Lightweight detection network for arbitrary-oriented vehicles in UAV imagery via precise positional information encoding and bidirectional feature fusion

Feng, Jiangfan; Wang, Jiaxin; Qin, Rui

doi:10.1080/01431161.2023.2197129

Cited by 6 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These dual-stage processes, although precise, incur obvious computational penalties [30,31]. Recently, some efforts have converged on developing optimized single-inference models to reconcile detection accuracy with operational practicality [32].…”

Section: Object Detection In Uav Imagesmentioning

confidence: 99%

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

Feng,

Wang,

Zhang

et al. 2024

CMC

View full text Add to dashboard Cite

Transformer-based models have facilitated significant advances in object detection. However, their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle (UAV) imagery. Addressing these limitations, we propose a hybrid transformer-based detector, H-DETR, and enhance it for dense small objects, leading to an accurate and efficient model. Firstly, we introduce a hybrid transformer encoder, which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently. Furthermore, we propose two novel strategies to enhance detection performance without incurring additional inference computation. Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression. Adversarial denoising learning is a novel enhancement method inspired by adversarial learning, which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise. Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach, achieving a significant improvement in accuracy with a reduction in computational complexity. Our method achieves 31.9% and 21.1% AP on the VisDrone and UAVDT datasets, respectively, and has a faster inference speed, making it a competitive model in UAV image object detection.

show abstract

Section: Object Detection In Uav Imagesmentioning

confidence: 99%

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

Feng,

Wang,

Zhang

et al. 2024

CMC

View full text Add to dashboard Cite

show abstract

“…Aravind et al [21] proposed a new bottleneck module by replacing the 3 × 3 convolution with an MHSA module. The cross-stage partial (CSP) bottleneck transformer module was proposed by Feng et al [22] to model the relationships between vehicles in UAV images. Yu et al [23] proposed a transformer module in the backbone network to improve the performance of detectors in sonar images.…”

Section: Introductionmentioning

confidence: 99%

R-LRBPNet: A Lightweight SAR Image Oriented Ship Detection and Classification Method

Gao,

Chen,

Feng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) has the advantage of continuous observation throughout the day and in all weather conditions, and is used in a wide range of military and civil applications. Among these, the detection of ships at sea is an important research topic. Ships in SAR images are characterized by dense alignment, an arbitrary orientation and multiple scales. The existing detection algorithms are unable to solve these problems effectively. To address these issues, A YOLOV8-based oriented ship detection and classification method using SAR imaging with lightweight receptor field feature convolution, bottleneck transformers and a probabilistic intersection-over-union network (R-LRBPNet) is proposed in this paper. First, a CSP bottleneck with two bottleneck transformer (C2fBT) modules based on bottleneck transformers is proposed; this is an improved feature fusion module that integrates the global spatial features of bottleneck transformers and the rich channel features of C2f. This effectively reduces the negative impact of densely arranged scenarios. Second, we propose an angle decoupling module. This module uses probabilistic intersection-over-union (ProbIoU) and distribution focal loss (DFL) methods to compute the rotated intersection-over-union (RIoU), which effectively alleviates the problem of angle regression and the imbalance between angle regression and other regression tasks. Third, the lightweight receptive field feature convolution (LRFConv) is designed to replace the conventional convolution in the neck. This module can dynamically adjust the receptive field according to the target scale and calculate the feature pixel weights based on the input feature map. Through this module, the network can efficiently extract details and important information about ships to improve the classification performance of the ship. We conducted extensive experiments on the complex scene SAR dataset SRSDD and SSDD+. The experimental results show that R-LRBPNet has only 6.8 MB of model memory, which can achieve 78.2% detection accuracy, 64.2% recall, a 70.51 F1-Score and 71.85% mAP on the SRSDD dataset.

show abstract

Machine Learning for UAV-Aided ITS: A Review With Comparative Study

Telikani,

Sarkar,

et al. 2024

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Lightweight detection network for arbitrary-oriented vehicles in UAV imagery via precise positional information encoding and bidirectional feature fusion

Cited by 6 publications

References 62 publications

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

R-LRBPNet: A Lightweight SAR Image Oriented Ship Detection and Classification Method

Machine Learning for UAV-Aided ITS: A Review With Comparative Study

Contact Info

Product

Resources

About