Sighthound Compute Hardware

Powerful Edge Compute & AI Devices

Sighthound's advanced edge computing hardware offers real-time video analytics. Designed for efficiency, scalability, and flexibility, these computing devices bring the power of AI directly to the edge, reducing latency and optimizing performance.

hardware background
Compute Hardware

About Our Hardware

About Hardware

Sighthound Compute Hardware combines cutting-edge AI capabilities with robust design

  • Edge Processing Power: Real-time video analytics directly at the source.

  • Open Platform: Run Sighthound or your own Linux-based Computer Vision applications.

  • High-Resolution Imaging: Capture clear, detailed video even in low light.

  • Rugged Design: IP67-rated for water and dust resistance.

  • Scalability: Supports multiple camera inputs and flexible storage options.

Use Cases

  • Parking Operations

    Parking Operations

    Optimize your parking management with real-time license plate recognition and vehicle tracking. Sighthound Compute Hardware enhances security and efficiency, providing actionable insights for better decision-making to optimize space usage, manage fees and identify violations.

  • Law Enforcement

    Law Enforcement

    Improve public safety with advanced video analytics. Sighthound Compute Hardware enables real-time monitoring, evidence collection, and situational awareness, helping law enforcement officers and prosecutors close cases faster.

  • Safety & Surveillance

    Safety & Surveillance

    Municipalities and businesses can augment their safety and security program with vehicle information to keep their corporate campuses, schools, neighborhoods, parks, and streets safe.

Advanced Edge Computing & AI Devices

Compute Camera

Sighthound Compute Camera 4

The Sighthound Compute Camera 4 combines high-resolution imaging with powerful edge computing, enabling real-time video analysis directly at the source. It allows you to run various Linux-based software and complex neural networks right where you need them.

This IP67-rated camera is perfect for outdoor and industrial environments, providing reliable performance under the harshest conditions.

  • Sony STARVIS IMX 334 8.3 MP sensor for high-resolution imaging

  • Motorized varifocal 4K lens options

  • Supports up to 4K resolution at 60 FPS

  • Onboard AI processing with NVIDIA GPU

  • Up to 4TB NVMe SSD storage

  • TLS encrypted communication

Applications:

  • Traffic management and safety analysis

  • Intelligent parking solutions for lots and curbsides

  • Enhanced security for retail and high-security areas

download datasheet
Compute Node

Sighthound Compute Node 4

The Sighthound Compute Node 4 is an edge computing powerhouse designed to make your non-smart camera infrastructure into an intelligent surveillance system with advanced AI capabilities. This compact, fanless, rugged device can easily digest the RTSP network camera stream and perform real-time video processing, reducing the need for centralized servers.

  • Quad-Core ARM CPU

  • NVIDIA GPU with 256 CUDA cores

  • Supports IP camera via RTSP stream

  • Up to 4TB NVMe SSD storage

  • TLS encrypted communication

  • IP67-rated for rugged environments

Applications:

  • Mobile computing for transport and logistics

  • Edge computing in remote or challenging locations

  • Retail and QSR enhancements for customer experience

Download Datasheet

Built to be flexible.

Proven. Powerful. Modular. Made in the USA.

NVIDIA

Sighthound Compute devices are built around our 3rd-generation Sighthound Compute Board, featuring a quad-core ARM CPU and 256-core NVIDIA GPU. The CPU provides unmatched flexibility to run bare-metal, Docker, or Kubernetes Linux applications anywhere.

The onboard GPU enables running complex neural networks, including Sighthound ALPR+ vehicle and license plate recognition, as well as other open-source, in-house, or third-party computer vision and AI solutions. The Compute Board also supports flexible, modular expansion with integrated cameras, lenses, NVMe storage, and USB devices.

  • Quad-core ARM CPU

  • 256-core NVIDIA GPU

  • Up to 4TB of storage

  • Deploy Linux apps

  • Deploy Computer Vision


Frequently Asked Questions

For more frequently asked questions about Sighthound Hardware and other Sighthound solutions, check out our Frequently Asked Questions page.

If you do not see the answer you are looking for, contact our experts.

Sighthound Hardware

  • Sighthound Compute Cameras are specifically designed for outdoor surveillance and parking lot applications, offering a rugged IP67-rated design that can withstand harsh environments. With customizable lens options, they provide excellent coverage and deliver high-quality images. Sighthound Compute Cameras can be easily mounted on parking lot light poles, at entry points of parking lots or garages, and in other strategic locations. In addition to their a ility to run an Linux applications, advanced features include license plate recognition, vehicle, and people detection, counting, and tracking, enabling enhanced security, efficient space management, and improved traffic management.

  • Yes! With the Sighthound Compute Node, you can transform your existing non-smart network camera into an intelligent device. Sighthound Compute Node integrates seamlessly with your deployed camera by processing the RTSP stream in real-time and providing real-time results at the edge.

    This allows you to enhance your existing camera infrastructure and gain valuable insights without the need for costly camera replacements.

  • Yes! The Sighthound Compute Board in our hardware products feature ARM CPU cores and NVIDIA GPU cores, and run a Linux-based software stack with the capability to run any Docker containers. This lets you to deploy and run your software directly on the camera.

    On the Compute Camera you can leverage the real-time stream provided by the onboard image sensor to capture and process data in real-time. On the Compute Node yTu can do the same with any source RTSP stream.

    Tis opens up possibilities for a wide range of applications, such as real-time event detection, object tracking, and custom analytics.

  • Our hardware solutions are built with ease of integration in mind, allowing for seamless deployment and minimal disruption to your operations.

    The devices support standard network protocols and are compatible with the most common, if not all, network infrastructures. They can be easily connected to your network and integrated into your existing system. Our devices offer remote management capabilities, enabling you to conveniently configure and monitor them from a centralized location.

  • Sighthound hardware utilizes the power of edge computing by processing data and running AI algorithms directly on the devices themselves, at the edge of your network. This significantly minimizes latency, improves responsiveness, and reduces reliance on constant network connectivity. With Sighthound Hardware, you can make critical decisions in real-time, ensure continuity of operations even in unreliable network conditions, and effectively manage and analyze your visual data without overwhelming your network infrastructure.

Become a partner

Sighthound empowers thousands of end users with computer vision solutions.

Learn about our partnership opportunities.