Stereo Vision 3DV

  • 3DV is a stereovision  system single box two cameras

  • provides full 3D reconstruction of the scene framed by both cameras.

  • VisLab’s proprietary algorithms developed through years of research

  • 3DV provides a quick interpretation of the environment,

  • Object detection and

  • tracking obstacles and

  • terrain surface estimating, and

  • slope estimation

  • 3DV is easily integrated into third parties robotics/vehicular/rover platforms

  • sold together with samples of cross platform code to ease its integration on existing systems.

3DV provides a dense 3D map of the surroundings (a 3D point cloud of up to 3 millions 3D points per second) in real time. Version A (3DV-A) uses an unboxed board as its processing engine, to ease its installation even on board of small robotic platforms.

Stereo Vision 3dv

Output is generated as UDP packets over a Gigabit Ethernet connection, and includes:

  • two raw images (left and right)

  • raw 3D depth map (one distance estimation per image pixel)

  • list of objects (detected and tracked over time); available as an additional plugin

  • terrain mapping (as a heights grid); available as an additional plugin

  • Visual odometry; available as an additional pluging in late 2014

  • Recalibration feature; available as an additional plugin in late 2014.

A special configuration for UAV is also available (3DV-W); the hardware weights less than 1kg and provides a full-size 3D depth map as output.


The 3DV embedded version (version 3DV-E), based on an FPGA, is currently under development and will be available in 2014.  3DV-E processes 640×480 pixels images at 30Hz and provides full size 3D point clouds in real time.






See video
"Old-ladies 3D" HD - 3D reconstruct
See video
"Walker" HD - 3D reconstruction
See video
VisLab's 3DV sensing technology. 1
See video
VisLab's 3DV sensing technology. 2
See video
VisLab's 3DV syetem mounted low