Non-Invasive Sensor Technology

Well as you know as a consumer yourself, you go into a retail store and you purchase fruit on the basis of what it looks like, take it home and you have an eating experience that’s bad and the research says that you won't go back to buy that fruit for four to six weeks, so it's not an instant decision but it’s certainly important to repeat purchase.

You know the big problem has been that to test mangoes in the past for maturity, they had to cut them. So the only tests we really had were the external visual cues, you know so whether it’s full, good shoulders, shape, bit of blush colour. But the reality is there's a big variation between varieties in that area and some varieties are really hard to tell by external cues, so the only sure method we had before was to actually take a mango and cut it in half and have a look at the flesh colour. So with one of the NIR guns we are now able to walk through the orchard testing fruit, seeing if there’s enough to go through a spot pick or whether they’re all ready and train up our workers as to the visual cues as to what a mature mango looks like. It just means we can get our start date correct so that we're picking fully mature fruit that the customer is going to be happy with.

Initially we were prompted by growers to look at estimating the quality of fruit non-invasively, its internal quality being sugar content or dry matter content and that took us down the path of measuring in-line. So you’re on a pack line, you’re sorting on colour and weight. Now we were adding in an another facility, that is estimating that the sugar content or dry matter content of that fruit. We were in the fields doing the dry matter measurements and we could see the grower practice of trying to estimate fruit yields, that is how much crop was on the tree, so that they could be organised in terms of labour requirements, pack house requirements and that was all being done manually with a hand counter, so that lead us into a new line of work looking at machine vision in the field, so rather than just machine vision in the pack house, taking it into the field to estimate crop load across the field. The next step on from that of course, having seen the fruit, is to try and reach out to pick the fruit to automate the harvest.

It’s actually getting more advanced and so now the machinery is able to identify and count fruit in the orchard and last year it turned out to be with only a few percent wrong from the actual count of numbers of mangoes are in that entire block. Now that technology is also able to give us the size range of that fruit and so knowing how much fruit is in the block, knowing when it’s going to be mature, knowing the size of the fruit means we can schedule our workforce, we can order the right number of cartons, we can order the right numbers of inserts to go in those cartons. This is going, this could be a real game-changer for not only our farm, but for the industry.

Kerry Walsh – Professor - Sensor Systems

The theme of Kerry Walsh’s career has been the application of non-invasive instrumentation to issues related to plant performance, and in particular in photosynthate transport - assimilate partitioning. He has led multidisciplinary work resulting in the association of a phytoplasma with the papaya dieback disorder, and the use of near infra-spectroscopy (NIRS) for fruit quality assessment. Kerry has a practical, hands-on, capability, yet an academic perspective on life. He strongly believes that his R&D effort should result in a gain to society, and that he should provide practically relevant training to undergraduates and postgraduates.

Current research projects:

• Multi-scale monitoring of tropical fruit trees - Horticulture Innovation Australia and the Commonwealth Department of Agriculture

Industry and funding partners:

• Australian Mango Industry Association
• Avocados Australia
• Horticulture Innovation Australia
• Commonwealth Department of Agriculture

Publications:

