Visual odometry from RealSense stereo for drift correction #586

Closed
opened 2026-03-14 12:15:38 -04:00 by sl-jetson · 0 comments
Collaborator

Implement visual odometry using RealSense D435i stereo cameras.Requirements:- Subscribe to /camera/infra1/image_rect_raw and /camera/infra2/image_rect_raw- Feature extraction and matching (ORB or FAST+BRIEF)- Frame-to-frame motion estimation via essential matrix- Scale from depth channel or stereo baseline- Publish nav_msgs/Odometry on /saltybot/visual_odom- TF2: camera_link relative to odom- Integration with UWB-IMU fusion for drift correction- Configurable feature count and matching thresholdDeliverables:- ROS2 Python package: saltybot_visual_odom- Launch file + params YAMLAssigned to: sl-perception

Implement visual odometry using RealSense D435i stereo cameras.**Requirements:**- Subscribe to /camera/infra1/image_rect_raw and /camera/infra2/image_rect_raw- Feature extraction and matching (ORB or FAST+BRIEF)- Frame-to-frame motion estimation via essential matrix- Scale from depth channel or stereo baseline- Publish nav_msgs/Odometry on /saltybot/visual_odom- TF2: camera_link relative to odom- Integration with UWB-IMU fusion for drift correction- Configurable feature count and matching threshold**Deliverables:**- ROS2 Python package: saltybot_visual_odom- Launch file + params YAMLAssigned to: sl-perception
Sign in to join this conversation.
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: seb/saltylab-firmware#586
No description provided.