andyzeng/apc-vision-toolbox

MIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.

53
/ 100
Established

This project helps roboticists and automation engineers working on pick-and-place systems to identify and precisely locate objects in cluttered warehouse environments. It takes raw RGB-D camera data from a RealSense sensor and outputs 2D object segmentation masks and the 6D pose (position and orientation) of recognized objects. The primary users are researchers and engineers developing robotic manipulation systems for logistics and manufacturing.

308 stars. No commits in the last 6 months.

Use this if you are building an automated robotic system that needs to accurately locate various objects in a bin or on a shelf, especially in challenging conditions with occlusions and sensor noise.

Not ideal if you are looking for a general-purpose object detection system for consumer applications or if your environment does not involve industrial robotic manipulation.

robotics warehouse-automation object-recognition robot-vision pick-and-place
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

308

Forks

140

Language

C++

License

BSD-2-Clause

Last pushed

Oct 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/andyzeng/apc-vision-toolbox"

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