• Walsh, K.B., Subedi, P., Tijskens, P. (2015)  A case study of a decision support system on mango maturity.  Acta Horticulturae · August 2015 DOI: 10.17660/ActaHortic.2015.1091.24
• Walsh, K.B. and Subedi, P.P (2016) In-field monitoring of mango fruit dry matter for maturity estimation.  Acta Hort. 1119, 273-278    doi 10.17660/ActaHortic.2016.1119.38 XXIX IHC – Proc. Int. Symposium on Abscission Processes in Horticulture and Non-Destructive Assessment of Fruit Attributes.  Ed. J.N. Wunsche et al.
• Walsh, K.B.  (2015) Detection of attribute ‘xxx’ in fruit ‘yyyy’ using NIRS.  Acta Horticulturae 1119, 141-146   doi 10.17660/ActaHortic.2016.1119.38 XXIX IHC – Proc. Int. Symposium on Abscission Processes in Horticulture and Non-Destructive Assessment of Fruit Attributes.  Ed. J.N. Wunsche et al.
• Walsh, K.B.  (2015) The evolution of spectrophotometers used in fruit quality assessment. Acta Horticulturae 1119, 203-208   doi 10.17660/ActaHortic.2016.1119.38 XXIX IHC – Proc. Int. Symposium on Abscission Processes in Horticulture and Non-Destructive Assessment of Fruit Attributes.  Ed. J.N. Wunsche et al.
• Walsh, K.B.  (2015) The impact of lamp environment on prediction of peach TSS content. Acta Horticulturae 1119, 155-162   doi 10.17660/ActaHortic.2016.1119.38 XXIX IHC – Proc. Int. Symposium on Abscission Processes in Horticulture and Non-Destructive Assessment of Fruit Attributes.  Ed. J.N. Wunsche et al.
• Walsh, K.B. (2018) Fruit and vegetable packhouse – Technologies for assessing fruit quantity and quality.  In: Advances in Agricultural Technology, ed. Chen, G.  CRC Press, Boca Raton. G.  pp. 367 – 395.
• Walsh, K.B. and Wang, Z. (2018) Monitoring fruit quality in mangoes In: Achieving sustainable cultivation of mangoes, e.d. Galan Sauco, V. and Lu, P.  Bureligh Dodds Publishing, Cambridge, UK.
• Walsh, K.B. (2015) Nondestructive assessment of fruit quality; in ‘Advances in postharvest fruit and vegetable technology’ . CRC Press series on Contemporary Food Engineering. Eds. R.B.H. Wills and J.B. Golding.  Elsevier.  pp. 40-61

H Index: 38

Students under supervision:

• Anand Koirala
• Nick Anderson

David Midmore - Emeritus Professor

David Midmore is retired from research but is active in writing, editing and guiding post-graduate students.

Having worked in research and senior management positions with the CGIAR system in Mexico [CIMMYT], Peru [CIP] and Taiwan [AVRDC] he has a holistic grasp of the issues facing the future of global agriculture and horticulture, and his opinions and input are sought widely, including by the CGIAR, DFID, USAID and the USDA where he has undertaken Programme and Consortium reviews.

Since arriving in Australia in 1995 he held until 2015 an appointment as Foundation Professor of Plant Science at CQUniversity Australia where he researched agronomy and physiology of new crop species, urban agriculture, crop resource use efficiency, solid and liquid waste management and abatement of pollution, sensing technologies and innovations in irrigation amongst others.

In early 2010 he relocated to the School of Agriculture, Policy and Development at the University of Reading as a Visiting Professor, from where he remotely ran the CQUniversity Centre for Plant and Water Science, and taught and engaged with students and proposal development in both Australia and the UK.

Since retiring in 2016, David has maintained contact with CQUniversity, publishing with staff, supervising students and still engaging in some project activities. He also teaches remotely from Mexico to the UK on courses relating to irrigation, sustainable intensification and urban agriculture.

Publications (2017-2018):

• Mousumi Debnath, Nanjappa Ashwath, Camilla Beate Hill, Damien L. Callahan, Daniel Anthony Dias, Nirupama Samanmalie Jayasinghe, David James Midmore, Ute Roessner (2018). Comparative metabolic and ionomic profiling of two cultivars of Stevia rebaudiana Bert. (Bertoni) grown under salinity stress. Plant Physiology and Biochemistry. (In Press).
• Smith N.J.C., Zahid D.M., Ashwath, N., Midmore, D.J., Reid D.J. (2018) Physiological Responses of Australian rainforest timber species to altered solar radiation, spectral quality and added nitrogen in a simulated natural environment. Journal of Sustainable Forestry, https://doi.org/10.1080/10549811.2018.1447489
• Prasai, T.P., Walsh, K.B, Midmore, D.J., Jones, B.E.H., Bhattarai, S.P. (2018). Manure from biochar, bentonite and zeolite feed supplemented poultry: Moisture retention and granulation properties, Journal of Environmental Management, 216, 82-88. https://www.sciencedirect.com/science/article/pii/S0301479717308253
• Prasai Tanka P, Walsh Kerry B, Bhattarai Surya P, Midmore David J, Van Thi TH, Moore Robert J, Stanley Dragana. (2017). Zeolite food supplementation reduces abundance of enterobacteria. Microbiological Research. 195, 24-30. http://dx.doi.org/10.1016/j.micres.2016.11.006
• G. Gautam Kafle, D.J. Midmore and R. Gautam (2017). Effect of nutrient omission and pH on the biomass and concentration and content of steviol glycosides in stevia (Stevia rebaudiana). Journal of Applied Research on Medicinal and Aromatic Plants. 7, 136-142.
• Prasai, T.P., Walsh, K.B, Midmore, D.J., Bhattarai, S.P. (2017). Biochar, zeolite and bentonite feed supplements influence broiler growth and meat yield and excreta properties. European Poultry Science. 81. 2017,. DOI: 10.1399/eps.2017.209
• Dahal, K.C., Bhattarai, S.P., Midmore, D.J., Oag, D. and Walsh, K.B. (2017). Table grape production in the subtropics and prospects for Nepal. Nepalese Horticulture, 12, 6-15.
• Tanka Prasai, Kerry Walsh, Surya Bhattarai, David Midmore (2017). Effect of biochar, zeolite and bentonite feed supplements on egg yield and excreta attributes. Animal Production Science. http://www.publish.csiro.au/an/AN16290

