Its computational imaging improves infrared (IR) visibility in degraded conditions, while AI models trained on Teledyne FLIR OEM’s real and synthetic data help deliver accurate detections with fewer false positives. Prism AIMMGen™ supports rapid expansion to new target classes as mission needs evolve. Built for rapid integration, Prism Ground ISR supports Boson®+ and Neutrino® cameras, including continuous zoom models, plus select third-party IR and electro-optical (EO) sensors for scalable deployment.
With AI-powered detection, image enhancement, and flexible sensor integration in one stack, Prism Ground ISR helps teams field capability faster, detect threats earlier, and maintain reliable tracks with less operator burden across border surveillance, force protection, and other ground-based security missions.
AI-POWERED DETECTION AND CLASSIFICATION
Extend detection range, improve track persistence, and reduce false alarms for earlier, more confident responses
- Supports up to 15 object classes, including fine-grained foreign military vehicle classification
- Trained on EO and IR data to improve target recognition in cluttered environments
- Enables customer-specific models with Prism AIMMGenTM using synthetic data to adapt to new missions
IMAGE ENHANCEMENT FOR HIGH‑FIDELITY TRACKING
Maintains stable multi-object tracks with low fragmentation for small, fast, and maneuvering targets.
- Turbulence mitigation, dehazing, and super resolution enhance visibility in tough conditions
- Separate acquisition and tracking pipelines for earlier detection and more responsive tracking
- Tune tracking logic to mission needs for greater operational flexibility
BUILT FOR STREAMLINED INTEGRATION
Lower integration risk with global-production scale and trusted technology, tools, and support
- SDK includes C++ sample application and access via MQTT and REST API
- Accepts 14-bit data from Boson+, Neutrino, and third-party IR cameras
- Compatible with EO sensors, enabling multi‑sensor solutions
- Experienced technical services team to support integration
Specifications
Hardware
- Part Number
- 110-0201-91
Performance Metric
- Correlation Tracker
- ~25 Pixels on Target
- Included Filters
- Dehaze, Electronic Stabilization, and Turbulence Mitigation
- Inference Time
- ~10 ms
- Input Wavelength
- EO, MWIR, and LWIR
- Latency (Average Glass-To-Glass)
- ~90 to 150 ms @ 30Hz (to display output) depending on video pipeline configuration
- Latency to Track Initiation from First Observation
- ≤100 ms, Configurable to 1 Frame Delay (lower accuracy)
- Metadata Output
- Bounding Box Area
Bound Box Location
Category ID
Object Class Label
Confidence
Time Stamp
Track ID
Frame Number
- Moving Target Indication
- ≥4 x 4 Pixels on Target (minimum)
- Object Classes - Infrared and EO
- bmp-2,bmp-3, btr-80, T-72m2, chevrolet_s10_2003, toyota_rav4_2013, ford_bronco_1989, and jeep patriot with additional classes in Release 2
- Object Classification >60% Confidence
- ≥6 x 6 Pixels on Target (minimum)
- Simultaneous Targets Tracked
- Maxuimum is System Dependent, Default is 16, Configurable
- Target Detection Confidence Threshold
- ≥60% for Small Targets (<32 x 32 pixels), Configurable
System Requirement
- Deliverables
- User Graphical Interface (GUI)
Software Development Kit (SDK)
Technical Documentation
- EO Camera
- 4 MP with UVC Input Typical
(larger format will affect frame rate)
- Hardware
- NVIDIA ORIN NX/AGX
- IR Cameras
- Boson+ with UVC
Neutrino LC with USB
Neutrino SX8 with USB
- Power
- <12 W (average) <15 W (maximum)
- Video Output
- WebRTP, RTSP, and HDMI
Resources & Support
News articles and white papers written by Teledyne FLIR OEM experts to help you integrate your Teledyne FLIR OEM products.
For technical questions, find answers by visiting our FAQ at: flir.custhelp.com
Application Note
A Guide on Cost-Effective Thermal Lens Integration: What to Know for Defense and Autonomous Vehicle Applications
Learn more
Webinar
How to Optimize MWIR Performance and Computational Imaging to Simplify Integration
Watch now
Whitepaper
How to Use Automated Synthetic Data Generation in AI Model Development for Object Detection
Read the StoryAssets below are shared by all models in this product family.
Prism Ground ISR - Datasheet
Integrating Teledyne FLIR OEM thermal camera modules is easier than ever with our library of how-to videos and more!
Visit the Support Center for help with your Teledyne FLIR OEM products or submit a support ticket, by visiting our Technical Support Center.
Related Products
Prism AI
Object Detection and Tracking Software Libraries
- 40+ Detection Categories
- 4M Training Annotations
- Compatible with Qualcomm or NVIDIA
Prism C-UAS
Unmanned Aircraft System Detection and Tracking Software Stack
- Sub-2 × 2‑pixel small‑drone detection and tracking
- Multispectral‑trained AI delivers high‑confidence detection and classification
- Supports 14‑bit IR data
Prism ISP
Advanced Computational Image Processing Software
- Super Resolution, MSX, VividIR, and more
- Supports LWIR, MWIR, and Visible
- Compatible with Qualcomm or NVIDIA
Prism SKR
Integrated Seeker and Autonomy Software
- Accepts Thermal and Visible Imagery
- WOSA-Compliant Interfaces
- Compatible with Qualcomm or NVIDIA