- Working with the “Machine Vision for road safety and traffic management” project team, improve the safety and experience of road users by analysing CCTV data to provide additional information and decision support to Transport Operation Centres.
- Of particular interest is the possibility of processing some, or all, of the CCTV data of the “Machine Vision for road safety and traffic management” project through embedded vision systems to create a more resilient and scalable monitoring infrastructure by minimising data bandwidth.
- Investigate factors affecting the trade-offs between on-board image processing vision systems and ransmitting/analysing the data remotely. Design a prototype embedded vision system that reflects these trade-offs in collaboration with the “Machine Vision for road safety and traffic management” project team.
- The project team (the students and, optionally, supervising staff) will be expected to attend at least three meetings at the NZTA Innovation Zone: a project briefing, a progress update, and a project debrief.
- The project briefing will outline preferred development principles and technologies to be used for the project - e.g. Cloud first, GitHub code repository, build automation, DevOps, etc.
- Hardware for project 4 might include the Raspberry Pi3 platform, which supports tensorflow, (e.g. https://www.youtube.com/watch?v=BBwEF6WBUQs) or the Nvidia Jetson TK1 / TX1. (e.g. https://www.youtube.com/watch?v=MCmgfHjMIKg)
- The Student, Supervisor and/or the University must enter into a Privacy Protection Agreement with the Sponsor, prior to any Personal Information (as defined in section 2(1) of the Privacy Act 1993) being provided to the Student, Supervisor and/or the University for the purposes of the Research Project.
- Computer Systems Engineering
Allocated (Not available for preferences)
Lab allocations have not been finalised