Category: Research Grant

New Article:Development of a robotic and computer vision method to assess foam quality in sparkling wines.

Abstract
Quality assessment of food products and beverages might be performed by the human senses of smell, taste, sound and touch. Likewise, sparkling wines and carbonated beverages are fundamentally assessed by sensory evaluation. Computer vision is an emerging technique that has been applied in the food industry to objectively assist quality and process control. However, publications describing the application of this novel technology to carbonated beverages are scarce, as the methodology requires tailored techniques to address the presence of carbonation and foamability. Here we present a robotic pourer (FIZZeyeRobot), which normalizes the variability of foam and bubble development during pouring into a vessel. It is coupled with video capture to assess several parameters of foam quality, including foamability (the ability of the foam to form) drainability (the ability of the foam to resist drainage) and bubble count and allometry. The foam parameters investigated were analyzed in combination to the wines scores, chemical parameters obtained from laboratory analysis and manual measurements for validation purposes. Results showed that higher quality scores from trained panelists were positively correlated with foam stability and negatively correlated with the velocity of foam dissipation and the height of the collar. Significant correlations were observed between the wine quality measurements of total protein, titratable acidity, pH and foam expansion. The percentage of the wine in the foam was found to promote the formation of smaller bubbles and to reduce foamability, while drainability was negatively correlated to foam stability and positively correlated with the duration of the collar. Finally, wines were grouped according to their foam and bubble characteristics, quality scores and chemical parameters. The technique developed in this study objectively assessed foam characteristics of sparkling wines using image analysis whilst maintaining a cost-effective, fast, repeatable and reliable robotic method. Relationships between wine composition, bubble and foam parameters obtained automatically, might assist in unraveling factors contributing to wine quality and directions for further research.
Fig-1-Diagram-illustrating-the-procedure-used-for-quantifying-foam-parameters-by-using
Pourer

Research from VoF will be applied to the streets of Melbourne!

Monitoring the Green Infrastructure of Cities by integrating an automated IoT robotic system on top of public transport and cloud computing.

Funding body: Melbourne Networked Society Institute.

BUS

Climate Change have resulted already in heat wave events becoming more frequent and severe in Australian cities and have put significant pressure into developing efficient systems to maintain and increase the urban green infrastructure to avoid tree dieback and eventually complete loss of urban trees. This effect can increase the “urban heat island effect” and its associated detrimental consequences for the society’s wellbeing and biodiversity of cities. Currently, there are no systematic tools to monitor the green infrastructure of cities to respond efficiently and in timely manner to demands imposed by the changing environment on urban trees.

This project proposes the integration of a monitoring tool and decision-making system based on infrared/visible robotic cameras mounted on top of buses and public service vehicles from cities, such as trams (Figs. 1 & 2 named as IR-Busmonitor). The main aim of the system is to obtain geo-referenced upward-looking imagery using internet of things technology (IoT) for data capture and transmission. Cloud computing and developed algorithms will be then used to obtain physiological information from tree canopies to create high temporal and spatial resolution information from the urban green infrastructure. The system will allow to: increase in the long term the green infrastructure of cities, offset carbon emissions by public services, carbon sequestration, recreational places for the public, ameliorate detrimental heat wave effects on population and biodiversity and decrease heating/cooling costs for the public through understanding the risk and resilience of green infrastructure in response to heat waves. The major novelty of the system proposed is that it will effectively transform public transport and service vehicles from cities into networked monitoring robots at affordable costs compared to alternatives, such as satellite imagery acquisition and analysis and the use of drones or unmanned aerial systems (UAS). The latter been highly regulated within urban environments through the Civil Aviation Safety Authority (CASA) and perceived by the public as invasive of privacy and security. This project also addresses specific activities, such as water and urban futures with emphasis in the application to novel adaptation strategies to climatic anomalies, such as heat wave events to be available to urban environments, the use of pervasive information through integrative technology and entrepreneurship by developing a novel product and service that can be easily replicated in major cities within Australia and around the world.

Expected Project Outcomes

One of the biggest challenges in the future for urban communities is to decrease detrimental effects of the Urban Heat Island effect and extreme events such as heat waves. Inadequate or inefficient management of the green infrastructure leads to tree dieback and complete loss of trees, associated to high costs for councils and community to replace them to the pre-mortality growth level. This funding will help understanding the short and long term effects of events mentioned before on the green infrastructure of the cities and provide an integrated system for city councils to acquire data, automatically analyse it and have processed information readily accessible for decision making and management. Specifically, maintaining and increasing the green infrastructure from cities offers a wide range of benefits to the communities and the environment, such as:

Decreasing:

  • Death rates in heat-waves for people over 65 years old
  • Respiratory problems on people below 16 years old
  • Tree dieback
  • Stress of aquatic ecosystems by degreasing temperature of storm water
  • Heating and cooling costs for inhabitants in general
  • Run-off and therefore erosion
  • Individual on-site inspection of treesIncreasing:Due to the versatility and network based concept of the system proposed, the number of people that can be benefited will be according to the general population of cities in which the system is put into practice with a national impact considering major cities in Australia.

The Digital Vineyard: Opportunities for Grape growers in Australia and the World

From: MNSI website.

Wine is one of Australia’s chief exports. Australia is the world’s fifth largest exporter of wine and the seventh largest producer of wine in the world. The wine industry is a significant contributor to the Australian economy. Growing conditions are, however, predicted to change with higher average temperatures, water scarcity and more pressure on land use from a growing population. The result is that wine makers will need to manage resources much more efficiently without comprising wine quality.

In the vineyard of the future, growers will use data from in-ground sensor and drones flying overhead taking multi-spectral images to better manage their crops and the environment within their vineyards. The ground sensor data and aerial imagery can be combined into metrics that growers can easily use to make decisions about growing conditions and when and where to irrigate and apply fertiliser. This is a form of precision agriculture that can target anything from larger blocks within a vineyard to small collections of plants that may need special attention.

This project takes a significant step towards this vision by developing the algorithms and software to acquire, combine, analyse and disseminate data from in-ground sensors and the multi-spectral images taken from drones. In-ground sensors provide a wealth of data about the condition of the soil such as the soil temperature, soil moisture content, salinity, pH levels and some other factors, while drones map valuable metrics for growth, early symptoms of undesirable plant health conditions, and indicators for fruit quality.

The project is developing key elements of sensor network and camera calibration, research and methods for combining the data from the different types of sensors and developing data analysis methods that will provide actionable metrics for growers. Development will focus on designing a standardised optical sensor calibration procedure, automated optical image geo-referencing and ortho-mosaic generation, dissemination and visualisation to end users.

Aerial and ground data will be collected from the Curly Flat vineyard in Lancefield (Victoria), Wynns Coonawara Estate vineyard (Treasury Wine Estates) in South Australia and Murray Valley Winegrowers vineyard in Victoria. The output will be able to produce metrics as well as clear visualisations of the winery overlaid with meaningful data.

Drone images by Teagan Glenane.

RESEARCH TEAM

  • Ed Kazmierczak – Department of Computing and Information Systems
  • Dongryeol Ryu – Department of Infrastructure Engineering
  • Sigfredo Fuentes – Department of Agriculture and Food Systems
  • Richard Collman – V3 Alliance
  • Mark O’Connell – Department of Economic Development, Jobs, Transport and Resources