Leveraging 3D computer vision for camera-based precise geo-localisation. This project aims to develop advanced 3D computer vision and image processing technology that can turn regular cameras into high-precision location-sensing devices. Spatial Location is a fundamental type of information of our physical world. Determining the precise location of people, vehicle, and mobile devices is essential for many critical applications. Outcomes of the project will enable a wide range of novel applicatio ....Leveraging 3D computer vision for camera-based precise geo-localisation. This project aims to develop advanced 3D computer vision and image processing technology that can turn regular cameras into high-precision location-sensing devices. Spatial Location is a fundamental type of information of our physical world. Determining the precise location of people, vehicle, and mobile devices is essential for many critical applications. Outcomes of the project will enable a wide range of novel applications of significant social, environmental and economic value, such as Location-Aware Service, Environment Monitoring, Augmented Reality, Autonomous Vehicle, and Rapid Emergency Response. The project will enhance Australia's international competitive advantage in forefront of ICT research and technology innovation.Read moreRead less
Developing key vision technology for automation of aquaculture factory. This project aims to investigate structural, coloured textural, and hyperspectral analysis approaches to achieve automated lobster molt-cycle staging and classification to the level required for commercial production. High labour cost, water contamination, and disease transmission are major barriers in Australian bay lobster aquaculture inhibiting its large scale production. Automation of the production process and reducing ....Developing key vision technology for automation of aquaculture factory. This project aims to investigate structural, coloured textural, and hyperspectral analysis approaches to achieve automated lobster molt-cycle staging and classification to the level required for commercial production. High labour cost, water contamination, and disease transmission are major barriers in Australian bay lobster aquaculture inhibiting its large scale production. Automation of the production process and reducing the human contact with animals are of high priority in the development of this Australian-led emerging industry. The project aims to develop technology to bring this world- first aquaculture factory to large scale production, and create new export opportunities for lobsters and production systems.Read moreRead less
Clarence River Green Prawn Market Diversification Assistance Measures
Funder
Fisheries Research and Development Corporation
Funding Amount
$165,000.00
Summary
The Clarence River Region is known for its high-quality prawn markets. The region was kept profitable during COVID restrictions due to a significant portion of the fisher directing its product to the highly profitable bait market. This diversification away from the consumer market has ensured stability for the region. Many fishing businesses pivoted their strategies to meet this new buyer to the region. The loss of the uncooked prawn market in the Clarence region will therefore destabilize t ....The Clarence River Region is known for its high-quality prawn markets. The region was kept profitable during COVID restrictions due to a significant portion of the fisher directing its product to the highly profitable bait market. This diversification away from the consumer market has ensured stability for the region. Many fishing businesses pivoted their strategies to meet this new buyer to the region. The loss of the uncooked prawn market in the Clarence region will therefore destabilize the industry. The restriction of uncooked prawn trade therefore must be addressed through market research, diversification and activation. However, there is immediate need for alternative markets so an intense focused market activation and access is the key. PFA has identified key market persons that can create links between industry and high-end chefs to: 1. Identify alternative market uses that fall within the quarantine requirements 2. Start immediate market trials and activation 3. Review online presence and build industry skills to improve online presence for sales • It is intended that this will lead into immediate supply agreements to these alternative markets that will in turn remove burden on the existing cooked prawn market
Objectives: 1. To identify and trial supplies of Clarence River prawns to alternative market 2. To activate alternative markets to reduce negative impact of trade restriction to the Clarence River region 3. To build skills within local fishers to build online presence Read moreRead less
Declarative Networks: Towards Robust and Explainable Deep Learning. The aim of this project is to develop declarative machine learning techniques that exploit inherent structure and models of the world. Deep learning has become the dominant approach for machine learning with many products and promises built on this technology. But deep learning is expensive, opaque, brittle and relies solely on human labelled data. This project intends to make deep learning more reliable by establishing theory a ....Declarative Networks: Towards Robust and Explainable Deep Learning. The aim of this project is to develop declarative machine learning techniques that exploit inherent structure and models of the world. Deep learning has become the dominant approach for machine learning with many products and promises built on this technology. But deep learning is expensive, opaque, brittle and relies solely on human labelled data. This project intends to make deep learning more reliable by establishing theory and algorithms that allow physical and mathematical models to be embedded within a deep learning framework, providing performance guarantees and interpretability. This would likely benefit machine learning based products that can understand the world and interact with humans naturally through vision and language.Read moreRead less
Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance witho ....Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.Read moreRead less
Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces an ....Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces and system dynamics. Both theoretical and algorithmic approaches will be applied to sustainable fishery management --- an important problem for Australia and an ideal context for POMDPs. The project will advance research in artificial intelligence, dynamical systems, and fishery operations, and benefit the national economy.Read moreRead less
Improving Southern Rock Lobster On-vessel Handling Practices, Data Collection And Industry Tools For Lobster Quality Assessment
Funder
Fisheries Research and Development Corporation
Funding Amount
$538,604.00
Summary
The export of Southern Rock Lobster (SRL) from Southern Australia to international markets is one of Australia's most valuable fisheries. There are increasing trends in post-harvest mortality of SRL confirmed by the recent Fisheries Research and Development Corporation project (FRDC 2016-235). This is costing the industry millions due to stock losses, decreased consumer confidence in product quality and reputational damage to the SRL market brand. The causes of this increased post-harvest mortal ....The export of Southern Rock Lobster (SRL) from Southern Australia to international markets is one of Australia's most valuable fisheries. There are increasing trends in post-harvest mortality of SRL confirmed by the recent Fisheries Research and Development Corporation project (FRDC 2016-235). This is costing the industry millions due to stock losses, decreased consumer confidence in product quality and reputational damage to the SRL market brand. The causes of this increased post-harvest mortality are inconsistent across the industry sector with a range of factors implicated including environmental stressors, novel health conditions, and sub-optimal post-harvest practices. Results from (FRDC2016-235) indicate a need to optimise live lobster management processes across the entire post-harvest chain of custody in-order to minimize lobster mortality and enhance the economics of the SRL fishing and processing industry sectors.