H Index: 36

Dr Phul Subedi - Research Scientist

Dr Phul Subedi has been involved for 15 years in R & D projects with tropical, sub-tropical and warm temperate horticulture crop industries, particularly focussing on quality control and supply chain management. His wider experiences as a researcher, academic and consultant has demonstrated an ability to document and deliver field and industry relevant solutions, using technologies novel to the horticultural industry. In recent years his particularly research focus is on “Instrument and Technology training in Near Infrared spectroscopy (NIR) as non-invasive technology to assess fruit maturity and internal defect detection of range of fruit crops”.

Current research projects:

External Grants (with Kerry Walsh)

• Technologies in fruit sorting (RC48923) Enterprise Connect with MAF Oceania P/L August 2017-July 2018.
• Quality standards, refinement and testing (MG15002) HIA (sub-component to larger DAF project) 2016-2017.
• Multi-scale monitoring tools for managing Australian Tree Crops:  Industry meets innovation. R&D 4 Profit (Federal DAFF – HIA) 2017-2019.

Industry and funding partners:

• Anthocyanin, Brix and dry matter estimation using portable near infrared spectroscopy.
• Estimation of sultana moisture content using portable near infrared spectroscopy.
• Determination of the dry matter content of sweet potato tubers using portable near infrared spectroscopy.

Publications:

Book Chapters

• Subedi, P.P, and Walsh, K.B. (2016). Technologies for assessing fruit quality: maturity, pigmentation, dry matter content, firmness. In ‘Mango Tree Encyclopedia, (Eds. Mango Tree Encyclopedia Administrative Committee) Chapter 10 pp. 1-39. (Royal Court Affairs, Sultanate of Oman: Muscat).
• Phul P. Subedi, Kerry Walsh, Bed P. Khatiwada, Umesh K. Acharya (2016)  Prospects of developing commercial production of tree fruits in Nepal with focus on citrus production, pp 87-111. In Adhikari, A.P. and Dahal, G.P. (eds). Sustainable Livelihood Systems in Nepal: Principles, practices and prospects. IUCN and CFFN, Kathmandu, Nepal. ISBN: 978-9937-8467-2-1.

Refereed Journal Articles 2015-2017

• Acharya, U., Subedi, P., Walsh, K.B., (2017) Robustness of tomato quality evaluation using portable VIS-SWNIRS for dry matter and colour. Journal of Food Chemistry.
• Anderson, N., Subedi, P.P, Walsh, K.B., (2017) Manipulation of mango fruit dry matter content to improve eating quality. Journal of Scientia Horticulturae.
• Khatiwada, B.P., Subedi,  P.P., Hayes, C., Cunha Carlos Jnr1,  L.C., Walsh, K.B (2016) Assessment of internal flesh browning in intact apple using visible-short wave near infrared spectroscopy. Postharvest Biology and Technology. 120,103-111.
• Deepa, R., Walsh, K.B., Subedi, P.P. and Ashwath, N. (2016) Quality estimation of Agave tequilana leaf for bioethanol production.  J. Near Infrared Spectrosc. 24, 453–465.
• Challagulla, V., Walsh, K.B. and Subedi, P. (2016) Microalgal fatty acid composition: rapid assessment using near-infrared spectroscopy. Journal of Applied Phycology. 28, 85- 94.
• Acharya, U., Subedi, P., Walsh, K.B., McGlasson, W.B. (2015) Estimation of fruit maturation and ripening using spectral indices.  Acta Horticulturae.
• Subedi, P.P, Walsh, K.B. (2015) Using handheld near infrared spectroscopy to guide mango harvest timing decisions: technique validation and application.  Acta Horticulturae.
• Walsh, K.B., Subedi, P. (2015) In-field monitoring of mango fruit dry matter for maturity estimation.  Acta Horticulturae.
• Khatiwada, B., Walsh, K.B., Subedi, P. (2015) Fruit internal defect sorting: Rejection makes the rest the best.  Acta Horticulturae.
• Acharya, U., Subedi, P. and Walsh, K.B. (2015) Spectrophotometer aging and prediction of total soluble solids.  Acta Horticulturae.

