Prism™ ISP is a collection of image signal processing (ISP) software libraries that include super-resolution, electronic image stabilization, image fusion, turbulence mitigation, noise reduction, and more. Compiled to run on low-power embedded processors from Qualcomm and NVIDIA, enabling developers to bring computational imaging to the edge while improving performance, lowering development costs, and shortening time to market.
Prism ISP is compatible with Teledyne FLIR market-leading thermal cores including Boson®, Tau® 2, Hadron™, and Neutrino®. The ISP libraries enable integrators to leverage high-performance ISP algorithms that dramatically enhance the viewed image quality and AI capabilities of world-class infrared camera modules for defense, industrial, and commercial applications.
Prism ISP is compatible with Teledyne FLIR market-leading thermal cores including Boson®, Tau® 2, Hadron™, and Neutrino®. The ISP libraries enable integrators to leverage high-performance ISP algorithms that dramatically enhance the viewed image quality and AI capabilities of world-class infrared camera modules for defense, industrial, and commercial applications.

卓越的热像仪性能
高价值图像质量增强技术,优化操作员观测体验并提升感知软件预处理效果
- 超分辨率成像解析细节特征,生成高质量图像
- 辐射测量 JPG 格式打通 Teledyne FLIR 生态系统,包括 FLIR Thermal Studio™
- Teledyne FLIR MSX® 专利技术通过融合可见光边缘细节显著增强热成像质量
- 去闪烁功能有效抑制远距成像中的大气湍流影响

利用算法生态系统缩短上市时间
灵活的软件库降低了集成热相机计算成像投资成本
- 兼容 Teledyne FLIR ADK、Boson、Tau 2、Hadron 和 Neutrino
- 支持 NVIDIA 和 Qualcomm 的最新
嵌入式处理器

专为开发人员打造,提供 Teledyne FLIR 品牌承诺
值得信赖的全球热红外传感和解决方案领导者
- 包含库和文档的 C++ 参考应用程序示例
- 技术服务专家可提供集成支持
- 支持 Linux 和 Windows(需申请)
规格
- Authentication
- Camera to ECU key handshake with 256-bit challenge/response
- Cross Modality Image Registration
- Automatic alignment of thermal and EO to compensate for parallax and time sync differences
- Deblurring
- Blind and semi blind (motion known) methods supported to restore MTF (thermal video)
- Dewarping
- Radial and tangential lens dewarping
- Haze Penetration
- Locally adaptive compensation for atmospheric dispertion (thermal)
- Motion Compensated Temporal Noise Reduction
- Advanced, mutiframe noise reduction (thermal video)
- Pseudo-Color
- Multiple color palletes available (thermal video)
- Rectification
- Visible & thermal camera calibration process with pixel-accurate registration of visible & thermal
- Scene Based Non-Uniformity Correction
- Fixed pattern nosie removal (thermal video)
- Super Resolution
- Multiframe SR on full image or crop (e-zoom), 2X, 3X and 4X modes supported
- Supported Hardware
- Qualcomm: Snapdragon 8 gen 1 (RB5/QRB5165) & Snapdragon 8 gen 2 (QCS8550)
NVIDIA: Jetson Xavier & Jetson Orin
Other Qualcomm and NVIDA HW on request
- Supported Operating Systems
- Linux (18.04 and 20.04) verification done on Ubuntu distribution(s). Windows by request.
- Supported Video Formats
- 16b monochrome for LWIR/MWIR, 24b RGB/BGR for visible
- Tone Mapping
- Global and locally adaptive methods supported, optimized for highly dynamic scenes
- Video Stabilization
- Removal of high temporal frequency jitter (thermal and EO)
资源和支持
由 Teledyne FLIR OEM 专家撰写的新文章和白皮书,旨在帮助您集成 Teledyne FLIR OEM 产品。
如有技术问题,请在 flir.custhelp.com 访问我们的常见问题解答页面以寻找答案
白皮书
Beyond Embedded AI: Optimizing the Thermal Perception Pipeline from Sensor Data to Edge Deployment
了解详情应用说明
A Guide on Cost-Effective Thermal Lens Integration: What to Know for Defense and Autonomous Vehicle Applications
了解详情以下资产为此产品系列所有型号共享。
Prism AI - Auto Datasheet
使用我们的操作方法视频库及更多资源,集成 Teledyne FLIR OEM 热像仪模块从未如此简单!