Hellbender On-Edge AI Stereo Camera is a fully programmable, industrial-grade depth perception sensor designed to revolutionize how robots see and navigate their world. Built for ground mobile systems, field robotics, and autonomous platforms, it delivers professional-grade machine vision capabilities in a compact, power-efficient package that processes everything locally—no cloud required.

It includes powerful features like PoE, NIR flood illumination as well as pattern projection. It also comes standard with a time synchronized on-board IMU for VINS applications, and a slew of environmental sensors. Its quad-core onboard processor and Hailo-8 AI accelerator with 26 TOPS capability let it tackle machine vision tasks with ease.

Don’t Settle for Sensors—Give Your Robot Sight

Whether you’re building autonomous rovers, inspection robots, or navigation systems, Hellbender On-Edge AI Stereo Camera gives your platform human-like depth perception combined with AI processing power. Unlike traditional stereo cameras that burden your host system with heavy computational loads, Hellbender handles the complex vision processing internally, freeing your main platform to focus on high-level decision making and control.

Hellbender On-Edge AI Stereo Camera excels in challenging environments where other vision systems fail. Its dual infrared illumination system—850nm flood lighting and 940nm pattern projection—ensures reliable depth perception in low-light conditions, while the global shutter cameras capture crisp images even during high-speed movement.

Ready to Ship, Ready to Code

For developers, we’ve made integration as simple as working with a Raspberry Pi. The familiar CM4 architecture means you can develop and deploy custom applications using the tools you already know, while the synchronized IMU provides essential motion data for VINS (visual-inertial navigation systems) applications.

Unlike development boards that require extensive additional components, Hellbender On-Edge AI Stereo Camera arrives as a complete, tested system. Simply connect to a compatible PoE injector or switch, and you’re ready to start developing.

Features & Specifications

Processors

• Raspberry Pi CM4 with quad-core ARM A72 processor (1.5 GHz)
• Hailo-8 AI accelerator with 26 TOPS of dedicated AI processing
• 8 GB RAM, 32 GB eMMC storage
• Real-time depth mapping and AI inference

Optics

• Dual 2 MP global shutter color cameras
• 140 mm stereo baseline for precise depth calculation
• 129 °H x 78 °V field of view (additional lens options available)
• Professional-grade imaging sensors built for industrial applications

Intelligent Illumination

• 850 nm infrared flood illumination (104 °H x 84 °V coverage)
• 940 nm structured light pattern projector (78 °H x 84 °V)

Power

• Power over Ethernet (PoE 802.3at) - under 15 W consumption
• Gigabit Ethernet for high-speed data transfer
• Industrial temperature range: -20 °C to 65 °C

Integrated Sensors

• 6-axis IMU with time synchronization for VINS
• Environmental sensors: temperature, pressure, humidity
• Real-time clock with backup battery
• Onboard EEPROM and I2C interface

Weight and Size

• Dimensions: 157 x 57 x 43.1 mm (6.18 x 2.24 x 1.7 in)
• Weight: 550 g (19.4 oz)
• Rugged construction for field deployment

Open Source

We believe in empowering developers with complete access to their tools. This will include:

• Open-source drivers and comprehensive documentation
• Application examples and development tutorials
• STEP files for mechanical integration
• PCB layouts and schematics (with selective redaction for IP protection)

Visit our website for current documentation, examples, and community contributions.

Interested in This Project?

You can sign up at the top of this page to be notified when the campaign launches and to receive other updates. We only send out relevant content, and you can unsubscribe at any time.