Next Article in Journal
A Radiative Transfer Model-Based Multi-Layered Regression Learning to Estimate Shadow Map in Hyperspectral Images
Previous Article in Journal
Bag of ARSRG Words (BoAW)
Article Menu

Export Article

Open AccessArticle

Deep Learning Based Object Recognition Using Physically-Realistic Synthetic Depth Scenes

Department of Robotics, Nazarbayev University, 53 Kabanbay batyr Ave., Astana Z05H0P9, Kazakhstan
*
Author to whom correspondence should be addressed.
Mach. Learn. Knowl. Extr. 2019, 1(3), 883-903; https://doi.org/10.3390/make1030051
Received: 29 March 2019 / Revised: 3 August 2019 / Accepted: 4 August 2019 / Published: 6 August 2019
(This article belongs to the Section Learning)
  |  
PDF [3763 KB, uploaded 6 August 2019]
  |  

Abstract

Recognizing objects and estimating their poses have a wide range of application in robotics. For instance, to grasp objects, robots need the position and orientation of objects in 3D. The task becomes challenging in a cluttered environment with different types of objects. A popular approach to tackle this problem is to utilize a deep neural network for object recognition. However, deep learning-based object detection in cluttered environments requires a substantial amount of data. Collection of these data requires time and extensive human labor for manual labeling. In this study, our objective was the development and validation of a deep object recognition framework using a synthetic depth image dataset. We synthetically generated a depth image dataset of 22 objects randomly placed in a 0.5 m × 0.5 m × 0.1 m box, and automatically labeled all objects with an occlusion rate below 70%. Faster Region Convolutional Neural Network (R-CNN) architecture was adopted for training using a dataset of 800,000 synthetic depth images, and its performance was tested on a real-world depth image dataset consisting of 2000 samples. Deep object recognizer has 40.96% detection accuracy on the real depth images and 93.5% on the synthetic depth images. Training the deep learning model with noise-added synthetic images improves the recognition accuracy for real images to 46.3%. The object detection framework can be trained on synthetically generated depth data, and then employed for object recognition on the real depth data in a cluttered environment. Synthetic depth data-based deep object detection has the potential to substantially decrease the time and human effort required for the extensive data collection and labeling.
View Full-Text
Keywords: machine learning; convolutional neural networks; deep learning; object recognition; synthetic data generation; big data; physics engine machine learning; convolutional neural networks; deep learning; object recognition; synthetic data generation; big data; physics engine
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Supplementary material

SciFeed

Share & Cite This Article

MDPI and ACS Style

Baimukashev, D.; Zhilisbayev, A.; Kuzdeuov, A.; Oleinikov, A.; Fadeyev, D.; Makhataeva, Z.; Varol, H.A. Deep Learning Based Object Recognition Using Physically-Realistic Synthetic Depth Scenes. Mach. Learn. Knowl. Extr. 2019, 1, 883-903.

Show more citation formats Show less citations formats

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Mach. Learn. Knowl. Extr. EISSN 2504-4990 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top