A fast and accurate object detection algorithm on humanoid marathon robot

Eko Rudiawan Jamzuri, Hanjaya Mandala, Jacky Baltes

Research output: Contribution to journalArticle

Abstract

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.

Original languageEnglish
Pages (from-to)204-214
Number of pages11
JournalIndonesian Journal of Electrical Engineering and Informatics
Volume8
Issue number1
DOIs
Publication statusPublished - 2020 Mar

Keywords

  • Convolution neural network
  • Deep learning
  • Object detection
  • Region proposal
  • Robotic vision

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Control and Systems Engineering
  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A fast and accurate object detection algorithm on humanoid marathon robot'. Together they form a unique fingerprint.

  • Cite this