All Issue

2019 Vol.28, Issue 4 Preview Page
Estimation of the Dimensions of Horticultural Products and the Mean Plant Height of Plug Seedlings Using Three-Dimensional Images

3차원 영상을 이용한 원예산물의 크기와 플러그묘의 평균초장 추정

Dong Hwa Jang1
,
Hyeon Tae Kim2
,
Yong Hyeon Kim34
장 동화1
,
김 현태2
,
김 용현34
1Dept. of Agricultural Machinery Engineering, Graduate School, Jeonbuk National University, Jeonju 54896, Korea
2Dept. of Biosystems Engineering, College of Agriculture & Life Sciences, Gyeongsang National University (Institute of Agriculture & Life Science), Jinju 52828, Korea
3Dept. of Bioindustrial Machinery Engineering, College of Agriculture & Life Sciences, Jeonbuk National University, Jeonju 54896, Korea
4Institute for Agricultural Machinery & ICT Convergence, Jeonbuk National University, Jeonju 54896, Korea
1전북대학교 대학원 농업기계공학과
2경상대학교 농업생명과학대학 바이오시스템공학과
3전북대학교 농업생명과학대학 생물산업기계공학과
4전북대학교 농업기계ICT융합연구소
*Corresponding author: yhkim@jbnu.ac.kr
30 November 2019. pp. 358-365
PDF XML Citation
Abstract

This study was conducted to estimate the dimensions of horticultural products and the mean plant height of plug seedlings using three-dimensional (3D) images. Two types of camera, a ToF camera and a stereo-vision camera, were used to acquire 3D images for horticultural products and plug seedlings. The errors calculated from the ToF images for dimensions of horticultural products and mean height of plug seedlings were lower than those predicted from stereo-vision images. A new indicator was defined for determining the mean plant height of plug seedlings. Except for watermelon with tap, the errors of circumference and height of horticultural products were 0.0-3.0% and 0.0-4.7%, respectively. Also, the error of mean plant height for plug seedlings was 0.0-5.5%. The results revealed that 3D images can be utilized to estimate accurately the dimensions of horticultural products and the plant height of plug seedlings. Moreover, our method is potentially applicable for segmenting objects and for removing outliers from the point cloud data based on the 3D images of horticultural crops.

Keywords
3D sensor
depth information
stereo vision
ToF camera

본 연구는 3차원 영상을 이용하여 원예산물의 크기와 플러그묘의 평균초장을 결정하고자 수행되었다. 3차원 영 상을 획득하고자 ToF 카메라와 스테레오비전 카메라를 사 용하였다. 본 연구의 3차원 영상 획득용 실험 재료로서 수 박, 사과, 배, 단호박, 오렌지의 원예산물과 수박, 토마토 및 고추 플러그묘를 사용하였다. 플러그묘의 평균 초장을 결정하는 지표로서 기존의 측정 기준 대신에 수정초장이 제시되었다. 스테레오비전 영상에 비해서 ToF 영상을 이 용한 경우에 원예산물의 크기와 플러그묘의 평균초장 오 차가 작게 나타났다. 꼭지가 있는 원예산물을 제외할 경우 ToF 영상을 이용한 원예산물의 둘레와 높이의 오차는 각 각 0.0-3.0%, 0.0-4.7%로 나타났다. 또한, 플러그묘의 평균 초장에 대한 오차는 0.0-5.5%로 나타났다. 본 연구를 통해 서 3차원 영상을 이용한 원예산물의 크기와 플러그묘에 대한 초장 추정의 가능성을 확인하였다. 더구나, 본 연구 에서 시도된 방법은 3차원 영상으로부터 물체와 배경의 효과적인 분리, 이상치의 제거 등에 활용될 것이다.

