Artificial Intelligence (AI), Computer Vision

Scooter Detection with AI and Computer Vision

About the project

Using AI for object training, detection, and tracking

Intranel created a solution to track, differentiate, and count different brands of scooters in public areas in real-time using only low-cost hardware.

A mock up of the laptop showing the capabilities of AI
Intranel employees are using AI tools to identify different brands of scooters

Why use local devices?

Detection, tracking, and counting had to be achieved at the local device level. We could have used a more conventional approach and send field video data to a central server for batch processing and analytics but it has several downsides:

  • Higher overall costs
  • Video requires high bandwidth
  • Privacy concerns from storing personally identifiable images centrally
  • No access to real-time data or analytics that is important for rapid decision making

Send only small snippets of data

The local processing means we only need to send small, anonymised data packets to a server. In this case, the numbers of different scooter brands crossing an area of pavement in a given time period.

The same process can easily be applied to any type of traffic—pedestrians, cyclists, cars, buses (or any mixtures of these), with data made available in real-time to upstream systems like traffic control centres.

Intranel is using Google’s beta Coral accelerator hardware in combination with a Raspberry Pi and camera module.

Run powerful AI applications, at 200$

The availability of cheap, low power compute boards like Raspberry Pi, and new hardware AI accelerator modules (in this case Google’s Coral inference engine) meant we could complete all computer vision and AI tasks on the field device, under $200.


What did we learn?

We were able to apply our model training processes to detect multiple types of scooters with high accuracy, with only a small sample set.

Training data came from hiring a set of scooters for a few hours and taking videos from multiple angles, from which still images were extracted.

We were able to apply our hardware-accelerated tracking algorithms to ensure higher recognition rates as the same object is tested multiple times, with a majority vote applied on the detected scooter type.

Let's work together

Ready to take your AI project to the next level? Get in touch with our team to get expert feedback and project estimates.

Ready to take the next step?

Book a free, no-obligation 40 min chat and meet our founder, Dave Sanders, to discuss your tech project and get expert feedback + project estimates.