FE-YOLO: A Feature Enhancement Network for Remote Sensing Target Detection

Xu, Danqing; Wu, Yiquan

doi:10.3390/rs13071311

Cited by 46 publications

(21 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithm mAP Faster R-CNN [55] 87.24 L-RCNN 2020 [55] 92.54 DFL 2018 [55] 90.54 FCN 2017 [56] 81.1 Faster RER-CNN 2018 [57] 82. 4 Ju, et al 2019 [58] 80.16 Improved FBPN Based Detection Network [37] 91.27 FE-YOLO 2021 [59] 89.12 DAR-Net 95.13 Computational Intelligence and Neuroscience Algorithm AP R-DFPN 2018 [28] 82.5 Improved Faster R-CNN [60] 83.0 DRBox 2017 [61] 85.0 O 2 -DNet 2016 [62] 86.72 P-RSDet 2020 [35] 87.36 R-FCN 2016 [35] 89.3 Deformable R-FCN [35] 91.7 S2ARN 2019 [61] 92.2 FADet 2019 [63] 92.72 RetinaNet-H 2019 [64] 93.6 R3Det 2019 [64] 94.14 A2RMNet [60] 94.65 SCRDet++ 2020 [65] 94.97 PolarDet 2020 [66] 94.96 ICN 2018 [29] 95.67 UCAS + NWPU + VS-GANs 2019 [67] 96.12 Improved FBPN Based Detection Network [37] 96.18 FE-YOLO 2021 [59] 90.85 DAR-Net 96.78 Algorithm AP LR-CNN 2020 [68] 56.09 Yang et al 2018 [37] 61.16 RoI Transformer [69] 68.81 e Light-Head R-CNN OBB + W/FPN [69] 70.15 Faster R-CNN Adapted 2018 [70] 74.9 DYOLO Module B 2018 [70] 76.0 SSD Adapted 2018 [70] 76.3 DFRCNN 2018 [71] 76.5 PolarDet [66] 78.53 DSSD 2017 [21] 79.0 DYOLO Module A 2018 [70] 79.2 RefineDet 2018 [70] 80.0 Ju, et al 2019 [58] 88.63 Faster R-CNN with MSCA…”

Section: Results On the Dota Datasetmentioning

confidence: 99%

“…As a result, some public datasets such as NWPU VHR-10 [53], RSOD [54], VEDAI, UCAS-AOD, and DOTA are produced recently. Among these datasets, VEDIA, UCAS-AOD, and DOTA are the most commonly used datasets to evaluate vehicle detection algorithms for aerial images [55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72]. To get better comparisons with state-of-the-art algorithms, these three datasets are also used in this section to evaluate the proposed framework and its components.…”

Section: Datasets Deep Learning Based Vision Algorithms Require Large-scale Labeled Training Datamentioning

confidence: 99%

See 1 more Smart Citation

DAR‐Net: Dense Attentional Residual Network for Vehicle Detection in Aerial Images

Wang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of deep learning and the wide usage of Unmanned Aerial Vehicles (UAVs), CNN-based algorithms of vehicle detection in aerial images have been widely studied in the past several years. As a downstream task of the general object detection, there are some differences between the vehicle detection in aerial images and the general object detection in ground view images, e.g., larger image areas, smaller target sizes, and more complex background. In this paper, to improve the performance of this task, a Dense Attentional Residual Network (DAR-Net) is proposed. The proposed network employs a novel dense waterfall residual block (DW res-block) to effectively preserve the spatial information and extract high-level semantic information at the same time. A multiscale receptive field attention (MRFA) module is also designed to select the informative feature from the feature maps and enhance the ability of multiscale perception. Based on the DW res-block and MRFA module, to protect the spatial information, the proposed framework adopts a new backbone that only downsamples the feature map 3 times; i.e., the total downsampling ratio of the proposed backbone is 8. These designs could alleviate the degradation problem, improve the information flow, and strengthen the feature reuse. In addition, deep-projection units are used to reduce the impact of information loss caused by downsampling operations, and the identity mapping is applied to each stage of the proposed backbone to further improve the information flow. The proposed DAR-Net is evaluated on VEDAI, UCAS-AOD, and DOTA datasets. The experimental results demonstrate that the proposed framework outperforms other state-of-the-art algorithms.

