Skip to content
RobothecaBeta
Log in

trackdlo_perception

  • Software
  • Perception
  • Tool

A ROS2 package that tracks deformable linear objects, such as cables or ropes, in real time from Intel RealSense RGB-D camera data.

Source on GitHub: github.com/HayatoShimada/trackdlo_perception (opens in a new tab). Facts read at commit 70dda1c (opens in a new tab).

Licenses

Code
BSD-3-Clause (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit 70dda1c (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Tracks a deformable linear object's node positions in real time using the CPD-LLE algorithm, based on TrackDLO.
  • Offers pluggable segmentation: HSV thresholding by default, with YOLO and DeepLab named as options, and an HSV tuner GUI.
  • Publishes tracked node positions as a standard PointCloud2 topic, so other ROS2 nodes can subscribe without custom messages.
  • Shows a 4-panel preview window with camera feed, segmentation mask, overlay, and tracking results.
  • Can be run in Docker with automatic GPU detection, or built natively with colcon.
  • Custom segmentation backends can be added by subclassing a segmentation base class that outputs a binary mask.

Written by Robotheca from the project's README (opens in a new tab) at commit 70dda1c.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
An Intel RealSense D415, D435, or D455 camera is needed for the launch example.

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
14 May 2026 on master
Latest release
v2.1.0 — Community-ready release with Jazzy support (2 Apr 2026)

Checked on GitHub on 16 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.