H Index: 10

Dr Zhenglin Wang - Postdoctoral Research Fellow

Dr Zhenglin Wang received his Bachelor of Electrical and Electronics Engineering from Zhejiang University, China in 2000; and his Master of Computer Science by Research and PhD both from the University of South Australia in 2012 and 2016 respectively. He also worked as a software engineer at TCL and UTStarcom from 2000 to 2009. Currently, he is an early career researcher at CQUniversity. His research interests include computer vision, deep learning and precision agriculture.

Current research projects:

• Multi-scale monitoring of tropical fruit trees

Publications:

• Wang, Z., Underwood, J., & Walsh, K. B. (2018). Machine vision assessment of mango orchard flowering. Computers and Electronics in Agriculture, 151, 501-511.
• Wang, Z., Walsh, K. B., & Verma, B. (2017). On-tree mango fruit size estimation using RGB-D images. Sensors, 17(12), 2738.
• Wang, Z., & Lee, I. (2014). Frequency-based image deblurring with periodic point spread function. Electronics letters, 50 (23), 1691-1693

H Index: 3

Students under supervision:

• Anand Koirala, PhD candidate (Associate Supervisor) – Multi-scale monitoring of tropical fruit trees

Anand Koirala - PhD Candidate

As a PhD candidate for ‘Precision Agriculture’ at CQUniversity, Ananda Koirala is working on machine vision technologies for fruit quality and yield estimation. He is interested in applying artificial intelligence and machine learning in different research domains through optimization and re-designing of existing frameworks. He has coding ability in Python/Java/C++ for AI and deep learning object detection and image classification tasks using different algorithms (YOLO, SSD, Faster-RCNN) on different platforms (Keras, Dl4j, OpenCV).

Current research projects:

• Deep learning for mango fruit detection
• Deep learning for mango flower assessment
• Deep learning for mango yield estimation

Industry and funding partners:

• RUN scholarship
• Multi-scale Monitoring of Tropical Fruit Trees, Hort Innovation Australia

Publications:

• Fruit load estimation in mango orchards – a method comparison (International Conference on Robotics and Automation, 2018)
• Automated mango flowering assessment via refinement segmentation (Image and Vision Computing New Zealand (IVCNZ), 2016)

Nicholas Anderson - PhD Candidate

Nicholas Anderson first began working on mango orchards while on a working holiday visa and was soon hooked on the fruit and studying crop forecasting at CQUniversity. He brought with him to Australia, IT experience from working with Alberta Health Services in Canada, where he received his undergraduate degree from DeVry University. Nick recently finished a Masters by Research at CQUni and is now pursuing a PhD in precision horticulture. His experience includes near infrared spectroscopy and a practical horticultural knowledge of mango production which ensures a strong focus on which technologies will deliver best value to growers.

Current research projects:

• Fruit maturity/quality via Near Infrared Spectroscopy
• Orchard design, considerations for robotic harvesting
• Flowering and fruit mapping for decision support systems

Industry and funding partners:

• Australian Mango Industry Association
• University of New England, University of Sydney, Department of Primary Industries (NT), Acacia Hills Farm, Tou’s Garden, Simpson’s Farm – Horticulture Innovation (Multi-scale Monitoring)

Publications:

• Manipulation of mango fruit dry matter content to improve eating quality - Scientia Horticulturae
• Estimation of fruit load in mango orchards - tree sampling considerations and use of machine vision and satellite imagery – Precision Agriculture

A century ago, harvested fruit were graded by human visual inspection and sorted on their perceived quality.

