Skip to main content
Log in

Applied machine vision of plants: a review with implications for field deployment in automated farming operations

Intelligent Service Robotics Aims and scope Submit manuscript

Abstract

Automated visual assessment of plant condition, specifically foliage wilting, reflectance and growth parameters, using machine vision has potential use as input for real-time variable-rate irrigation and fertigation systems in precision agriculture. This paper reviews the research literature for both outdoor and indoor applications of machine vision of plants, which reveals that different environments necessitate varying levels of complexity in both apparatus and nature of plant measurement which can be achieved. Deployment of systems to the field environment in precision agriculture applications presents the challenge of overcoming image variation caused by the diurnal and seasonal variation of sunlight. From the literature reviewed, it is argued that augmenting a monocular RGB vision system with additional sensing techniques potentially reduces image analysis complexity while enhancing system robustness to environmental variables. Therefore, machine vision systems with a foundation in optical and lighting design may potentially expedite the transition from laboratory and research prototype to robust field tool.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  • Andersen H, Reng L, Kirk K (2005) Geometric plant properties by relaxed stereo vision using simulated annealing. Comput Electron Agric 49: 219–232

    Article  Google Scholar 

  • Bacci L, Vincenzi MD, Rapi B, Arca B, Benincasa F (1998) Two methods for the analysis of colorimetric components applied to plant stress monitoring. Comput Electron Agric 19: 167–186

    Article  Google Scholar 

  • Carter G, Miller R (1994) Early detection of plant stress by digital imaging within narrow stress-sensitive wavebands. Remote Sens Environ 50: 295–302

    Article  Google Scholar 

  • Casady W, Singh N, Costello T (1996) Machine vision for measurement of rice canopy dimensions. Tran ASAE 39(5): 1891–1898

    Google Scholar 

  • Chaerle L, Hulsen K, Hermans C, Strasser R, Valcke R, Hofte M, van der Straeten D (2003) Robotized time-lapse imaging to assess in-planta uptake of phenylurea herbicides and their microbial degradation. Physiol Plant 118(4): 613–619

    Article  Google Scholar 

  • Chien C, Lin T (2005) Non-destructive growth measurement of selected vegetable seedlings using orthogonal images. Trans ASAE 48(5): 1953–1961

    Google Scholar 

  • Chien C, Wang C, Yeh C, Lin T (2004) Plant seedling measurement and graphical reconstruction using multiple orthogonal-view images. In: Proceedings of the 2nd international symposium on machinery and mechatronics for agriculture and biosystems engineering

  • Colaizzi P, Barnes E, Clarke T, Choi C, Waller P, Haberland J, Kostrzewski M (2003) Water stress detection under high frequency sprinkler irrigation with water deficit index. J Irrig Drain Eng 129(1): 36–43

    Article  Google Scholar 

  • Driggers, RG (ed) (2003) Encyclopedia of optical engineering, vol 2. Marcel Dekker, New York

    Google Scholar 

  • Dror R, Shimshoni I (2009) Using phyllotaxis for date palm tree 3D reconstruction from a single image. In: ‘VISAPP 2009—proceedings of the 4th international conference on computer vision theory and applications, vol 2, pp 288–296

  • Du J, Wang X, Zhang G (2007) Leaf shape based plant species recognition. Appl Math Comput 185: 883–893

    Article  MATH  Google Scholar 

  • Edan Y, Rogozin D, Flash T, Miles G (2000) Robotic melon harvesting. IEEE Trans Robot Autom 16(6): 831–834

    Article  Google Scholar 

  • Evans R, Benham B, Trooien T (eds) (1997a) National irrigation symposium: proceedings of the 4th decennial symposium, American Society of Agricultural Engineers. Phoenix, Arizona

  • Evans R, Buchleiter G, Sadler E, King B, Harting G (1997b) Controls for precision irrigation with self-propelled systems. In: Evans et al. (1997a) op. cit. pp 322–331

  • Ewing R, Horton R (1999) Quantitative color image analysis of agronomic images. Agron J 91: 148–153

