Jawney, Andrew (2023) MM-Wave Assisted Automatic Camera Tracking System. [USQ Project]
![[img]](https://sear.unisq.edu.au/style/images/fileicons/text.png) |
Text (Project – redacted)
Jawney_A_Tobias_Low_Redacted.pdf Download (6MB) |
Abstract
Each day there are a great deal of presentations or performances occurring in front of audiences all around the world. These events are often recorded by a person aiming a camera or in other cases the camera will have an automatic tracking system. Having a dedicated camera person will usually achieve excellent tracking performance, however this task is tedious and focus can easily be diverted. For this reason camera tracking systems have been developed to automate this process. These existing tracking systems can often get distracted with movements in the audience or poor lighting conditions. Usually, machine vision is the main mechanism used for this camera tracking. However, these methods are computationally expensive and cannot operate effectively in all lighting conditions.
To address these issues, the idea of pairing a mm-wave sensor with a camera tracking system was conceived. These sensors are immune from any visual obstructions like low light, smoke or glare. Previous research has successfully used a mm-wave sensor to detect, count and monitor the positions of people in software (Huang et al. 2021). However the final step in pairing this to a physical camera tracking system has never been done. This research gap is where the final year project will be focused. The aim is that an automatic camera tracking system will be developed which is able to successfully track a speaker, with lower computation requirements while performing better in more extreme lighting conditions. This project will also attempt to answer the question of whether the idea of pairing a mm-wave sensor with a camera tracking system is advantageous when compared to existing methods.
To determine the answer to this question, a new type of camera tracking system which uses a mm-wave sensor will be developed and compared to an existing system. This project requires many steps to achieve these goals; these first few steps will be similar to the methods used in the research identified. Building on this, more algorithms need to be developed to interface with the motors inside the camera gimballing hardware to allow smooth tracking. Once a system is operational, some degree of software and hardware refinement will be performed to improve the design. Finally the developed camera tracking system will be compared head to head with another camera tracking system and some key performance characteristics will be measured. These results will be interpreted and the findings will be discussed in the dissertation.
|
Statistics for this ePrint Item |
| Item Type: | USQ Project |
|---|---|
| Item Status: | Live Archive |
| Faculty/School / Institute/Centre: | Current – Faculty of Health, Engineering and Sciences - School of Engineering (1 Jan 2022 -) |
| Supervisors: | Low, Tobias; Lobsey, Craig |
| Qualification: | Bachelor of Engineering (Mechatronic) |
| Date Deposited: | 29 Sep 2025 22:58 |
| Last Modified: | 29 Sep 2025 22:58 |
| Uncontrolled Keywords: | camera tracking system; mm-wave sensor |
| URI: | https://sear.unisq.edu.au/id/eprint/52960 |
Actions (login required)
 |
Archive Repository Staff Only |
