Cargando…
Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks †
In this paper, we present a real-time object detection and depth estimation approach based on deep convolutional neural networks (CNNs). We improve object detection through the incorporation of transfer connection blocks (TCBs), in particular, to detect small objects in real time. For depth estimati...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309632/ https://www.ncbi.nlm.nih.gov/pubmed/34300491 http://dx.doi.org/10.3390/s21144755 |
_version_ | 1783728567559913472 |
---|---|
author | Wang, Huai-Mu Lin, Huei-Yung Chang, Chin-Chen |
author_facet | Wang, Huai-Mu Lin, Huei-Yung Chang, Chin-Chen |
author_sort | Wang, Huai-Mu |
collection | PubMed |
description | In this paper, we present a real-time object detection and depth estimation approach based on deep convolutional neural networks (CNNs). We improve object detection through the incorporation of transfer connection blocks (TCBs), in particular, to detect small objects in real time. For depth estimation, we introduce binocular vision to the monocular-based disparity estimation network, and the epipolar constraint is used to improve prediction accuracy. Finally, we integrate the two-dimensional (2D) location of the detected object with the depth information to achieve real-time detection and depth estimation. The results demonstrate that the proposed approach achieves better results compared to conventional methods. |
format | Online Article Text |
id | pubmed-8309632 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-83096322021-07-25 Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † Wang, Huai-Mu Lin, Huei-Yung Chang, Chin-Chen Sensors (Basel) Article In this paper, we present a real-time object detection and depth estimation approach based on deep convolutional neural networks (CNNs). We improve object detection through the incorporation of transfer connection blocks (TCBs), in particular, to detect small objects in real time. For depth estimation, we introduce binocular vision to the monocular-based disparity estimation network, and the epipolar constraint is used to improve prediction accuracy. Finally, we integrate the two-dimensional (2D) location of the detected object with the depth information to achieve real-time detection and depth estimation. The results demonstrate that the proposed approach achieves better results compared to conventional methods. MDPI 2021-07-12 /pmc/articles/PMC8309632/ /pubmed/34300491 http://dx.doi.org/10.3390/s21144755 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Wang, Huai-Mu Lin, Huei-Yung Chang, Chin-Chen Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title | Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title_full | Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title_fullStr | Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title_full_unstemmed | Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title_short | Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks † |
title_sort | object detection and depth estimation approach based on deep convolutional neural networks † |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309632/ https://www.ncbi.nlm.nih.gov/pubmed/34300491 http://dx.doi.org/10.3390/s21144755 |
work_keys_str_mv | AT wanghuaimu objectdetectionanddepthestimationapproachbasedondeepconvolutionalneuralnetworks AT linhueiyung objectdetectionanddepthestimationapproachbasedondeepconvolutionalneuralnetworks AT changchinchen objectdetectionanddepthestimationapproachbasedondeepconvolutionalneuralnetworks |