., Yoon, I., Paik, J. (2016) Human height analysis using multiple uncalibrated cameras. Proceeding of the International Conference on Consumer Electronics, Jan. 7-11, Las Vegas, NV, pp. 213-214.
  10. Jia, W., Ren, Y., Li, B., Beatrice, B., Que, J., Cao, S., Wu, Z., Mao, Z.H., Lo, B., Anderson, A.K., Frost, G., McCrory, M.A., Sazonov, E., Steiner-Asiedu, M., Baranowski, T., Burke, L.E., Sun, M. (2022) A Novel Approach to Dining Bowl Reconstruction for Image-Based Food Volume Estimation. Sensors 2022, 22(4), 1493.
  11. Kim, H.J., Yoon, J.H., Kwon, S.K. (2023). Deep Learning Braille Block Recognition Method for Embedded Devices. Journal of Korea Society of Industrial Information Systems, 28(4), 1-9.
  12. Liu, J., Collins, R., Liu, Y. (2011) Surveillance camera auto calibration based on pedestrian height distributions. Proceeding of the British Machine Vision Conference, Dundee, Aug. 29, - Sep. 2, UK, pp. 1-11.
  13. Lee, D.S. Kwon, S.K., (2016) Improvement of Depth Video Coding by Plane Modeling, Journal of Korea Society of Industrial Information Systems, 21(5), 11-17.
  14. Lee, D.S. Kwon, S.K., (2019) Vehicle Plate Detection Method by Measuring Plane Similarity Using Depth Information, Journal of Korea Society of Industrial Information Systems, 24(2), 47-55.
  15. Liu, Y., Lai, J., Sun, W., Wei, Z., Liu, A., Gong, W., Yang, Y. (2020) Food Volume Estimation Based on Reference. The International Conference on Innovation in Artificial Intelligence, May. 8-11, Xiamen, China, pp. 84-89.
  16. Lee, D.S., Kwon, S.K. (2022). Intra Prediction Method by Quadric Surface Modeling for Depth Video. Journal of Korea Society of Industrial Information Systems, 27(2), 35-44.
  17. Lee, D.S., Kwon, S.K. (2023). Structure Recognition Method of Invoice Document Image for Document Processing Automation. Journal of Korea Society of Industrial Information Systems, 28(2), 11-19.
  18. Li J., Wu, M., Li, H. (2023) 3D Reconstruction and Volume Estimation of Jujube Using Consumer-Grade RGB-Depth Sensor IEEE Access Volume 11, DOI: 10.1109/ACCESS.2023.3285713.
  19. Okamoto, K., Yanai, K. (2016) An Automatic Calorie Estimation System of Food Images on A Smartphone. International Workshop on Multimedia Assisted Dietary Management, Oct. 16, Amsterdam, Netherlands, pp. 63-67.
  20. Pribyl, B., Zemcik, P. (2011) Simple single view scene calibration. Proceeding of the Lecture Notes in Computer Science, Aug. 22-25 Berlin Heidelberg, Heidelberg, Germany, pp. 748-759.
  21. Quintino, Ferreira, B., Grine, M., Gameiro, D., Costeira, J.P., Sousa Santos, B. (2014) VOLUMNECT: measuring volumes with Kinect Proceeding of the SPIE Volume 9013, DOI:10.1117/12.2036493.
  22. Rother, D., Patwardhan K.A., Sapiro, G. (2007) What can casual walkers tell us about a 3d scene?. Proceeding of the International Conference on Computer Vision, Oct. 14-21, Rio de Janeiro, Brazil, pp. 1-8.
  23. Schonberger, J.L., Zheng, E., Frahm, J., Pollefeys, M. (2016) Pixelwise View Selection for Unstructured Multi-View Stereo. Proceeding of the 14th European Conference on Computer Vision, Oct. 11-14, Amsterdam, Netherlands, pp. 501-518.
  24. Tushar, J., Kulbir, S., Aditya, A. (2019) Volumetric estimation using 3D reconstruction method for grading of fruits. Multimed Tools Appl 78, June. 28, DOI:https://doi.org/10.1007/s11042-018-6271-3.
  25. Viswanath, P., Kakadiaris, I.A., Shah, S.K. (2009) A simplified error model for height estimation using a single camera. Proceeding of the International Conference on Computer Vision, Sep. 29, - Oct. 2, Kyoto, Japan, pp. 1259-1266.