키워드
깊이 정보
3차원 센서
스테레오비전
ToF 카메라
References
1
Bassel, G.W. 2015. Accuracy in quantitative 3D image analysis. Plant Cell 27:950-953. 10.1105/tpc.114.135061 25804539PMC4558689
10.1105/tpc.114.13506125804539PMC4558689
2
Besl, P.J. 1988. Active, optical range imaging Sensors. Mach. Vis. Appl. 1:127-152. 10.1007/978-1-4612-4532-2_1
10.1007/BF01212277
3
Edan, Y., S. Han, and N. Kondo. 2009. Automation in agriculture. p. 1095-1128. In: Nof, S.Y. (ed.), Handbook of automation. Springer, New York, NY. 10.1007/978-3-540-78831-7_63
10.1007/978-3-540-78831-7_63
4
Gélard, W., A. Herbulot, M. Devy, P. Debaeke, R.F. McCormick, S.K. Truong, and J. Mullet. 2017. Leaves segmentation in 3D point cloud. p. 664-674. In: Blanc-Talon, J., R. Penne, W. Philips, D. Popescu, and P. Scheunders (eds.), Advanced concepts for intelligent vision systems. Springer, New York, NY. 10.1007/978-3-319-70353-4_56
10.1007/978-3-319-70353-4_56
5
Grift, T. 2008. A review of automation and robotics for the bioindustry. J. Biomechatron. Eng. 1:37-54.
6
Kim, Y.H 2000. Application of biotechnology in the field of agricultural machinery engineering - Development of closed system for transplant production. J. of the Korean Society for Agricultural Machinery 25:311-326 (in Korean).
7
Kise, M., Q. Zhang, F. Rovira Más. 2005. A stereovisionbased crop row detection method for tractor-automated guidance. Biosyst. Eng. 90:357-367. 10.1016/j.biosystemseng.2004.12.008
10.1016/j.biosystemseng.2004.12.008
8
Lee, J.S., H.I. Lee, and Y.H. Kim. 2012. Seedling quality and early yield after transplanting of paprika nursed under lightemitting diodes, fluorescent lamps and natural light. J. of Bio-Environment Control 21:220-227 (in Korean).
9
Li, D., Y. Cao, X. Tang, S. Yan, and X. Cai. 2018. Leaf segmentation on dense plant point clouds with facet region growing. Sensors 18:3625-3640. 10.3390/s18113625 30366434PMC6263610
10.3390/s1811362530366434PMC6263610
10
Ma, Y., S. Soatto, J. Kosecka, and S. Sastry. 2004. Representation of a three-dimensional moving scene. p. 15-43. In: An invitation to 3-D vision: From images to geometric models. Springer, New York, NY. 10.1007/978-0-387-21779-6_2
10.1007/978-0-387-21779-6_2
11
Markovic, V., M. Djurovka, Z. Ilin, and B. Lazic. 2000. Effect of seeding quality on yield characters of plant and fruits of sweet pepper. Acta Horticulturae 533:113-120. 10.17660/ActaHortic.2000.533.12
10.17660/ActaHortic.2000.533.12
12
Nakarmi, A. and L. Tang. 2012. Automatic inter-plant spacing sensing at early growth stages using a 3D vision sensor. Comput. Electron. Agric. 82:23-31. 10.1016/j.compag.2011.12.011
10.1016/j.compag.2011.12.011
13
Nissimov, S., J. Goldberger, and V. Alchanatis. 2015. Obstacle detection in a greenhouse environment using the Kinect sensor. Comput. Electron. Agric. 113:104-115. 10.1016/j.compag.2015.02.001
10.1016/j.compag.2015.02.001
14
Rusu, R.B., Z.C. Marton, N. Blodow, M. Dolha, and M. Beetz. 2008. Towards 3D point cloud based object maps for household environments. Robot. Auton. Syst. 56:927-941. 10.1016/j.robot.2008.08.005
10.1016/j.robot.2008.08.005
15
Templin, K., P. Didyk, T. Ritschel, K. Myszkowski, and H.P. Seidel. 2012. Highlight microdisparity for improved gloss depiction. ACM T. Graphic. 31(4):1-5. 10.1145/2185520.2185588
10.1145/2185520.2185588
16
Thilakarathne, B.L.S., U.M. Rajagopalan, H. Kadono, and T. Yonekura. 2014. An optical interferometric technique for assessing ozone induced damage and recovery under cumulative exposures for a Japanese rice cultivar. Springerplus 3:89-100.10.1186/2193-1801-3-89 24570855PMC3932158
10.1186/2193-1801-3-8924570855PMC3932158
17
Vázquez-Arellano, M., H.W. Griepentrog, D. Reiser, and D.S. Paraforos. 2016. 3-D imaging systems for agricultural applications-A review. Sensors 16:618-641. 10.3390/s16050618 27136560PMC4883309
10.3390/s1605061827136560PMC4883309
18
Viazzi, S., C. Bahr, T. van Hertem, A. Schlageter-Tello, C.E.B. Romanini, I. Halachmi, C. Lokhorst, and D. Berckmans. 2014. Comparison of a three-dimensional and two-dimensional camera system for automated measurement of back posture in dairy cows. Comput. Electron. Agric. 100:139-147. 10.1016/j.compag.2013.11.005
10.1016/j.compag.2013.11.005
19
Wei, J., J.F. Reid, and S. Han. 2005. Obstacle detection using stereo vision to enhance safety of autonomous machines.Trans. Am. Soc. Agric. Eng. 48:2389-2397. 10.13031/2013.20078
10.13031/2013.20078
20
Yin, X., N. Noguchi, and J. Choi. 2013. Development of a target recognition and following system for a field robot. Comput. Electron. Agric. 98:17-24. 10.1016/j.compag.2013.07.005
10.1016/j.compag.2013.07.005
21
Zhao, Y., Y. Sun, X. Cai, H. Liu, and P.S. Lammers. 2012. Identify plant drought stress by 3D-based image. J. Integr. Agric. 11:1207-1211. 10.1016/S2095-3119(12)60116-6
10.1016/S2095-3119(12)60116-6
22
농업과학기술 연구조사분석기준. 2012. 농촌진흥청.
Information
  • Publisher :The Korean Society for Bio-Environment Control
  • Publisher(Ko) :(사)한국생물환경조절학회
  • Journal Title :Protected Horticulture and Plant Factory
  • Journal Title(Ko) :시설원예ㆍ식물공장
  • Volume : 28
  • No :4
  • Pages :358-365
  • Received Date : 2019-08-22
  • Revised Date : 2019-09-18
  • Accepted Date : 2019-10-01
  • DOI :https://doi.org/10.12791/KSBEC.2019.28.4.358
Journal Informaiton Journal of Bio-Environment Control Journal of Bio-Environment Control
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close