See how it works
These performance metrics are for demonstrative purposes only, based on configurations with proven results. Actual performance may vary by setup. Our algorithms are optimized for use with any chip, platform, or sensor. Contact us for details.
update rate
Up to 10 Hz
initialization time
<10 seconds
Operating Range
Unlimited (environment-dependent)
Supported companion hardware
Nvidia Jetson, ModalAI Voxl2 / Mini, Qualcomm RB5, IMX7, IMX8, Raspberry PI
Supported flight controllers
PX4, APX4, Ardupilot
Basis-SW/OS
Linux, Docker required
Interfaces
ROS2
Input - Sensors
Any type of camera (sensor agnostic)
Input - Data
1) Camera's video frames
2) Intrinsic & extrinsic sensor calibration (optional)
Output - Data
Object position in video frame
Minimum
Recommended
RAM
2 GB
4 GB
Storage
20 GB
50 GB
Camera
320 x 240 px, 10 FPS
1920 x 1080 px, 30 FPS
The information provided reflects recommended hardware specifications based on insights gained from successful customer projects and integrations. These recommendations are not limitations, and actual requirements may vary depending on the specific configuration.
Our algorithms are compatible with any chip, platform, sensor, and individual configuration. Please contact us for further information.
visionairy®
object re-identification - IR | EO
A powerful solution for object re-identification in video streams—accurately matching target objects across scenes, even under changing perspectives.
Benefits
Lightweight and Efficient
Optimized to run on small, low-power devices without sacrificing accuracy.
Seamless integration
Integrates seamlessly with diverse camera sensors for maximum deployment flexibility.
Realtime Performance
Capable of re-identifying objects instantly in live video streams for responsive applications.
Performance Metrics
Position accuracy
±2.5 cm in typical environments
update rate
Up to 200 Hz
initialization time
<1 second
Maximum Velocity
20 m/s with full accuracy
Operating Range
Unlimited (environment-dependent)
Drift
<0.1% of distance traveled
Features
Our technology combines advanced AI models with flexible deployment to deliver reliable, real-time object tracking across cameras. Below are the core components that make our solution accurate, scalable, and ready for real-world use:
High Accuracy in Real-World Conditions - Works across varying lighting, angles, and occlusions to deliver consistent performance.
Flexible Sensor & Platform Support - Compatible with a wide range of camera types and deployment environments (edge, cloud, hybrid).
Fast, Scalable Performance - Real-time or near real-time identification that scales across large camera networks.
Privacy-Aware Design - No need for facial recognition or personally identifiable information — ideal for compliance-sensitive use cases.
Why Object Re-Identification - IR | EO?
Object Re-Identification - IR | EO (Re-ID) makes it possible to track the same person or object across multiple cameras, enabling smarter surveillance, retail insights, and mobility systems. It adds continuity and context that single-camera systems can't provide.
Our solution supports a wide range of camera sensors, platforms, and use cases. With optimized models and diverse datasets, we deliver accurate, flexible Re-ID performance across edge and cloud deployments.
Seamless multi-camera object tracking
Track objects with high accuracy, even as perspectives shift
Enable advanced surveillance, retail analytics, and mobility solutions
