Precision weed detection via colour and depth data fusion in real-time for automatic spot spraying

PhD Thesis


Rees, Steven. 2015. Precision weed detection via colour and depth data fusion in real-time for automatic spot spraying. PhD Thesis Doctor of Philosophy. University of Southern Queensland.
Title

Precision weed detection via colour and depth data fusion in real-time for automatic spot spraying

TypePhD Thesis
Authors
AuthorRees, Steven
SupervisorMcCarthy, Cheryl
Hancock, Nigel
Institution of OriginUniversity of Southern Queensland
Qualification NameDoctor of Philosophy
Number of Pages312
Year2015
Abstract

Broadacre and row crop farming in Australia uses no-till and minimum-till farming systems which have led to the overuse of specific herbicides for weed control,
causing resistance to those specific herbicides to build-up in weeds. Automatic weed spot spraying can help reduce resistance build-up by specifically detecting weeds for targeted control with alternative herbicides, hence breaking the resistance cycle. Existing commercial weed spot sprayers are only capable of distinguishing green from brown, i.e. plant material in a fallow situation, and image
analysis research for weed discrimination typically was not developed for commercial on-farm conditions. The research in this thesis has developed a real-time, real-world machine vision spot spray system that can operate at groundspeeds up to 20 km/h and discriminate green from green (i.e. weed from crop) under commercial conditions for two very different crop types and size scales, specifically
sugarcane (grass-like) and pyrethrum (broadleaf).

Occlusion of a weed leaf by another leaf or plant is a major impediment for real-world operation of a machine vision weed spot sprayer. A Depth Colour Segmentation Algorithm (DCSA) has been developed which combines depth data and colour image data to segment individual leaves from each other, based on pixel connectedness in height and colour, providing an accuracy when occluded of greater than 99%. The DCSA has a �filtering capability that can reduce the amount of data requiring further analysis by an observed 83% for sugarcane and 53% for pyrethrum.

Existing feature extraction techniques have been evaluated in the thesis and have been shown to be unsatisfactory in discriminating weed from crop especially when the weed and crop are similar species, e.g. grass-like weed (guinea grass) from grass-like crop (sugarcane). Depth features were added to the extracted features of a local binary pattern function, improving the accuracy from 63% to 90% for pyrethrum identification, and showing that depth data combined with 2D data can improve the discrimination result. Additional real-world custom algorithms have been
developed to achieve an identification accuracy of 87% (where 86% of the weed was occluded) with a 3.5% false positive rate for sugarcane. The Depth, Colour, Size and Spatial (DCSS) algorithm developed for pyrethrum achieved
98% accuracy for pyrethrum identification with a 1.2% false positive rate.

Real-time functionality has been obtained by the development of a Synchronised Parallel Processing
(SPP) technique. The SPP technique maintains a high frame rate (which determines the maximum groundspeed) by assigning the workload in a permanently allocated pipeline synchronised by the incoming video image. Calculations for sugarcane and pyrethrum show that speeds up to 18.5 and 17.2 km/h respectively are achievable based on the algorithms developed and a higher core count CPU
(six cores were used in the calculation) would achieve higher groundspeeds. The gains from the additional processing availability provided by SPP can be used to achieve a higher groundspeed, or undertake additional image analysis, if required.

It is concluded that the machine vision components developed in this thesis comprise a real-time,
real-world machine vision spot sprayer that can operate at commercial groundspeeds up to 20 km/h and discriminate weed from crop.

Keywordsweed detection; machine vision; image analysis; line detection; spot spraying
ANZSRC Field of Research 2020460304. Computer vision
400799. Control engineering, mechatronics and robotics not elsewhere classified
300409. Crop and pasture protection (incl. pests, diseases and weeds)
Byline AffiliationsNational Centre for Engineering in Agriculture
Permalink -

https://research.usq.edu.au/item/q4v42/precision-weed-detection-via-colour-and-depth-data-fusion-in-real-time-for-automatic-spot-spraying

Download files


Published Version
Rees_2015_whole.pdf
File access level: Anyone

  • 630
    total views
  • 185
    total downloads
  • 2
    views this month
  • 1
    downloads this month

Export as

Related outputs

Coals seam gas (CSG) in agriculture - a review: technical and market analysis for Australia
Yusaf, Talal, Hamawand, Ihsan, Schmidt, Erik, Binnie, James, Rees, Steven and Chakrabarty, Sayan. 2014. "Coals seam gas (CSG) in agriculture - a review: technical and market analysis for Australia ." Sustainable Energy Technologies and Assessments. 8, pp. 149-158. https://doi.org/10.1016/j.seta.2014.08.005
Technologies for cattle monitoring - proof of concept study
Rees, S.. 2008. Technologies for cattle monitoring - proof of concept study. Toowoomba, Australia. University of Southern Queensland.
Commercialisation of precision agriculture technologies in the macadamia industry
Rees, Steven, Dunn, Mark, Werkman, Peter and McCarthy, Cheryl. 2009. Commercialisation of precision agriculture technologies in the macadamia industry. Toowoomba, Australia. University of Southern Queensland.
Preliminary evaluation of shape and colour image sensing for automated weed identification in sugarcane
McCarthy, Cheryl, Rees, Steven and Baillie, Craig. 2012. "Preliminary evaluation of shape and colour image sensing for automated weed identification in sugarcane." Bruce, R. C. (ed.) 34th Annual Conference of the Australian Society of Sugar Cane Technologists (ASSCT 2012). Palm Cove, Australia 01 - 04 May 2012 Australia.
Development and evaluation of a prototype precision spot spray system using image analysis to target guinea grass in sugarcane
Rees, S. J., McCarthy, C. L., Baillie, C. P., Burgos-Artizzu, X. P. and Dunn, M. T.. 2011. "Development and evaluation of a prototype precision spot spray system using image analysis to target guinea grass in sugarcane." Australian Journal of Multi-Disciplinary Engineering. 8 (2), pp. 97-106.
Machine vision-based weed spot spraying: a review and where next for sugarcane?
McCarthy, Cheryl, Rees, Steven and Baillie, Craig. 2010. "Machine vision-based weed spot spraying: a review and where next for sugarcane?" Bruce, R. C. (ed.) 32nd Annual Conference of the Australian Society of Sugar Cane Technologists (ASSCT 2010). Bundaberg, Australia 11 - 14 May 2010 Australia.
Development of a prototype precision spot spray system using image analysis and plant identification technology
Rees, Steven, McCarthy, Cheryl, Artizzu, X. P. B., Baillie, Craig and Dunn, Mark. 2009. "Development of a prototype precision spot spray system using image analysis and plant identification technology." Banhazi, T. M. and Saunders, C. (ed.) SEAg 2009: Agricultural Technologies In a Changing Climate. Brisbane, Australia 13 - 16 Sep 2009 Brisbane, Australia.
Evaporation, seepage and water quality management in storage dams: a review of research methods
Craig, Ian, Aravinthan, Vasantha, Baillie, Craig Peter, Beswick, Alan, Barnes, Geoff, Bradbury, Ron, Connell, Luke, Cooper, Paul, Fellows, Christopher, Fitzmaurice, Li, Foley, Joseph P., Hancock, Nigel, Lamb, David, Morrison, Pippa, Mossad, Ruth, Misra, R. K., Pittaway, Pam, Prime, Emma, Rees, Steve, ..., Turnbull, David. 2007. "Evaporation, seepage and water quality management in storage dams: a review of research methods." Environmental Health. 7 (3), pp. 84-97.