SCITEPRESS (original) (raw)
Paper
FotonNet: A Hardware-efficient Object Detection System using 3D-depth Segmentation and 2D-deep Neural Network Classifier
Topics: Image and Video Analysis and Understanding; Sensors and Early Vision
Gurjeet Singh 1 ; Sunmiao 2 ; Shi Shi 2 and Patrick Chiang 1 ; 3 ; 2
Affiliations: 1 Dept. of EECS, Oregon State University, Corvallis, U.S.A. ; 2 State Key Laboratory of ASIC & System, Fudan University, Shanghai, China ; 3 PhotonIC Technologies, Shanghai, China
Keyword(s): Object Detection, 3D Data, Hardware, Depth Sensors.
Abstract: Object detection and classification is one of the most crucial computer vision problems. Ever since the introduction of deep learning, we have witnessed a dramatic increase in the accuracy of this object detection problem. However, most of these improvements have occurred using conventional 2D image processing. Recently, low-cost 3D-image sensors, such as the Microsoft Kinect (Time-of-Flight) or the Apple FaceID (Structured-Light), can provide 3D-depth or point cloud data that can be added to a convolutional neural network, acting as an extra set of dimensions. We are proposing a hardware-based approach for Object Detection by moving region of interest identification closer to sensor node in the hardware. Due to this approach, we do not need a large dataset with depth images to retrain the network. Our 2D + 3D system takes the 3D-data to determine the object region followed by any conventional 2D-DNN, such as AlexNet. In this method, our approach can readily dissociate the informa tion collected from the Point Cloud and 2D-Image data and combine both operations later. Hence, our system can use any existing trained 2D network on a large image dataset and does not require a large 3D-depth dataset for new training. Experimental object detection results across 30 images show an accuracy of 0.67, whereas 0.54 and 0.51 for FasterRCNN and YOLO, respectively. (More)
Object detection and classification is one of the most crucial computer vision problems. Ever since the introduction of deep learning, we have witnessed a dramatic increase in the accuracy of this object detection problem. However, most of these improvements have occurred using conventional 2D image processing. Recently, low-cost 3D-image sensors, such as the Microsoft Kinect (Time-of-Flight) or the Apple FaceID (Structured-Light), can provide 3D-depth or point cloud data that can be added to a convolutional neural network, acting as an extra set of dimensions. We are proposing a hardware-based approach for Object Detection by moving region of interest identification closer to sensor node in the hardware. Due to this approach, we do not need a large dataset with depth images to retrain the network. Our 2D + 3D system takes the 3D-data to determine the object region followed by any conventional 2D-DNN, such as AlexNet. In this method, our approach can readily dissociate the information collected from the Point Cloud and 2D-Image data and combine both operations later. Hence, our system can use any existing trained 2D network on a large image dataset and does not require a large 3D-depth dataset for new training. Experimental object detection results across 30 images show an accuracy of 0.67, whereas 0.54 and 0.51 for FasterRCNN and YOLO, respectively.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guest:Register as new SciTePress user now for free.
Download limit per month - 500 recent papers or 4000 papers more than 2 years old.
SciTePress user: please login.
You are not signed in, therefore limits apply to your IP address 34.48.153.221
In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total
Paper citation in several formats:
Singh, G., Sunmiao, , Shi, S. and Chiang, P. (2020). FotonNet: A Hardware-efficient Object Detection System using 3D-depth Segmentation and 2D-deep Neural Network Classifier. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-397-1; ISSN 2184-4313, SciTePress, pages 461-468. DOI: 10.5220/0008958604610468
@conference{icpram20,
author={Gurjeet Singh and Sunmiao and Shi Shi and Patrick Chiang},
title={FotonNet: A Hardware-efficient Object Detection System using 3D-depth Segmentation and 2D-deep Neural Network Classifier},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2020},
pages={461-468},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008958604610468},
isbn={978-989-758-397-1},
issn={2184-4313},
}
TY - CONF
JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - FotonNet: A Hardware-efficient Object Detection System using 3D-depth Segmentation and 2D-deep Neural Network Classifier
SN - 978-989-758-397-1
IS - 2184-4313
AU - Singh, G.
AU - Sunmiao.
AU - Shi, S.
AU - Chiang, P.
PY - 2020
SP - 461
EP - 468
DO - 10.5220/0008958604610468
PB - SciTePress