    Article  Google Scholar 

  • Fleisher D, Rodriguez L, Both A, Cavazzoni J, Ting K (2006) Advanced life support systems in space. In: CIGR handbook of agricultural engineering, vol 6. Information technology, pp 339–354

  • Geiger D (2004) Extending the utility of machine based height sensors to spatially monitor cotton growth, Biological and agricultural engineering, Texas A & M University. Master’s Thesis

  • Haff RP, Slaughter DC (2009) X-ray based stem detection in an automatic tomato weeding system. In: ASABE Meeting Paper No. 096050, ASABE, Sacramento, California, ASAE

  • Harding KG (2003) Machine vision—lighting. In: Driggers (ed) (2003) op. cit. pp 1227–1236

  • Hemming J, Rath T (2002) Image processing for plant determination using the Hough transform and clustering methods. Gartenbauwissenschaft 67(1): 1–10

    Google Scholar 

  • Hemming J, van Henten E, van Tuijl B, Bontsema J (2005) A leaf detection method using image sequences and leaf movement. In: van Straten et al. (ed) (2005) op. cit. pp 765–772

  • Humphries S, Simonton W (1993) Identification of plant parts using color and geometric image data. Trans ASAE 36(5): 1493–1500

    Google Scholar 

  • Hussain A, Raine SR, Henderson CW, Jensen T (2008) Evaluation of a proximal vision data acquisition system for measuring spatial variability in lettuce growth. In: National conference, Agronomy Society of Australia, 21–25th September, Adelaide

  • Ishida M (2004) Automatic thresholding for digital hemispherical photography. Can J For Res 34(11): 2208–2216

    Article  Google Scholar 

  • Jimenez A, Ceres R, Pons J (2000) A survey of computer vision methods for locating fruit on trees. Trans ASAE 43(6): 1911–1920

    Google Scholar 

  • Jin J, Tang L (2009) Corn plant sensing using real-time stereo vision. J Field Robot 26(6–7): 591–608

    Article  MathSciNet  Google Scholar 

  • Jonckheere I, Fleck S, Nackaerts K, Muys B, Coppin P, Weiss M, Baret F (2004) Review of methods for in situ leaf area index determination. Part I theories, sensors and hemispherical photography. Agric For Meteorol 121(1–2): 19–35

    Article  Google Scholar 

  • Kacira M, Ling P (2001) Design and development of an automated and noncontact sensing system for continuous monitoring of plant health and growth. Trans ASAE 44(4): 989–996

    Google Scholar 

  • Kacira M, Ling P, Short T (2002) Machine vision extracted plant movement for early detection of plant water stress. Trans ASAE 45(4): 1147–1153

    Google Scholar 

  • Kise M, Zhang Q (2006) Reconstruction of a virtual 3D field scene from ground-based multi-spectral stereo imagery. ASAE Meeting Paper No. 063098, ASAE, Sacramento, California, ASAE

  • Komi PJ, Jackson MR, Parkin RM (2007) Plant classification combining colour and spectral cameras for weed control purposes. In: IEEE international symposium on industrial electronics, pp 2039–2042

  • Kondo N, Ting K (1998) Robotics for plant production. Artif Intell Rev 12(1–3): 227–243

    Article  Google Scholar 

  • Kumar L, Schmidt KS, Dury S, Skidmore AK (2001) Imaging spectrometry and vegetation science. In: van der Meer F, de Jong SM (eds) Imaging spectrometry. Kluwer, Dordrecht, pp 111–155

    Google Scholar 

  • Kurata K, Yan J (1996) Water stress estimation of tomato canopy based on machine vision. Acta Horticult 440: 389–394

    Google Scholar 

  • Lee WS, Slaughter DC (2004) Recognition of partially occluded plant leaves using a modified Watershed algorithm. Trans ASAE 47(4): 1269–1280

    Google Scholar 

  • Leinonen I, Jones H (2004) Combining thermal and visible imagery for estimating canopy temperature and identifying plant stress. J Exp Botany 55(401): 1423–1431

