A SOFTWARE LIBRARY FOR 3D RECONSTRUCION
AT THE EDGE
To speed up the integration of state-of-the-art 3D vision for OEMs, Deep Vision has created 3D+AI, a software library for 3D reconstruction with deep learning from stereo cameras, delivering incredibly dense 3D metric data in real time on embedded devices. 3D+AI requires Hailo-8™ hosted on NXP i.MX 8M Plus or Intel® Core.
DEPTH WITH 3D+AI
POINT CLOUD WITH 3D+AI
Piano room images from Middelbury Stereo Dataset, D. Scharstein, et al. High-resolution stereo datasets with subpixel-accurate ground truth. GCPR 2014
3D vision means having depth, point clouds and metric data, that are necessary in many use cases from industries like automotive, robotics, agritech, industrial automation and others. Approaching 3D vision with deep learning techniques is possible and unleashes greater opportunities if compared to 3D vision with traditional techniques; however, technical and computational complexity increases significantly. And when deep learning for 3D vision needs to be applied at the edge, the matter can get extremely intricate.
3D+AI addresses these 3 elements together (3D reconstrucion with leep learning at the edge) and brings to OEMs a ready-to-use solution.
To ease 3D+AI testing and adoption by OEMs, it is possible to activate a time-limited free trial on the StereoCam Deep Vision Starter Kit.
METRIC DEPTH FROM STEREO CAMERA WITH 3D+AI
LIVE AT 10 FPS ON i.MX 8M PLUS AND HAILO-8
Metric depth from stereo camera computed with 3D+AI. The stereo matching is computed via deep learning on Hailo-8 and iMX 8M Plus, live at 10fps.On the left, one of the two video streams from the stereo camera. On the right, the depth with jet colormap (red = close, blue = far). The slider on top right shows the metric distance at the center point of the depth map.
DEPTH WITH 3D+AI
Metric depth from stereo camera with IR randomic pattern projection computed with 3D+AI.
Intel® x86/x64 Linux
or NXP i.MX 8M Plus
your preferred camera modules
choose baseline and lenses according to your use case
via GStreamer plugin or
C++ library interface
ADDITIONAL VISION TASKS
create your own logics or get custom developments from Deep Vision
LICENSING AND SUPPORT
3D+AI is licensed with an unlimited perpetual license model. See details below.
For pricing information fill the contact form.
Unlimited number of devices
On single hardware platform (i.MX 8M Plus on Deep Vision Starter Kit or Intel® Core on standard PC configuration)
On single software dependency configuration (Hailo SDK version, Yocto based BSD or Ubuntu versio, etc)
10h jumpstart support (1h block, expiration 12 months)
Port the Unlimited Perpetual License to a different software dependency configuration among the supported ones
20h support (1h block, expiration in 12 months)
examples: extra support over documentation, design of stereo camera parameters, stereo calibration, other vision tasks