Computer vision for advanced rider assistance system
An advanced system designed to provide real-time alerts for various road threats, ensuring safer travel for all users.
Vehicle safety
Computer vision
Ongoing
A system for real-time alerts against road threats
For riders
With the help of computer vision, the ARAS is able to provide real-time alerts about potential accidents and road threats.
For fleet management
Computer vision helps organizations using the ARAS monitor their fleet and optimize their logistics operations.
Project Idea
A well-funded startup providing an Advanced Rider Assistance System (ARAS) for motorcycle riders partnered with Yellow to improve their existing solution with computer vision. They aimed to achieve higher model accuracy and optimize resource efficiency.
The client had
Functional solution verified by several major companies like Coca Cola and IBM. Need for computer vision improvement.
What we did
We increased accuracy, reworked the essential models, and enabled a smooth transition to a specialized edge AI environment.
Compliance Strengthening
The AI-powered screening tool aids in compliance efforts by ensuring comprehensive monitoring of money laundering references.
Product Functionality
Proven safety
The solution was tested by thousands of motorcycle riders in both general and extreme weather conditions so the ARAS safety is proven to be effective.
360° detection
AI-based computer vision helps the system analyze real-time footage and detect all possible threats around the vehicle.
Top-tier technology
The ARAS uses computer vision, data analytics, and cloud technologies to provide the best user experience.
Non-intrusive alerts
With the help of timely and nondisturbing alerts, the rider has enough time to react and avoid threats.
Tech Stack
Here’s a list of technologies we worked with on the project.
Development Challenges and Solutions
How our team coped with a range of development challenges.
Enhancing safety monitoring
Challenge: We needed to improve the accuracy of the front collision prevention module’s safety monitoring.
Solution: We used the XGBoost model for the task. The new model is optimized for better threat detection: Compared to the previous version, it now operates with 40 carefully selected features, and the core accuracy metrics increased up to 10%.
Model optimization
Challenge: The client wanted to upgrade the Detection & Classification module for better efficiency.
Solution: We optimized detection and classification models within the pipeline with the help of transitioning to more advanced architectures and applying targeted optimizations. The latest versions now consume 50% fewer resources while maintaining performance metrics.
Migration to an edge AI solution
Challenge: We needed to help the client migrate their solution from Jetson platform to Hailo AI.
Solution: We assisted in model conversion and adaptation for computer vision tasks. Our team also participated in extensive testing to ensure high performance on the new hardware. The migration aimed at reducing power consumption while maintaining real-time processing capabilities. As a result, it boosted system efficiency enough to enable smooth deployment and high accuracy in resource-constrained environments.
Results and Future Plans
The model’s accuracy is increased, while resource consumption is optimised.
Experience the system in action during an actual traffic scenario
Planned: Experiments with detector and classifier models to continue improving accuracy of detection.
Planned: Adapting the software to the new hardware the device has been recently moved to.
Planned: Correct device reaction in border cases (for instance, vehicle in the next lane should not trigger an alert).