Dr Cheryl L McCarthy

Curriculum vitae

Contact information

  • Email address: Cheryl.McCarthy@usq.edu.au
  • Official website address: http://www.ncea.org.au
  • Postal address: National Centre for Engineering in Agriculture, University of Southern Queensland, West Street
  • City/region: Toowoomba
  • Country: Australia
  • Business phone: 0746312297
  • Mobile phone: 0447133575
  • Fax number: 0746311870

Publications

McCarthy, Cheryl and Hancock, Nigel and Raine, Steven R. (2006) A preliminary evaluation of machine vision sensing of cotton nodes for automated irrigation control. In: Irrigation Australia 2006: Irrigation Association of Australia National Conference and Exhibition, 9-11 May 2006, Brisbane, Australia.

Shalal, Nagham and Low, Tobias and McCarthy, Cheryl and Hancock, Nigel (2013) A preliminary evaluation of vision and laser sensing for tree trunk detection and orchard mapping. In: Australasian Conference on Robotics and Automation (ACRA 2013), 2-4 Dec 2013, Sydney, Australia.

McCarthy, Cheryl and Hancock, Nigel and Raine, Steven R. (2007) A preliminary field evaluation of an automated vision-based plant geometry measurement system. In: 5th International Workshop on Functional Structural Plant Models (FSPM07), 4-9 Nov 2007, Napier, New Zealand.

McCarthy, Cheryl (2004) Advance rate measurement for furrow irrigation. [USQ Project]

McCarthy, Cheryl and Hancock, Nigel and Raine, Steven R. (2010) Apparatus and infield evaluations of a prototype machine vision system for cotton plant internode length measurement. Journal of Cotton Science, 14 (4). pp. 221-232. ISSN 1523-6919

McCarthy, Cheryl and Billingsley, John (2009) Applied machine vision in agriculture at the NCEA. In: SEAg 2009: Agricultural Technologies in a Changing Climate, 13-16 Sep 2009, Brisbane, Australia.

McCarthy, Cheryl (2009) Automatic non-destructive dimensional measurement of cotton plants in real-time by machine vision. [Thesis (PhD/Research)]

Rees, Steven and Dunn, Mark and Werkman, Peter and McCarthy, Cheryl (2009) Commercialisation of precision agriculture technologies in the macadamia industry. Project Report. University of Southern Queensland, National Centre for Engineering in Agriculture , Toowoomba, Australia. [Report]

Koirala, Anand and Walsh, Kerry B. and Wang, Zhenglin and McCarthy, Cheryl (2019) Deep learning - method overview and review of use for fruit detection and yield estimation. Computers and Electronics in Agriculture, 162. pp. 219-234. ISSN 0168-1669

Rees, Steven and McCarthy, Cheryl and Artizzu, X. P. B. and Baillie, Craig and Dunn, Mark (2009) Development of a prototype precision spot spray system using image analysis and plant identification technology. In: SEAg 2009: Agricultural Technologies in a Changing Climate, 13-16 Sep 2009, Brisbane, Australia.


Last updated on 03 July 2020, 22:27

Biography

Dr Cheryl McCarthy is a Senior Research Fellow in mechatronic engineering with the Centre for Agricultural Engineering (formerly NCEA) at the University of Southern Queensland. Her research involves developing machine vision and sensing systems for agriculture. She has worked on machine vision projects for the beef, fodder and macadamia industries and her current projects include precision sensing of weeds for the sugar, cotton and grains industries. She has a BEng (Mechatronic) and PhD from USQ. Her research interests include the application of mechatronic engineering to agriculture and imaging spectrometry. She holds a CASA UAV Operator's Certificate.

Areas of expertise

Machine vision and image analysis applied to agriculture

Field instrumentation for remote sites

Current research activities

  • Novel detection of chicken welfare using machine vision
  • Real-time sugarcane harvester losses assessment with machine vision systems
  • Real-time image analysis and prescription map from UAV / RPAS imagery
  • Precision weed sensing for pyrethrum, sugar, cotton and grains industries
  • Remote sensing of beehives to improve surveillance for honeybee pests
  • Accelerating autonomous tractor technologies for agriculture
  • Remote grain variety trial site monitoring

Livestock project publications by USQ-CAE's Automation theme

  • Neves, DP; Abdanan Mehdizadeh, SA; TSCHARKE, M; De Alencar Nass, I; Banhazi, TM (2015). Detection of flock movement and behavior of broiler chickens at different feeders using image analysis. Information Processing in Agriculture, Vol. 2, p. 177-182, 2015.

       http://www.sciencedirect.com/science/article/pii/S2214317315000475

  • Cronin, G. M. and Borg, S. S. and DUNN, M. T. (2008) Using video image analysis to count hens in cages and reduce egg breakage on collection belts. Australian Journal of Experimental Agriculture, 48 (7). pp. 768-772. ISSN 0816-1089

       http://www.publish.csiro.au/paper/EA07404.htm

  • Finch, Neal A. and Murray, Peter J. and DUNN, Mark T. and BILLINGSLEY, John (2006) Control of watering point access using machine vision classification of animals. Transactions of the Western Section of the Wildlife Society, 42. pp. 16-19. ISSN 0893-214X

       http://www.tws-west.org/transactions/Finch%20invasive%20species.pdf

Cattle counting from drone

Remote sensing of bait boxes to improve surveillance http://www.portbees.com.au/

The Australian honeybee industry is currently free from a number of exotic bee pests that have devastated honeybee populations around the world. This HIA/RIRDC project was to develop an electronic sensing system that could automatically detect when a swarm of bees had entered a bait box (an old beehive which is used as a pest bee trap), to save a bait box officer from having to continually check for exotic bees inside the bait box, and to allow round-the-clock trap monitoring.

1-BoxAtPort.JPG  BeesInTrial1.jpg

 BeeActivityDetection.JPG

HIA-logo.jpg  ri.png

Remote surveillance bait box project on 60 Minutes 'Bee Scared' 31 May 2015

The HIA-RIRDC bait box project featured on '60 minutes', see story at

http://www.9jumpin.com.au/show/60minutes/stories/2015/may/bee-scared/

60Mins2.JPG.2

Weed spot spraying for the cotton, sugar and pyrethrum industries

Weeds cost Australian agriculture $2-4 billion each year, with control methods typically comprising manual spot spraying, broadcast spraying or tillage operations. A Machine Vision System mounted on a tractor or ground robot can tell the difference between weeds and crop plants growing next to each other, and only spray the weed, hence reducing herbicide use.

Treated2b_BigText.jpg  TreatedPaddock_BigText.jpg

 SingleRowGear.JPG  Weeds.jpg

sra-logo-150x150.jpg  ri.png  BRA logo.jpg  HIA-logo.jpg  CRDC logo_small.jpg

Queensland Government Accelerate Fellowship: UAV hotspot detection

UAVweeds.jpg

USQ_CoBrand_NCEA_FullCol.jpegune-logo.png  v-tollogo.jpg

 

 

Drone and Isaac robot co-ordination

Vineyard imaging with octocopter

Vineyard closeup with ground camera

Irrigation visualisation tool

OVERSched: A visualisation tool for centre pivots and lateral moves