    Article  Google Scholar 

  • McCarthy C, Hancock N, Raine S (2009) Automated internode length measurement of cotton plants under field conditions. Trans ASABE 52(6): 2093–2103

    Google Scholar 

  • Milroy S, Goyne P, Larsen D (2002) Cotton information sheet: irrigation scheduling of cotton. Technical report, Australian Cotton Cooperative Research Centre

  • Murase H, Nishiura Y, Mitani K (1997) Environmental control strategies based on plant responses using intelligent machine vision technique. Comput Electron Agric 18(2): 137–148

    Article  Google Scholar 

  • Neto J, Meyer G, Jones D (2006) Individual leaf extractions from young canopy images using Gustafson-Kessel clustering and a genetic algorithm. Comput Electron Agric 51(1–2): 68–85

    Google Scholar 

  • Nobis M, Hunziker U (2005) Automatic thresholding for hemispherical canopy-photographs based on edge-detection. Agric For Meteorol 128(2): 243–250

    Article  Google Scholar 

  • Noh H, Zhang Q, Han S, Shin B, Reum D (2005) Dynamic calibration and image segmentation methods for multispectral imaging crop nitrogen deficiency sensors. Trans ASAE 48(1): 393–401

    Google Scholar 

  • Noordam J, Hemming J, van Heerde C, Golbach F, van Soest R, Wekking E (2005) Automated rose cutting in greenhouses with 3D vision and robotics: analysis of 3D vision techniques for stem detection. In: van Straten et al. (2005) op. cit. pp 885–892

  • Pan Z, Hu W, Guo X, Zhao C (2004) An efficient image-based 3D reconstruction algorithm for plants. In: The 2004 international conference on computational science and its applications. Assisi, Italy, pp 751–760

  • Praat J, Bollen F, Irie K (2004) New approaches to the management of vineyard variability in New Zealand. In: The 12th Australian wine industry technical conference, managing vineyard variation (precision viticulture). Australian Wine Industry, Melbourne, pp 24–30

  • Rovira-Mas F, Zhang Q, Reid J (2005) Creation of three-dimensional crop maps based on aerial stereoimages. Biosyst Eng 90(3): 251–259

    Google Scholar 

  • Safren O, Alchanatis V, Ostrovsky V, Levi O (2007) Detection of green apples in hyperspectral images of apple-tree foliage using machine vision. Trans ASABE 50(60): 2303–2313

    Google Scholar 

  • Schumann A, Zaman Q (2005) Software development for real-time ultrasonic mapping of tree canopy size. Comput Electron Agric 45(1): 25–40

    Article  Google Scholar 

  • Seginer I, Elster R, Goodrum J, Reiger M (1992) Plant wilt detection by computer-vision tracking of leaf tips. Trans ASAE 35(5): 1563–1567

    Google Scholar 

  • Shearer S, Holmes R (1990) Plant identification using color co-occurrence matrices. Trans ASAE 33(6): 2037–2044

    Google Scholar 

  • Shlyakhter I, Rozenoer M, Dorsey J, Teller S (2001) Reconstructing 3D tree models from instrumented photographs. IEEE Comput Graph Appl 21(3): 53–61

    Article  Google Scholar 

  • Singh S, Montemerlo M (1997) Recent results in the grading of vegetative cuttings using computer vision. In: Proceedings of the IEEE-RSJ international conference on intelligent robots and systems innovative robots for real-world applications, pp 1845–1850

  • Slaughter DC, Giles DK, Downey D (2008) Autonomous robotic weed control systems: a review. Comput Electron Agric 61: 63–78

    Article  Google Scholar 

  • Smith RJ, Raine SR, McCarthy AC, Hancock NH (2009) Managing spatial and temporal variability in irrigated agriculture through adaptive control. Aust J Multi-disciplinary Eng 7(1): 79–90

    Google Scholar 

  • Soille P (2000) Morphological image analysis applied to crop field mapping. Image Vis Comput 18(13): 1025–1032

    Article  Google Scholar 

  • Stajnko D, Lakota M, Hocevar M (2003) Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging. Comput Electron Agric 42(1): 31–42

