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 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.

[1]  Xiaorun Li,et al.  Local similarity constraint-based sparse algorithm for hyperspectral target detection , 2019 .

[2]  Paolo Addesso,et al.  Editorial for Special Issue "Remote Sensing for Target Object Detection and Identification" , 2020, Remote. Sens..

[3]  Jing Li,et al.  Application Research of Improved YOLO V3 Algorithm in PCB Electronic Component Detection , 2019, Applied Sciences.

[4]  Jianlin Wang,et al.  DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection , 2019, Inf. Sci..

[5]  Jörn Kohlus,et al.  Mapping seagrass (Zostera) by remote sensing in the Schleswig-Holstein Wadden Sea , 2020, Estuarine, Coastal and Shelf Science.

[6]  Bin Song,et al.  Battlefield Image Situational Awareness Application Based on Deep Learning , 2020, IEEE Intelligent Systems.

[7]  Pratibha Rathi,et al.  YOLO v3-Tiny: Object Detection and Recognition using one stage improved model , 2020, 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS).

[8]  Naoto Yokoya,et al.  Object Detection Based on Sparse Representation and Hough Voting for Optical Remote Sensing Imagery , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Bo Zhang,et al.  SFSSD: Shallow Feature Fusion Single Shot Multibox Detector , 2019, CSPS.

[10]  Yuyu Tian,et al.  Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot , 2020, Comput. Electron. Agric..

[11]  Liqi Wang,et al.  Feature Fusion and Enhancement for Single Shot Multibox Detector , 2019, 2019 Chinese Automation Congress (CAC).

[12]  Guoxu Liu,et al.  YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3 , 2020, Sensors.

[13]  J. Morin,et al.  Deep learning habitat modeling for moving organisms in rapidly changing estuarine environments: A case of two fishes , 2020, Estuarine, Coastal and Shelf Science.

[14]  Wang Zhenrui,et al.  Aircraft detection in remote sensing imagery with lightweight feature pyramid network , 2020 .

[15]  Philip J. Kellman,et al.  Local features and global shape information in object classification by deep convolutional neural networks , 2020, Vision Research.

[16]  Vinh-Tiep Nguyen,et al.  Building an Automatic Image Tagger with DenseNet and Transfer Learning , 2019, 2019 International Conference on Advanced Computing and Applications (ACOMP).

[17]  Fumiki Hosoi,et al.  Automatic Tree Detection from Three-Dimensional Images Reconstructed from 360° Spherical Camera Using YOLO v2 , 2020, Remote. Sens..

[18]  Ruey-Feng Chang,et al.  Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks , 2020, Comput. Methods Programs Biomed..

[19]  Jie Liu,et al.  A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3 , 2018, Sensors.

[20]  Yang Nan,et al.  Water depth retrieval models of East Dongting Lake, China, using GF-1 multi-spectral remote sensing images , 2020, Global Ecology and Conservation.

[21]  Fuchun Sun,et al.  Ship Detection Based on Faster R-CNN Network in Optical Remote Sensing Images , 2019 .

[22]  Lei Xing,et al.  Prostate Segmentation with Encoder-Decoder Densely Connected Convolutional Network (Ed-Densenet) , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[23]  Xiaoxin Liu,et al.  Improved SSD-Based Multi-scale Pedestrian Detection Algorithm , 2020 .

[24]  Bing Li,et al.  A binary sampling Res2net reconstruction network for single-pixel imaging. , 2020, The Review of scientific instruments.

[25]  Mingjie Liu,et al.  UAV-YOLO: Small Object Detection on Unmanned Aerial Vehicle Perspective , 2020, Sensors.

[26]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Ji Zhao,et al.  Adaptive conditional random field classification framework based on spatial homogeneity for high-resolution remote sensing imagery , 2020 .

[28]  P. Diamond,et al.  Turbulence model reduction by deep learning. , 2020, Physical review. E.

[29]  Abdulkadir Şeker,et al.  Evaluation of Fabric Defect Detection Based on Transfer Learning with Pre-trained AlexNet , 2018, 2018 International Conference on Artificial Intelligence and Data Processing (IDAP).

[30]  Junchao Li,et al.  Optical Fiber Defect Detection Method Based on DSSD Network , 2019, 2019 IEEE International Conference on Smart Internet of Things (SmartIoT).

[31]  Kai Zhao,et al.  Res2Net: A New Multi-Scale Backbone Architecture , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Tian Yuan,et al.  Defect diagnosis technology of typical components on transmission line based on Fully Convolutional Network , 2020 .

[34]  Yufeng Jane Tseng,et al.  Different molecular enumeration influences in deep learning: an example using aqueous solubility , 2020, Briefings Bioinform..

[35]  Jianting Zhou,et al.  Autoregressive Model-Based Structural Damage Identification and Localization Using Convolutional Neural Networks , 2020, KSCE Journal of Civil Engineering.

[36]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Ping Huang,et al.  Application Research of YOLO v2 Combined with Color Identification , 2018, 2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC).

[38]  Kun Hu,et al.  Use fast R-CNN and cascade structure for face detection , 2016, 2016 Visual Communications and Image Processing (VCIP).

[39]  Huang Rui,et al.  A Rapid Recognition Method for Electronic Components Based on the Improved YOLO-V3 Network , 2019, Electronics.

[40]  Thierry Chateau,et al.  Scene-Specific Pedestrian Detector Using Monte Carlo Framework and Faster R-CNN Deep Model: PhD Forum , 2016, ICDSC.

[41]  Nigel J. Tapper,et al.  Using convolutional neural networks incorporating hierarchical active learning for target-searching in large-scale remote sensing images , 2020, International Journal of Remote Sensing.