# Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects

## TL;DR

This paper introduces a real-time, geometry-based object detection system for tabletop scenes using RGB-D sensors, combining point cloud clustering and CNN recognition to improve robustness and dataset creation.

## Contribution

The novel detection pipeline integrates geometry-based region proposals with deep learning, enabling efficient, accurate detection and dataset generation for robotic tabletop environments.

## Key findings

- High detection accuracy demonstrated in experiments
- Real-time performance achieved on standard hardware
- Effective dataset creation method for training deep models

## Abstract

We present a novel object detection pipeline for localization and recognition in three dimensional environments. Our approach makes use of an RGB-D sensor and combines state-of-the-art techniques from the robotics and computer vision communities to create a robust, real-time detection system. We focus specifically on solving the object detection problem for tabletop scenes, a common environment for assistive manipulators. Our detection pipeline locates objects in a point cloud representation of the scene. These clusters are subsequently used to compute a bounding box around each object in the RGB space. Each defined patch is then fed into a Convolutional Neural Network (CNN) for object recognition. We also demonstrate that our region proposal method can be used to develop novel datasets that are both large and diverse enough to train deep learning models, and easy enough to collect that end-users can develop their own datasets. Lastly, we validate the resulting system through an extensive analysis of the accuracy and run-time of the full pipeline.