SuperDet: An Efficient Single-Shot Network for Vehicle Detection in Remote Sensing Images

Ju, Moran; Niu, Buniu; Jin, Si-Nian; Liu, Zhaoming

doi:10.3390/electronics12061312

Cited by 4 publications

(14 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…S 2 ANet selects RetinaNet as the backbone network and replaces the original horizontal box regression with oriented bounding box regression while the rest settings remain unchanged. After RetinaNet extracts features of the remote sensing image, the backbone sends the future maps to the Neck for feature fusion.…”

Section: S 2 Anetmentioning

confidence: 99%

“…Different models have a different detection and recognition accuracy of various aircraft types in the FAIR1M dataset. In order to verify the effectiveness of the improved algorithm in this paper, we compare the FS 2 ANet model with excellent models in remote sensing rotated object detection, such as Roi-Transformer, SASM, ReDet, R 3 Det, Faster-Rcnn, Rotated RetinaNet, GWD, and S 2 ANet, in the experiment. The comparative experimental results are shown in Table 2, which mainly compares the mAP 0.5 , AP, and Recall of each algorithm.…”

Section: Image Enhancementmentioning

confidence: 99%

“…There is no significant training fluctuation like Roi-Transformer, ReDet, and SASM. The line chart of FS 2 ANet is closest to the upper left corner, which indicates that The mAP 0.5 of the FS 2 ANet model is 46.82%, which is 4.55%, 13.49%, 4.83%, 5%, 5.06%, 8.51%, 4.54%, and 3.87% higher than Roi Transformer, SASM, ReDet, R 3 Det, Faster-Rcnn, Rotated RetinaNet, GWD, and S 2 ANet, respectively. The FS 2 ANet model has a significant improvement in accuracy.…”

Section: Image Enhancementmentioning

confidence: 99%

“…In the last decade, many scholars have used a Convolutional Neural Network (CNN) [1] to improve a large number of object detection networks in the field of remote sensing object detection due to its excellent feature extraction ability [2][3][4]. Compared with traditional remote sensing aircraft detection methods, deep learning methods are faster, more accurate, and have a better generalization ability, and gradually become the preferred choice for remote sensing aircraft object detection.…”

Section: Introductionmentioning

confidence: 99%

“…In order to solve the above problems, this paper proposes a remote sensing aircraft object detection and fine-grained recognition algorithm called FS 2 ANet, and the main innovations of this algorithm are as follows:…”

mentioning

confidence: 99%

See 4 more Smart Citations

Aircraft Detection and Fine-Grained Recognition Based on High-Resolution Remote Sensing Images

et al. 2023

View full text Add to dashboard Cite

In order to realize the detection and recognition of specific types of an aircraft in remote sensing images, this paper proposes an algorithm called Fine-grained S2ANet (FS2ANet) based on the improved Single-shot Alignment Network (S2ANet) for remote sensing aircraft object detection and fine-grained recognition. Firstly, to address the imbalanced number of instances of various aircrafts in the dataset, we perform data augmentation on some remote sensing images using flip and color space transformation methods. Secondly, this paper selects ResNet101 as the backbone, combines space-to-depth (SPD) to improve the FPN structure, constructs the FPN-SPD module, and builds the aircraft fine feature focusing module (AF3M) in the detection head of the network, which reduces the loss of fine-grained information in the process of feature extraction, enhances the extraction capability of the network for fine aircraft features, and improves the detection accuracy of remote sensing micro aircraft objects. Finally, we use the SkewIoU based on Kalman filtering (KFIoU) as the algorithm’s regression loss function, improving the algorithm’s convergence speed and the object boxes’ regression accuracy. The experimental results of the detection and fine-grained recognition of 11 types of remote sensing aircraft objects such as Boeing 737, A321, and C919 using the FS2ANet algorithm show that the mAP0.5 of FS2ANet is 46.82%, which is 3.87% higher than S2ANet, and it can apply to the field of remote sensing aircraft object detection and fine-grained recognition.

show abstract

Section: S 2 Anetmentioning

confidence: 99%

Section: Image Enhancementmentioning

confidence: 99%

Section: Image Enhancementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Aircraft Detection and Fine-Grained Recognition Based on High-Resolution Remote Sensing Images

et al. 2023

View full text Add to dashboard Cite

show abstract

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

Zhao,

Guo,

Shao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Satellite remote sensing technology significantly contributes to intelligent transportation by optimizing traffic planning via global perspectives and rich data, enhancing traffic efficiency and reducing environmental impact. However, current target detection models frequently exhibit low accuracy in vehicle detection tasks due to complex background interference in satellite imageries and a need for critical semantic information. To improve vehicle target detection accuracy, this study introduces SatDetX-YOLO, a vehicle detection model for satellite remote sensing images based on YOLOv8. The model involves reconstructing the backbone network with FasterNet for enhanced feature extraction, a redesigned decoupled head for improved computational efficiency and complex data processing, and incorporating the Deformable Attention Module (DAM) to increase sensitivity to small targets and feature correlation capture. Employing the Maximum Probabilistic Distance IoU (MPDIoU) loss function enhances adaptability and generalization to diverse vehicle targets. Experimental results demonstrate that under comparable FPS, SatDetX-YOLO's Precision (P), Recall (R), and Mean Average Precision (mAP) improved by 3.5%, 3.3%, and 3.2%, respectively. Despite a minor reduction in FPS, the model significantly enhances detection accuracy, striking a balance between accuracy and speed.

show abstract

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

Du,

Jiang

2024

CMC

View full text Add to dashboard Cite

To address the challenges of high complexity, poor real-time performance, and low detection rates for small target vehicles in existing vehicle object detection algorithms, this paper proposes a real-time lightweight architecture based on You Only Look Once (YOLO) v5m. Firstly, a lightweight upsampling operator called Content-Aware Reassembly of Features (CARAFE) is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles, reducing the missed detection rate and false detection rate. Secondly, a new prediction layer for tiny targets is added, and the feature fusion network is redesigned to enhance the detection capability for small targets. Finally, this paper applies L1 regularization to train the improved network, followed by pruning and fine-tuning operations to remove redundant channels, reducing computational and parameter complexity and enhancing the detection efficiency of the network. Training is conducted on the VisDrone2019-DET dataset. The experimental results show that the proposed algorithm reduces parameters and computation by 63.8% and 65.8%, respectively. The average detection accuracy improves by 5.15%, and the detection speed reaches 47 images per second, satisfying real-time requirements. Compared with existing approaches, including YOLOv5m and classical vehicle detection algorithms, our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.

show abstract

SuperDet: An Efficient Single-Shot Network for Vehicle Detection in Remote Sensing Images

Cited by 4 publications

References 45 publications

Aircraft Detection and Fine-Grained Recognition Based on High-Resolution Remote Sensing Images

Aircraft Detection and Fine-Grained Recognition Based on High-Resolution Remote Sensing Images

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

Contact Info

Product

Resources

About