2023 HDR Curtin round - Integrated Wearable Sensor Data Acquisition and Analytics for Livestock Monitoring using UAVs
Applications open: 8/07/2022
Applications close: 18/08/2022
About this scholarship
The global consumption of food and other products harvested from animals rises by 7% every year. It indicates that the number of livestock will have to increase steadily. It urges the improvement in livestock management methods to keep up with this demand and the development of automated techniques to support the farmers. Australia is currently rebuilding the state in terms of livestock, as it is recovering from its lowest levels in two decades brought on by relentless drought. To stay competitive in the global market, Australia needs to increase the number of livestock it produces, which significantly depends on intensive livestock management. Nevertheless, it is critically vital and challenging to accomplish such a need, especially considering climate change, receding water levels, and shrinking arable land. As climate change intensifies, the risk of disease, heat stress, and other health issues will increase among the livestock, leading to economic losses. Thus it creates a greater urgency to identify health issues and disease outbreaks pre-emptively by monitoring livestock in real-time through an environmentally sustainable solution.
In the context of Australia, due to its unique geographical distribution, it is difficult for farmers to monitor animal health and welfare closely. There is a need for innovative and autonomous solutions to keep up with demand in the agricultural industry. According to International Food Policy Research Institute, data-driven techniques are able to help us achieve this goal by increasing farming productivity by as much as 67% and cutting down agricultural losses. The use of wearable sensors such as collars to monitor livestock has gone beyond research, and the industry is growing to commercialise this research. These sensors are able to generate characteristic signals modelled to infer animal behaviour, health conditions, birth difficulty and other essential phenomena that could be used for effective management decisions. The data is usually generated at a very high frequency and stored onboard. Due to the remote nature of commercial farms with a lack of network coverage and infrastructural support, limited battery life, and limited transmission capability of the sensors, the data nowadays is either analysed offline, or only a summary is transmitted in real-time for processing. For example, CSIRO has developed a cattle collar used to analyse cow movement using four inbuilt sensors: an accelerometer, gyroscope, GPS, and magnetometer. However, such sensory raw data get discarded as soon as it is processed on the collar. The recent versions of these collars can store sensor data on a chip, which needs to be manually removed and replaced from the collar on the cow as it can only store them for roughly a week.
Therefore, it is required to develop an improved way of collecting and analysing the data that does not require manual removal and can harvest the raw data to be processed later. Hence, it is necessary to access the complete data set that is collected in near-real-time for decision making in urgent situations (e.g., birth difficulty requires immediate attention). Consequently, the autonomous system will improve the productivity and welfare of livestock by detecting sick animals and intelligently recognising room for improvement.
In this case, to offer such an integrated wearable sensor data acquisition and analytics platform for livestock monitoring, this project proposes using Unmanned Aerial Vehicles (UAVs) as an effective solution. It will deploy UAVs to fly on the farm periodically and detect the livestock with collars using computer vision algorithms. The UAVs then fly in close proximity to the animals and establish communication with their wearable sensors. UAVs will also pull out the raw data at high speed and transmit it to the Cloud for further analysis. Data analytics methods will run in real-time at the cloud data centre to infer valuable phenomena and alert the farmers if urgent action is necessary. This near-real-time data acquisition and decision making can save the farmers a lot from the economic loss.
The specific objectives of this project are to:
• Design an efficient communication framework for UAV aided sensor data acquisition and analytics in a smart agricultural field,
• Investigate the optimal number of UAVs and proper configuration of UAVs to deploy in the smart agricultural field, reducing the production cost of the farmers,
• Design and develop an efficient computer vision algorithm for detecting livestock in real-time by UAVs,
• Develop a robust path planning algorithm for the UAVs to offer faster movement towards the livestock for sensor data collection,
• Evaluate the proposed framework and algorithms' performance by a proof-of-concept demonstration on the real testbed and commercial smart agricultural field.
An Internship opportunity may also be available with this project.
- Future Students
Faculty of Science & Engineering
- Science courses
- Engineering courses
- Western Australian School of Mines (WASM)
- Higher Degree by Research
- Australian Citizen
- Australian Permanent Resident
- New Zealand Citizen
- Permanent Humanitarian Visa
- International Student
- Merit Based
The annual scholarship package (stipend and tuition fees) is approx. $60,000 - $70,000 p.a.
Successful HDR applicants for admission will receive a 100% fee offset for up to 4 years, stipend scholarships, valued at approx. $28,800 p.a. for up to a maximum of 3.5 years, are determined via a competitive selection process. Applicants will be notified of the scholarship outcome in November 2022.
For detailed information, visit: Research Training Program (RTP) Scholarships | Curtin University, Perth, Australia.
All applicable HDR courses
We are looking for a graduate in either Computer Science, Software Engineering, Mechatronic Engineering, Electrical and Computer Engineering with good programming and modeling skills.
If this project excites you, and your research skills and experience are a good fit for this specific project, you should contact the Project Lead (listed below in the enquires section) via the Expression of Interest (EOI) form.
Eligible to enrol in a Higher Degree by Research Course at Curtin University by March 2023
To enquire about this project opportunity that includes a scholarship application, contact the Project lead, Associate Professor Aneesh Krishna via the EOI form above.