Kent, Mathew (2018) Machine vision and data acquisition for the optimisation of black soldier fly breeding. [USQ Project]
Abstract
This paper details research into the field of insect rearing for use as animal feed and specifically how modernised machine vision and environmental data acquisition methods may be able to improve insect larvae production rates and increase the overall success of a farmed insect colony. The target animal in which rearing is to be studied is the black soldier fly officially known as Hermetia illucens. Literature surrounding the rearing of the black soldier fly has been reviewed to establish the current methods for rearing and known setbacks surrounding what is required to achieve successful breeding.
Since computer vision can be computationally expensive its uptake in emerging fields (such as insect farming) is generally slow. However now due to the wide spread availability of cheap, powerful and mobile computing power computer vision applications are now something to be considered with the imagination being the only bottleneck. When we think computing power it’s natural to picture a scientific computer locked in a climate controlled room, but all we need to do is look at our mobile phone and other connectivity devices for what a mini super computer looks like. These same devices house an array of useful sensors for detecting the state of the world around them whilst also being packed with a high detail optical camera. This study sets out to determine if a packaged combination of a high detail camera, an array of environmental sensors and a mini super computer can provide a platform for a novel approach to low cost machine vision and environmental data acquisition in the insect rearing sphere. To implement the methodology of this study a machine vision and data acquisition system was successfully developed integrated into a mobile phone. Logging of the phones environmental sensors and counting of breeding flies within an image were performed to a high degree of accuracy on a real world device.
This dissertation outlines the reviewed literature, the perceived knowledge gaps, the aims and objectives of the research, research limitations and the final results of the study. The promising research results of this project lay a foundation for further research into the application of machine vision and data acquisition technology, specifically within a live operating black soldier fly farm.
|
Statistics for this ePrint Item |
| Item Type: | USQ Project |
|---|---|
| Item Status: | Live Archive |
| Faculty/School / Institute/Centre: | Historic - Faculty of Health, Engineering and Sciences - School of Mechanical and Electrical Engineering (1 Jul 2013 - 31 Dec 2021) |
| Supervisors: | Banhazi, Thomas; Helwig, Andreas |
| Qualification: | Bachelor of Engineering (Honours) (Mechatronic) |
| Date Deposited: | 30 Aug 2022 00:03 |
| Last Modified: | 29 Jun 2023 01:47 |
| Uncontrolled Keywords: | Hermetia illucens; black soldier fly; machine vision; environmental date acquisitions |
| URI: | https://sear.unisq.edu.au/id/eprint/40684 |
Actions (login required)
 |
Archive Repository Staff Only |
