Description:

• Improve the safety and experience of road users by analysing CCTV data to provide additional information and decision support to Transport Operation Centres.
• Currently, key information on speed, and (to an extent) vehicle type, are provided by induction loops embedded into the road at strategic points. CCTV data should be able to provide similar information (which can be validated against loop data), as well as additional information - such as lane-keeping and wrong-way-driving detection, richer vehicle classification, tracking individual vehicles from one CCTV camera to another, and congestion/incident/crash detection. 
• Build on existing libraries e.g. using TensorFlow, to analyse CCTV data from our CCTV test-site to generate insights and decision support for Traffic Operation Centres. Vehicle count and speed should be validated against loop data.

Constraints

• 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.
• 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.

Type:

Undergraduate

Outcome:

Prerequisites

None

Specialisations

• Computer Systems Engineering
• Electrical and Electronic Engineering

Categories

• Transport Technology

Supervisor

• Mark Andrews

Co-supervisor

• Morteza Biglari-Abhari

Team

Allocated (Not available for preferences)

Lab

Lab allocations have not been finalised