A new approach discovered a couple of decades ago from local fruit growers has resulted in the development of technology with worldwide application in the more accurate grading of fruit quality.

Non-invasive devices using near infrared spectroscopy (NIRS) have been successfully developed in collaboration with various manufacturers and funding sources to improve the overall quality of fruit.

Research undertaken at CQUniversity Australia has translated the theoretical potential of NIRS to commercial practice and explored related agronomic issues relevant to the production of quality fruit.

The NIRS project began in the mid-1990s following an approach from growers in the local Central Queensland pineapple industry who believed they were producing sweeter fruit than their southern counterparts and needed an objective test to demonstrate this.

After exploring some colorimetric options, reports on the potential for NIRS were encountered, appropriate laboratory instrumentation was acquired and the concept was demonstrated to the fruit industry.

However, no appropriate equipment existed for fruit grading, with emergent Japanese technology too expensive and slow for use in western horticulture. An Australian Research Council (ARC) Large and ARC Collaborative grant allowed exploration of appropriate optical geometries (patent taken), instrumentation and chemometric development to allow practical use on pack-lines. Horticulture Australia Limited (HAL) funding further supported extension of the work into different fruit commodities and development of portable instrumentation that allowed in-field use.

From the late 1990s, the project team from CQUniversity worked with an Australian fruit grading manufacturer, Colour Vision Systems (CVS), to investigate how to integrate NIRS into a fruit pack-line.

While continuing this collaboration the research team worked with a manufacturer of handheld devices, first Integrated Spectronics Pty Ltd, then, more recently, Felix Instruments Incorporated to produce a handheld NIRS device for use in assessment of fruit on trees.

The worldwide market for such devices is modest, such that the value of the technology is in the value added to fruit production, rather than equipment sales.

To support the uptake of the technology, the research team has worked with growers and supply chain groups focused on production of quality fruit to use the technology to improve their product. For example, the technology has become integral to the success of the Calypso mango.

The project has not been without its challenges. An early business model collapsed due to the failure of Australian supply chains to provide reward for sweeter fruit and to changes within the world’s largest fruit grading manufacturer.

Research has continued with a focus on identification of fruit with defects, i.e. negative features rather than positive features such as sweetness.

Pilot commercial installations now exist in several apple pack houses, where sorting for internal browning occurs.

Fruit industry groups like Montague also seek commercial advantage with retailers through use of internal defect sorting.

Management of harvest time decisions and ultimate eating quality are related to internal parameters including carbohydrate (sugar) content and defects such as flesh browning.

Commercially, learning how to grow sweeter, as opposed to more, fruit has become significant. Interest in sweetness sorting has re-emerged within the citrus industry, which has a growing export market in Japan and Korea – markets that require and reward sweetness.

CQUniversity has been instrumental in these developments, working in concert with the engineers of CVS, and later French-based MAF Pty Ltd, for inline sorting technology, as well as those of Integrated Spectronics, then Felix Instruments incorporated, for the handheld unit.

The research group has also worked with various agronomic collaborators to develop protocols for the use of the technology within the production system, ultimately creating value in apple, citrus and mango supply chains.

The research that began in the mid-1990s with a local enquiry and in a modest confirmation of the work of Japanese researchers that NIRS could be used to sort high moisture, non-homogenous products such as fruit, has continued and now has global implications.

Other non-invasive technologies do exist, e.g. transmission X-ray imaging, magnetic resonance imaging, acoustic frequency methods, although the widespread commercial adoption in fruit sorting is yet to occur using such technologies.

Non-Invasive Assessment of Fruit - Improving Quantity and Quality

A research team, led by CQUniversity’s Professor Kerry Walsh, has been working in collaboration with fruit growers, horticultural industry bodies and technology-solution providers to develop technologies that can help farmers improve their yields and potentially automate on‑farm processes in the future.

CQUni 'A Leading Light' in Use of Near Infrared Spectroscopy, Says VIP Visitor

A world-renowned specialist in near infrared spectroscopy, Peter Flinn visited CQUniversity  for networking with researchers using NIR to gauge fruit quality.

CQUni Evaluates Fruit Maturity Sensors as Part of 'Rural R&D for Profit'

CQUniversity will draw on $600,000 in fresh funding to evaluate fruit maturity sensors, as part of a project resourced through the 'Rural R&D for Profit' program.