Leopard Imaging Launches Hawk 3D Depth Cameras Leveraging NVIDIA Jetson Edge AI and Isaac Robotics Platforms

Leopard Imaging in collaboration with NVIDIA is delivering cost-effective 3D stereo imaging solutions that provide real-time, accurate depth perception, giving developers the high-quality results needed to build and deploy edge AI and robotics applications. The Hawk Camera offers a wide horizontal field of view of 120° and integrates dual onsemi AR0234CS RGB image sensors with an active−pixel array of 1920 (H) x 1200 (V) to support full HD video up to 120 fps. The dual RGB global shutter sensors reduce visual artifacts for improved perception performance in any high-vibration environments that the robot may encounter. This is coupled with a 6-axis IMU for highly accurate (sub-microsecond) timestamping of the camera frames relative to the IMU which is needed for high-precision robotics perception.

Top iTechnology Digital Transformation News: Esper and Lenovo Collaborate on Android Device Deployment in Enterprises

In addition, the camera’s high-speed GMSL2 interface enables reliable operation at distances up to 10m away from NVIDIA Jetson edge AI platform to further satisfy the challenging mechanical design needs of today’s AI-enabled robots. The Hawk Camera provides accurate depth perception from 15cm to 5m and has the ability to detect 10cmx10cm objects with superior resolution. The camera solution works with NVIDIA Vision Programming Interface (VPI) algorithms and integrates to the NVIDIA Isaac platform to ensure optimum performance on the Jetson AGX Xavier and Jetson Xavier NX system on modules (SOM). The camera is supported out of the box by the camera and stereo depth Isaac ROS GEMs, enabling developers to quickly integrate in their products.

NVIDIA Jetson is the leading AI-at-the-edge computing platform with over 850,000 developers. With pretrained AI models, developer SDKs and support for cloud-native technologies across the full Jetson lineup, manufacturers of intelligent machines and AI developers can build and deploy high-quality, software-defined features on embedded and edge devices targeting robotics, AIoT, smart cities, healthcare, industrial applications, and more.

Top iTechnology IT and DevOps News: McObject and Lynx Software Technologies Team Up for the First COTS Hard Real-Time DBMS for Mission- and Safety-Critical Systems

The NVIDIA Isaac platform comes stacked with comprehensive tools, application frameworks, GPU-enabled algorithms, reference designs, and pretrained capabilities to accelerate development workflows for robotics applications. This includes Isaac Sim on NVIDIA Omniverse for simulation and training of robots in virtual environments before deploying them in the real world and Isaac ROS open software development framework that speeds up robotics development and deployment. A suite of Isaac GEMs for ROS — preoptimized software packages to accelerate image processing and DNN performance on NVIDIA Jetson – makes it easier to add AI for perception and navigation into modern-day robots.

Leopard Imaging, an Elite Partner in the NVIDIA Jetson ecosystem, enhances the imaging quality with active alignment (AA) technology through its powerful manufacturing capabilities. Leopard Imaging’s full integration services will help customers incorporate the Hawk Camera into a full range of robotics projects and deployments.

“Together with the performance and flexibility of NVIDIA’s technology in autonomous machines, Leopard Imaging continues to advance in embedded camera design and manufacturing – delivering a scalable range of camera solutions for our customers,” remarks Bill Pu, President and Co-Founder of Leopard Imaging.

“By leveraging our full stack of GPU-accelerated computing technologies and enabling ease of deployment of cost-effective 3D camera solutions, Leopard Imaging is accelerating time-to-market of vision-based edge AI and robotics applications,” said Murali Gopalakrishna, Head of Product Management, Autonomous Machines and General Manager for Robotics at NVIDIA.