    Article  Google Scholar 

  • Steward B, Tian L, Nettleton D, Tang L (2004) Reduced-dimension clustering for vegetation segmentation. Trans ASAE 47(2): 609–616

    Google Scholar 

  • Takakura T, Shimomachi T, Takemasa T (2002) Non-destructive detection of plant health. In: Acta Horticulturae, vol 578. International Society for Horticultural Science, pp 303–306

  • Takizawa H, Ezaki N, Mizuno S (2005) Measurement of plants by stereo vision for agricultural applications. In: Proceedings of the seventh IASTED internal conference: signal and image processing

  • Tang L, Tian L, Steward B (2000) Color image segmentation with genetic algorithm for in-field weed sensing. Trans ASAE 43(4): 1019–1027

    Google Scholar 

  • Tarbell K, Reid J (1991) A computer vision system for characterizing corn growth and development. Trans ASAE 34(5): 2245–2255

    Google Scholar 

  • Tian L, Slaughter D (1998) Environmentally adaptive segmentation algorithm for outdoor image segmentation. Comput Electron Agric 21: 153–168

    Article  Google Scholar 

  • Tumbo S, Salyani M, Whitney J, Wheaton T, Miller W (2002) Investigation of laser and ultrasonic ranging sensors for measurements of citrus canopy volume. Appl Eng Agric 18(3): 367–372

    Google Scholar 

  • van Henten E, Hemming J, van Tuijl B, Kornet J, Meuleman J, Bontsema J, van Os E (2002) An autonomous robot for harvesting cucumbers in greenhouses. Autonom Robots 13(3): 241–258

    Article  MATH  Google Scholar 

  • van Straten G, Bot G, van Meurs W, Marcelis L (eds) (2005) Proceedings of the international conference on sustainable greenhouse systems, Acta Horticulturae, vol 691. International Society for Horticultural Science

  • Vrindts E, de Baerdemaeker J (1997) Optical discrimination of crop, weed and soil for on-line weed detection. In: Stafford J (ed) Precision Agriculture 1997, vol 2. Technology, IT and Management. BIOS, Oxford, pp 533–544

    Google Scholar 

  • Waksman A, Rosenfeld A (1997) Assessing the condition of a plant. Mach Vis Appl 10(1): 35–41

    Article  Google Scholar 

  • Wang N, Zhang N, Dowell F, Sun Y, Peterson D (2001) Design of an optical weed sensor using plant spectral characteristics. Trans ASAE 44(2): 409–419

    Google Scholar 

  • Wang Z, Heinemann P, Sommer H III, Walker P, Morrow C, Heuser C (1998) Identification and separation of micropropagated sugarcane shoots based on the Hough transform. Trans ASAE 98: 1535–1541

    Google Scholar 

  • Wei J, Salyani M (2004) Development of a laser scanner for measuring tree canopy characteristics: Phase 1 Prototype development. Trans ASAE 47(6): 2101–2107

    Google Scholar 

  • Williams L, Ayars J (2005) Grapevine water use and the crop coefficient are linear functions of the shaded area measured beneath the canopy. Agric For Meteorol 132: 201–211

    Article  Google Scholar 

  • Woebbecke D, Meyer G, Von Bargen K, Mortensen D (1995) Color indices for weed identification under various soil, residue, and lighting conditions. Trans ASAE 38(1): 259–269

    Google Scholar 

  • Zeng Q, Liu C, Miao Y, Fei S, Wang S (2008) A machine vision system for continuous field measurement of grape fruit diameter. In: IEEE second international symposium on intelligent information technology application, pp 1064–1068

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to C. L. McCarthy.

Rights and permissions

Reprints and permissions

About this article

Cite this article

McCarthy, C.L., Hancock, N.H. & Raine, S.R. Applied machine vision of plants: a review with implications for field deployment in automated farming operations. Intel Serv Robotics 3, 209–217 (2010). https://doi.org/10.1007/s11370-010-0075-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11370-010-0075-2

Keywords

Navigation