MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection
High-altitude remote sensing target detection has problems related to its low precision and low detection rate. In order to enhance the performance of detecting remote sensing targets, a new YOLO (You Only Look Once)-V3-based algorithm was proposed. In our improved YOLO-V3, we introduced the concept...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/19/3118 |
id |
doaj-b11a8cf3e21145dcbcb815af21f840d6 |
---|---|
record_format |
Article |
spelling |
doaj-b11a8cf3e21145dcbcb815af21f840d62020-11-25T03:18:55ZengMDPI AGRemote Sensing2072-42922020-09-01123118311810.3390/rs12193118MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target DetectionDanqing Xu0Yiquan Wu1College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaHigh-altitude remote sensing target detection has problems related to its low precision and low detection rate. In order to enhance the performance of detecting remote sensing targets, a new YOLO (You Only Look Once)-V3-based algorithm was proposed. In our improved YOLO-V3, we introduced the concept of multi-receptive fields to enhance the performance of feature extraction. Therefore, the proposed model was termed Multi-Receptive Fields Fusion YOLO (MRFF-YOLO). In addition, to address the flaws of YOLO-V3 in detecting small targets, we increased the detection layers from three to four. Moreover, in order to avoid gradient fading, the structure of improved DenseNet was chosen in the detection layers. We compared our approach (MRFF-YOLO) with YOLO-V3 and other state-of-the-art target detection algorithms on an Remote Sensing Object Detection (RSOD) dataset and a dataset of Object Detection in Aerial Images (UCS-AOD). With a series of improvements, the mAP (mean average precision) of MRFF-YOLO increased from 77.10% to 88.33% in the RSOD dataset and increased from 75.67% to 90.76% in the UCS-AOD dataset. The leaking detection rates are also greatly reduced, especially for small targets. The experimental results showed that our approach achieved better performance than traditional YOLO-V3 and other state-of-the-art models for remote sensing target detection.https://www.mdpi.com/2072-4292/12/19/3118remote sensing target detectionmulti-scalemulti-reception fielddensely connected networkRes2 blockYOLO-V3 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Danqing Xu Yiquan Wu |
spellingShingle |
Danqing Xu Yiquan Wu MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection Remote Sensing remote sensing target detection multi-scale multi-reception field densely connected network Res2 block YOLO-V3 |
author_facet |
Danqing Xu Yiquan Wu |
author_sort |
Danqing Xu |
title |
MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection |
title_short |
MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection |
title_full |
MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection |
title_fullStr |
MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection |
title_full_unstemmed |
MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection |
title_sort |
mrff-yolo: a multi-receptive fields fusion network for remote sensing target detection |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-09-01 |
description |
High-altitude remote sensing target detection has problems related to its low precision and low detection rate. In order to enhance the performance of detecting remote sensing targets, a new YOLO (You Only Look Once)-V3-based algorithm was proposed. In our improved YOLO-V3, we introduced the concept of multi-receptive fields to enhance the performance of feature extraction. Therefore, the proposed model was termed Multi-Receptive Fields Fusion YOLO (MRFF-YOLO). In addition, to address the flaws of YOLO-V3 in detecting small targets, we increased the detection layers from three to four. Moreover, in order to avoid gradient fading, the structure of improved DenseNet was chosen in the detection layers. We compared our approach (MRFF-YOLO) with YOLO-V3 and other state-of-the-art target detection algorithms on an Remote Sensing Object Detection (RSOD) dataset and a dataset of Object Detection in Aerial Images (UCS-AOD). With a series of improvements, the mAP (mean average precision) of MRFF-YOLO increased from 77.10% to 88.33% in the RSOD dataset and increased from 75.67% to 90.76% in the UCS-AOD dataset. The leaking detection rates are also greatly reduced, especially for small targets. The experimental results showed that our approach achieved better performance than traditional YOLO-V3 and other state-of-the-art models for remote sensing target detection. |
topic |
remote sensing target detection multi-scale multi-reception field densely connected network Res2 block YOLO-V3 |
url |
https://www.mdpi.com/2072-4292/12/19/3118 |
work_keys_str_mv |
AT danqingxu mrffyoloamultireceptivefieldsfusionnetworkforremotesensingtargetdetection AT yiquanwu mrffyoloamultireceptivefieldsfusionnetworkforremotesensingtargetdetection |
_version_ |
1724624945342840832 |