NVIDIA-ISAAC-ROS/isaac_ros_depth_segmentation

NVIDIA-accelerated, deep learned depth segmentation and obstacle field ranging using Bi3D

44
/ 100
Emerging

This project helps roboticists and autonomous system developers quickly detect and avoid obstacles. By taking synchronized left and right stereo camera images, it outputs a segmented view showing whether objects are within a defined proximity field, along with a clear indication of free space. This is for engineers building robots or autonomous vehicles that need reliable, real-time collision avoidance.

Use this if you need to determine if obstacles are within a critical distance and identify clear pathways for autonomous navigation.

Not ideal if you require precise, continuous depth measurements for every point in the scene, rather than proximity segmentation.

robotics autonomous-navigation collision-avoidance machine-vision perception-systems
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

56

Forks

8

Language

C++

License

Apache-2.0

Last pushed

Dec 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVIDIA-ISAAC-ROS/isaac_ros_depth_segmentation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.