scan_detection_fusion

Software
Perception
Tool

A ROS 2 library that fuses 2D camera object detections with a planar LiDAR scan to give labeled obstacles with range estimates and ground footprint polygons for navigation.

Source on GitHub: github.com/HexboxRC/scan_detection_fusion (opens in a new tab). Facts read at commit 0d7de31 (opens in a new tab).

Licenses

Code: Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 0d7de31 (opens in a new tab), on 16 Oct 2026.
Commercial use: Yes

What it does

Matches each detection's bearing to LiDAR returns at that bearing and estimates a robust range.
Routes LiDAR sampling to the vertical region of each bounding box where the class intersects the scan plane.
Publishes a width by depth ground polygon per object, sized from a per-class table and refined from the observed angular span.
Projects detected objects into the map frame and publishes them as a JSON registry, RViz markers and footprint polygons.
The fusion algorithm is a plain ROS-free Python class, so it can be used and tested without the ROS graph.
Targets ROS 2 Jazzy and works with standard vision_msgs detections, camera_info and TF transforms.

Written by Robotheca from the project's README (opens in a new tab) at commit 0d7de31.

Getting started

Difficulty: Intermediate
Hardware it needs, as the project states it: A planar 2D LiDAR publishing a LaserScan, and a camera-based object detector; a camera driver supplying camera_info is optional.
How to start: The project's README (opens in a new tab)

Maintenance

Status: Active: a commit in the last 90 days
Newest commit: 6 Sept 2026 on main
Latest release: None published on GitHub

Checked on GitHub on 16 Oct 2026.

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.