show abstract

Section: Results On the Dota Datasetmentioning

confidence: 99%

Section: Datasets Deep Learning Based Vision Algorithms Require Large-scale Labeled Training Datamentioning

confidence: 99%

DAR‐Net: Dense Attentional Residual Network for Vehicle Detection in Aerial Images

Wang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…(1) The basis of wide-baseline image matching is the extraction of local invariant features, which are local features that remains table between the stereo images under geometric or radiometric distortions, such as viewpoint change or illumination variation. In recent years, researchers have focused on exploring feature detection schemes for deep learning with enhancing network [50]. Using the supervised learning strategy as an example, Lenc et al first proposed a local invariant feature loss function L cov (x) [51].…”

Section: Deep-learning-based Feature Detectionmentioning

confidence: 99%

Review of Wide-Baseline Stereo Image Matching Based on Deep Learning

et al. 2021

View full text Add to dashboard Cite

Strong geometric and radiometric distortions often exist in optical wide-baseline stereo images, and some local regions can include surface discontinuities and occlusions. Digital photogrammetry and computer vision researchers have focused on automatic matching for such images. Deep convolutional neural networks, which can express high-level features and their correlation, have received increasing attention for the task of wide-baseline image matching, and learning-based methods have the potential to surpass methods based on handcrafted features. Therefore, we focus on the dynamic study of wide-baseline image matching and review the main approaches of learning-based feature detection, description, and end-to-end image matching. Moreover, we summarize the current representative research using stepwise inspection and dissection. We present the results of comprehensive experiments on actual wide-baseline stereo images, which we use to contrast and discuss the advantages and disadvantages of several state-of-the-art deep-learning algorithms. Finally, we conclude with a description of the state-of-the-art methods and forecast developing trends with unresolved challenges, providing a guide for future work.

show abstract

“…As an important problem in computer vision, object detection is widely used in face detection [1,2], traffic sign detection [3,4], remote sensing image detection [5,6], big data [7,8], and other related fields. With the great progress of deep learning on image classification tasks, deep learning-based target detection algorithms have gradually become main stream.…”

Section: Introductionmentioning

confidence: 99%

Lightweight target detection algorithm based on improved YOLOv4

Wang

Chen

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Traditional YOLOv4 object detection network is difficult to be applied to mobile embedded devices because it has some deficiencies such as complex structure and too many parameters. In this paper, the authors propose a lightweight object detection algorithm. Firstly, Mobienetv3 is used to replace the original feature extraction network, and the Mish function is used to be the activation function, which reduces the number of model parameters. Secondly, the dilated convolution is used to replace the maximum pooling operation in the original spatial pyramid pooling (SPP) structure. Then, a custom Dcn-Dw structure is used to replace the convolution operation in the original PANet, which improves the accuracy of the model for irregular object detection and reduces the model size. Finally, a CBAM lightweight attention mechanism module is introduced in front of the YOLO Head, which further improves the model accuracy. An experiment on the VOC2007 dataset is carried out, and the results show that the mean average precision (mAP) is 80.3% and frames per second (FPS) is 15. At the expense of 3% accuracy, the detection speed is increased to two to three times, and the model size is reduced to one-fifth of the original model. The lightweight object detection algorithm can suit for real-time detection tasks on resource-constrained embedded devices.

show abstract

FE-YOLO: A Feature Enhancement Network for Remote Sensing Target Detection

Cited by 46 publications

References 41 publications

DAR‐Net: Dense Attentional Residual Network for Vehicle Detection in Aerial Images

DAR‐Net: Dense Attentional Residual Network for Vehicle Detection in Aerial Images

Review of Wide-Baseline Stereo Image Matching Based on Deep Learning

Lightweight target detection algorithm based on improved YOLOv4

Contact Info

Product

Resources

About