NVIDIA-ISAAC-ROS/isaac_ros_image_segmentation

NVIDIA-accelerated, deep learned semantic image segmentation

50
/ 100
Established

This helps robotics engineers and perception system developers identify specific objects or regions within an image stream from a robot's camera. It takes a raw camera image and outputs a detailed map where each pixel is labeled with a specific category, like 'floor', 'wall', or 'robot arm'. This allows the robot to precisely understand its environment and the exact shape of objects in a 2D image or a 3D scene.

118 stars.

Use this if you need your robot to precisely understand the contours and exact locations of different objects and surfaces in its environment from camera feeds.

Not ideal if you only need to know if an object exists in a general area, as a simpler object detection solution would be more efficient.

robotics autonomous-navigation perception-systems computer-vision object-recognition
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

118

Forks

10

Language

C++

License

Apache-2.0

Last pushed

Mar 24, 2026

Commits (30d)

0

Get this data via API

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

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