The FRDC SRL live holding project (2016-235) conducted an analysis of the processing industry sector practices and provided guidance for best practices. These recommendations have been welcomed by the industry and further consultation has identified a critical need to extend this approach to the fishing component of the industry.
This project will address these key industry priorities and conduct an analysis of on-vessel live lobster handling and holding practices, quantify the impact of systems and practices on lobster quality and provide recommendations on improving on-vessel post-harvest practices. The current FRDC traceability project (FRDC 2016-177) is trialing a range of traceability technologies that this proposed new project will extend and enhance on-vessels to strengthen the capture, monitoring, and analysis of post-harvest data on lobster welfare, quality, and handling practices.
This project will also extend the development of practical and easy to use tools for the evaluation of lobster health including the handheld lactate meter and refractive index. Building evidenced-based approaches to measuring health and stress will provide all industry sectors with improved measurement of quality, animal welfare, and sustainability at all points in the supply chain.
Objectives: 1. Investigate the impacts of on-vessel handling and maintenance practices on live SRL post-harvest performance 2. Develop practical tools for the improved management of SRL industry live lobster operations (ie hand-held lactate meter and refractive index including thresholds for poor lobster performance) 3. Extend findings to the SRL industry (best practice guides and workshops) and incorporation of results into the SRL Clean green program. Read moreRead less
Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global com ....Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global competitiveness. Expected outcomes of this project will help to break the communication barriers between the Deaf and hearing population. This should provide significant benefits to Deaf communities through enhanced communication and improved quality-of-life, leading to a fair, more inclusive and resilient Australian society.Read moreRead less
Assessing The Benefits Of Sea Urchin Processing Waste As An Agricultural Fertiliser And Soil Ameliorant
Funder
Fisheries Research and Development Corporation
Funding Amount
$199,996.00
Summary
The primary need of this project is to facilitate a profitable Longspined Sea Urchin fishery to move the industry away from subsidies. A large-scale sustainable fishery is seen as the most feasible and sustainable way to apply downward pressure on the rapidly expanding Sea Urchin population in Tasmania. Longspined Sea Urchin populations have grown to some 20 million (5,500 tonnes) and have resulted in 15% of the Tasmania East Coast reefs becoming unproductive urchin barren, up from 3% 15 years ....The primary need of this project is to facilitate a profitable Longspined Sea Urchin fishery to move the industry away from subsidies. A large-scale sustainable fishery is seen as the most feasible and sustainable way to apply downward pressure on the rapidly expanding Sea Urchin population in Tasmania. Longspined Sea Urchin populations have grown to some 20 million (5,500 tonnes) and have resulted in 15% of the Tasmania East Coast reefs becoming unproductive urchin barren, up from 3% 15 years ago.
Subsides for the Longspined Sea Urchin harvest commenced in 2016 and in the last 3 years some $500,000 has been spent. This initiated significant investment in the industry to facilitate export market establishment and resulted the 2019 harvest reaching an excess of 550 tonnes, now Tasmania’s 3rd largest wild fishery by weight. However, the industry needs to move away from subsides and waste utilisation is seen a viable option to turn a current financial cost (estimated at $80,000 in 2019 to dump 400 tonnes of waste generated) into an income stream.
FRDC 2016-208 highlighted the significant potential of sea urchin waste utilisation in the agricultural industry and called for commercial upscaling of trials. This project is designed to meet that need. Based on this, the Abalone Industry Reinvestment Fund (AIRF) has committed to providing $538,686 in kind to initiate the project. This whole of project application is to allow multi-season agricultural trials of waste products to obtain scientifically and industry meaningful results, allow testing on perennial crops (such as cherries) and to employ a dedicated post-doctoral researcher on the project.
In the push for sustainably produced food, agricultural industries are demanding alternative nutritional sources to synthetic fertilisers. Urchin waste is comprised of two major parts: gut waste - a nitrogenous rich liquid which can be converted in a stable drench or spray and; shell waste – a calcium and boron rich solid which can be dried and powdered for use as a soil ameliorant. As such this fisheries enhancement project will additionally for fill this agricultural need.
Objectives: 1. To develop commercial scale processing equipment of sea urchin waste. 2. Determine the nutrient composition and plant bioavailability of nutrients from two high throughput waste streams: liquid gut waste and dried powdered shell waste 3. Evaluate the agronomic benefits of liquid gut waste as a frost retardant in perennial tree cropping (cherries) 4. Evaluate the agronomic benefits of powdered shell waste as a soil ameliorant in a wide range of annual and perennial cropping systems 5. Undertake a cost benefit analysis comparing fertiliser products (foliar sprays and/or soil conditioners) from this work to other products on the market to assess if the products are commercially viable Read moreRead less
Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored ....Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored to individual characteristics. The success of this project could significantly advance the fundamental research in image analysis. Expected outcomes include new knowledge and algorithms for image analysis, which could benefit fields like biology and archaeology, where labeled images are hard to attain and scarce.Read moreRead less