Deep Learning Based Object Recognition Using Physically-Realistic Synthetic Depth Scenes
Open Access
- 6 August 2019
- journal article
- research article
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 1 (3), 883-903
- https://doi.org/10.3390/make1030051
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.Keywords
This publication has 30 references indexed in Scilit:
- Aligning 3D models to RGB-D images of cluttered scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Deep learningNature, 2015
- Locomotion Strategy Selection for a Hybrid Mobile Robot Using Time of Flight Depth SensorJournal of Sensors, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Depth-image-based rendering for 3DTV service over T-DMBSignal Processing: Image Communication, 2009
- Stereoscopic Image Generation Based on Depth Images for 3D TVIEEE Transactions on Broadcasting, 2005
- Infrared image processing and data analysisInfrared Physics & Technology, 2004
- Complex wavelets for extended depth‐of‐field: A new method for the fusion of multichannel microscopy imagesMicroscopy Research and Technique, 2004