People Counting at Train Stations and Bus Stops
A public transport company engaged Blackbook AI to investigate technical solutions to understand people's movements at stations in order to improve safety and incident response.
The Challenge
A public transport company had limited insights into the number of people in or around Public Transport facilities due to the constant flow of patrons. This limited their ability to plan, respond, and generally maintain the efficiency and safety of the network in the event of routine works and during incidents. Blackbook AI was engaged to investigate technical solutions, including custom hardware and software, to utilise machine vision and machine learning methods to count people and generate timely insights to positively influence safety, efficiency, and incident response.
The Solution
Custom hardware and software solutions were explored, leveraging machine vision and machine learning methods to count people and generate timely insights.
Key components of solution:
- Utilised machine vision and machine learning methods to count people and generate timely insights
- Dedicated Edge Computing devices were installed to count people and return point-in-time counts
- Batched CCTV allowed for 15 different computer vision models to be trialed, and performances compared
The Outcomes
The solution allowed the Department of Transport and Main Roads to proactively plan and respond rapidly to changing conditions and incidents.
Key outcomes include:
- Developed edge-capable devices that count pedestrian traffic at bus stops and train stations, and fed data back for storage and display.
- Integrated infrared technology to count people in dark or shadowed areas.
- Implemented overlapping object detection and crowd density mapping methods to enhance accuracy.
- Uploaded data into dashboards, providing users with current, real-time insights, including peak demand times at stops and stations.
The Challenge
A public transport company had limited insights into the number of people in or around Public Transport facilities due to the constant flow of patrons. This limited their ability to plan, respond, and generally maintain the efficiency and safety of the network in the event of routine works and during incidents. Blackbook AI was engaged to investigate technical solutions, including custom hardware and software, to utilise machine vision and machine learning methods to count people and generate timely insights to positively influence safety, efficiency, and incident response.
The Solution
Custom hardware and software solutions were explored, leveraging machine vision and machine learning methods to count people and generate timely insights.
Key components of solution:
- Utilised machine vision and machine learning methods to count people and generate timely insights
- Dedicated Edge Computing devices were installed to count people and return point-in-time counts
- Batched CCTV allowed for 15 different computer vision models to be trialed, and performances compared
The Outcomes
The solution allowed the Department of Transport and Main Roads to proactively plan and respond rapidly to changing conditions and incidents.
Key outcomes include:
- Developed edge-capable devices that count pedestrian traffic at bus stops and train stations, and fed data back for storage and display.
- Integrated infrared technology to count people in dark or shadowed areas.
- Implemented overlapping object detection and crowd density mapping methods to enhance accuracy.
- Uploaded data into dashboards, providing users with current, real-time insights, including peak demand times at stops and stations.
