Cargando…
Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information
Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8949180/ https://www.ncbi.nlm.nih.gov/pubmed/35336525 http://dx.doi.org/10.3390/s22062354 |
_version_ | 1784674833281318912 |
---|---|
author | Yu, Ruonan Li, Hongguang Jiang, Yalong Zhang, Baochang Wang, Yufeng |
author_facet | Yu, Ruonan Li, Hongguang Jiang, Yalong Zhang, Baochang Wang, Yufeng |
author_sort | Yu, Ruonan |
collection | PubMed |
description | Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less. |
format | Online Article Text |
id | pubmed-8949180 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-89491802022-03-26 Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information Yu, Ruonan Li, Hongguang Jiang, Yalong Zhang, Baochang Wang, Yufeng Sensors (Basel) Article Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less. MDPI 2022-03-18 /pmc/articles/PMC8949180/ /pubmed/35336525 http://dx.doi.org/10.3390/s22062354 Text en © 2022 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 Yu, Ruonan Li, Hongguang Jiang, Yalong Zhang, Baochang Wang, Yufeng Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title | Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title_full | Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title_fullStr | Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title_full_unstemmed | Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title_short | Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information |
title_sort | tiny vehicle detection for mid-to-high altitude uav images based on visual attention and spatial-temporal information |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8949180/ https://www.ncbi.nlm.nih.gov/pubmed/35336525 http://dx.doi.org/10.3390/s22062354 |
work_keys_str_mv | AT yuruonan tinyvehicledetectionformidtohighaltitudeuavimagesbasedonvisualattentionandspatialtemporalinformation AT lihongguang tinyvehicledetectionformidtohighaltitudeuavimagesbasedonvisualattentionandspatialtemporalinformation AT jiangyalong tinyvehicledetectionformidtohighaltitudeuavimagesbasedonvisualattentionandspatialtemporalinformation AT zhangbaochang tinyvehicledetectionformidtohighaltitudeuavimagesbasedonvisualattentionandspatialtemporalinformation AT wangyufeng tinyvehicledetectionformidtohighaltitudeuavimagesbasedonvisualattentionandspatialtemporalinformation |