VEHICLES

HERMES Vehicle Classifier

Model Overview

The CVEDIA HERMES Vehicle Classifier is a deep learning-based algorithm designed to correctly interpret vehicle type including busses, pickups, sedans, bicycles, and more. Performing from both a car-mounted and elevated perspective, HERMES is an asset for traffic data, security, and smart intersection applications, while conforming to a low power profile. HERMES can be regularly updated with newly released vehicles according to your requirements.

The HERMES model was built to reflect North American and European roads. Custom classes and classification parameters, including make and model, are available through CVEDIA solutions services.

Highlights

Performance

Optimized for edge performance with a low power profile

Range

300 metres

Conditions

Dawn to dusk

Environment

Environmentally-agnostic performance

About CVEDIA

CVEDIA is a pioneer in the use of synthetic data for machine perception. We use deep learning to create synthetic-based detection and classification algorithms. CVEDIA models actually outperform traditional models because synthetic data allows for feature-based design. That means our models are safer and quicker to market. Today we work with over 30 of the world’s largest companies on their most complex deep learning projects.

Every model is backed by an ongoing maintenance service, as well as the ability to customize and add to a model through our in-house development team. We’ll even help you deploy our models in your software stack. Contact us for more information.

Operating Specifications

FUNCTIONALITY

Detection

SENSOR MODALITY

Visible light

ARCHITECTURE

Backbone: Resnet-101, Detector: RefineDet

KERNEL INPUT SIZE

512×512

CVEDIA Services

Maintenance

Each CVEDIA model comes backed with an ongoing maintenance agreement. Our team is available for continuous improvements and to ensure upkeep. Reach out to us for more information.

Fine Grain Classification

Speak to our team to discuss vehicle classification as a service add on or as a separate model. CVEDIA’s in-house team will work with you to define your requirements, and build a synthetic-based model incorporating your classification specifications.

Additional Classes

CVEDIA models are built using proprietary synthetic data technology – meaning adding additional classes to your model is possible in a matter of weeks.

Use Cases

Smart Cities

Use HERMES as a reliable component of your smart intersection grid. HERMES performs with higher accuracy than traditional algorithms thanks to proprietary CVEDIA synthetic technology.

Traffic Data and Analytics

Calculate road usage analytics and highway traffic data using HERMES, with the ability to add new vehicle makes and models as they’re released.

Security

Quickly localize vehicles of interest using security camera grids with HERMES.

Vehicle ADAS

Use HERMES in your vehicle autonomy system to correctly classify vehicle size. HERMES has been developed to maintain a low power profile, making it perfect for battery-powered vehicles and applications.