Make and Model Recognition (MMR)

Highlights

11 categories
295 makes
2294 models
6075 generations
9 TAGs
front + rear views
day + night light

Accuracy & Performance

99% category
98% make and model
95% generation & variation
4 ms GPU speed

Our AI based software analyses vehicle appearance and recognizes vehicle category, make, model, generation, variation, TAG and colour. It processes front and rear images taken in both day and night light conditions.

Typical applications: toll systems, traffic safety and surveillance systems, law enforcement, entrance and parking systems, police and governmental applications, traffic infrastructure planning systems, smart cities and others.

TAG recognition

Since the 2022/12 release of MMR SDK 2.20.0, we also recognize additional vehicle features called TAGs.

ambulance
law enforcement
fire brigade
caravan
pickup
push bumper
rear mount
wood truck
animal transport

What's new in version 2.21.0

The new version of MMR allows you to enter a reference position with the bounding box of the vehicle. This solution allows vehicles to be analysed even at very low resolution and under poor conditions when licence plates cannot be reliably detected. It also means that vehicles that do not have a licence plate at all can be classified. The advantage of this solution is that the MMR product can be used separately without the ANPR software. As always, the new version of MMR is expanded to include car models placed on the market between releases.

Feature Product type
SDK Embedded SDK REST API Server
Recognition Category + Make + Model + Generation + Variation + Color + Tags
Camera View Frontal + Rear
Regions Europe, Middle East, North America, Asia&Pacific, South Africa
Target Implementation Cameras & Computer connected cameras Customer Proprietary Applications Service on Demand at client site
Supported Platforms
  • Windows (Win32 & x64)
  • Unix (x86_64 & AArch64)
  • CPU / GPU
    • *other on request
  • Windows (Win32 & x64)
  • Unix (x86_64 & AArch64)
  • CPU / GPU
    • *other on request
  • Docker image
  • Ubuntu x86_64
  • CPU / GPU
    • *other on request
    License type Time unlimited license with 12 months support (extendable)
    Performance 4 ms per vehicle on GPU, 8 ms on CPU, see technical sheet for details
    Accuracy
  • Category > 99 %
  • Make and model > 98 %
  • Generation and variation > 95 %
  • Color > 80 %
    • *in normal daylight conditions
    Online Demo Yes, available here
    *you can also request offline demo

    In action

    Try our ONLINE DEMO or ...

    Contact us

    Our references