TY - JOUR
T1 - A fast and accurate object detection algorithm on humanoid marathon robot
AU - Jamzuri, Eko Rudiawan
AU - Mandala, Hanjaya
AU - Baltes, Jacky
N1 - Funding Information:
This work was financially supported by the Chinese Language and Technology Center of National Taiwan Normal University (NTNU) from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan, and Ministry of Science and Technology, Taiwan, under Grants No. MOST 108-2634-F-003-002, MOST 108-2634-F-003-003, and MOST 108-2634-F-003-004 (administered through Pervasive Artificial Intelligence Research (PAIR) Labs), as well as MOST 107-2811-E-003-503-. We are grateful to the National Center for High-performance Computing for computer time and facilities to conduct this research.
Publisher Copyright:
© 2019 Institute of Advanced Engineering and Science.
PY - 2020/3
Y1 - 2020/3
N2 - This paper introduces a fast and accurate object detection algorithm based on a convolutional neural network for humanoid marathon robot applications. The algorithm is capable of operating on a low-performance CPU without relying on the GPU or hardware accelerator. A new region proposal algorithm, based on color segmentation, is proposed to extract a region containing a potential object. As a classifier, the convolution neural network is used to predict object classes from the proposed region. In the training phase, the classifier is trained with an Adam optimizer to minimize the loss function, using datasets collected from humanoid marathon competitions and diversified using image augmentation. An NVIDIA GTX 1070 training machine, with 500 batch images per epoch and a learning rate of 0.001, required 12 seconds to minimize the loss value below 0.0374. In the accuracy evaluation, the proposed method successfully recognizes and localizes three classes of marker with a training accuracy of 99.929%, validation accuracy of 99.924%, and test accuracy of 98.821%. As a real-time benchmark, the algorithm achieves 41.13 FPS while running on a robot computer with Intel i3-5010U CPU @ 2.10GHz.
AB - This paper introduces a fast and accurate object detection algorithm based on a convolutional neural network for humanoid marathon robot applications. The algorithm is capable of operating on a low-performance CPU without relying on the GPU or hardware accelerator. A new region proposal algorithm, based on color segmentation, is proposed to extract a region containing a potential object. As a classifier, the convolution neural network is used to predict object classes from the proposed region. In the training phase, the classifier is trained with an Adam optimizer to minimize the loss function, using datasets collected from humanoid marathon competitions and diversified using image augmentation. An NVIDIA GTX 1070 training machine, with 500 batch images per epoch and a learning rate of 0.001, required 12 seconds to minimize the loss value below 0.0374. In the accuracy evaluation, the proposed method successfully recognizes and localizes three classes of marker with a training accuracy of 99.929%, validation accuracy of 99.924%, and test accuracy of 98.821%. As a real-time benchmark, the algorithm achieves 41.13 FPS while running on a robot computer with Intel i3-5010U CPU @ 2.10GHz.
KW - Convolution neural network
KW - Deep learning
KW - Object detection
KW - Region proposal
KW - Robotic vision
UR - http://www.scopus.com/inward/record.url?scp=85083978667&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083978667&partnerID=8YFLogxK
U2 - 10.11591/ijeei.v8i1.1960
DO - 10.11591/ijeei.v8i1.1960
M3 - Article
AN - SCOPUS:85083978667
SN - 2089-3272
VL - 8
SP - 204
EP - 214
JO - Indonesian Journal of Electrical Engineering and Informatics
JF - Indonesian Journal of Electrical Engineering and Informatics
IS - 1
ER -