An Efficient Rep-Style Gaussian–Wasserstein Network: Improved UAV Infrared Small Object Detection for Urban Road Surveillance and Safety

Aibibu, Tuerniyazi; Lan, Jinhui; Zeng, Yiliang; Lu, Weijian; Gu, Naiwei

doi:10.3390/rs16010025

Cited by 6 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the relatively limited processing power and storage space of UAV, highprecision target detection models such as YOLOv8 are unsuitable for effective operation on UAV due to their high number of parameters and calculations. T. Aibibu et al [33] gives that the mAP of YOLOv8 on the HIT-UAV dataset is 75.5%, while according to the data provided by the official YOLO, the number of references of [34] YOLOv8 is 68.2 M. Cui.C et al [22] gives the LCNet parameter number without improvement as only 3.0 M. The number of parameters of LCNet network is much smaller than that of YOLOv8. Facing the airborne terminal deployment requirements for real-time processing and rapid identification, lightweight networks are the key to achieving efficient real-time identification.…”

Section: Improved Network Based On Lcnetmentioning

confidence: 99%

“…The dataset consists of 2898 thermal infrared images with a resolution of 640 × 512, contains 24,899 labels, and is divided into five categories, namely Person, Car, Bicycle, OtherVehicle, and don-care. Currently, only T. Aibibu et al [33] and X. Zhao et al [35] have launched and published model detection performance optimization work on the HIT-UAV dataset. Among them, T. Aibibu et al [33] were the first team to optimize the recognition performance of five categories of the complete dataset, and they finally achieved an accuracy of 80%.…”

Section: Datasetsmentioning

confidence: 99%

“…Currently, only T. Aibibu et al [33] and X. Zhao et al [35] have launched and published model detection performance optimization work on the HIT-UAV dataset. Among them, T. Aibibu et al [33] were the first team to optimize the recognition performance of five categories of the complete dataset, and they finally achieved an accuracy of 80%. X. Zhao et al [35] only optimized the recognition performance of the vehicle categories in this dataset, and the accuracy was 94.5%.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Recognition Algorithm of Small Target for UAV Infrared Detection

Zhang,

Zhou,

2024

Sensors

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) infrared detection has problems such as weak and small targets, complex backgrounds, and poor real-time detection performance. It is difficult for general target detection algorithms to achieve the requirements of a high detection rate, low missed detection rate, and high real-time performance. In order to solve these problems, this paper proposes an improved small target detection method based on Picodet. First, to address the problem of poor real-time performance, an improved lightweight LCNet network was introduced as the backbone network for feature extraction. Secondly, in order to solve the problems of high false detection rate and missed detection rate due to weak targets, the Squeeze-and-Excitation module was added and the feature pyramid structure was improved. Experimental results obtained on the HIT-UAV public dataset show that the improved detection model’s real-time frame rate increased by 31 fps and the average accuracy (MAP) increased by 7%, which proves the effectiveness of this method for UAV infrared small target detection.

show abstract

Section: Improved Network Based On Lcnetmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Recognition Algorithm of Small Target for UAV Infrared Detection

Zhang,

Zhou,

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Yang et al [ 27 ] merged an enhanced channel attention mechanism with a better version of E-ELAN [ 28 ] to introduce an upgraded YOLOv7 model, which is designed to identify small spots on grape leaves. Aibibu et al [ 29 ] combined the strengths of various networks to improve the detection performance of small target vehicles. Liu et al [ 30 ] utilized dynamic snake convolution [ 31 ] and introduced WISE-IoU [ 32 ] to boost the model’s effectiveness in detecting small traffic-related objects.…”

Section: Related Workmentioning

confidence: 99%

OD-YOLO: Robust Small Object Detection Model in Remote Sensing Image with a Novel Multi-Scale Feature Fusion

Bu,

Ye,

Tie

et al. 2024

Sensors

View full text Add to dashboard Cite

As remote sensing technology has advanced, the use of satellites and similar technologies has become increasingly prevalent in daily life. Now, it plays a crucial role in hydrology, agriculture, and geography. Nevertheless, because of the distinct qualities of remote sensing, including expansive scenes and small, densely packed targets, there are many challenges in detecting remote sensing objects. Those challenges lead to insufficient accuracy in remote sensing object detection. Consequently, developing a new model is essential to enhance the identification capabilities for objects in remote sensing imagery. To solve these constraints, we have designed the OD-YOLO approach that uses multi-scale feature fusion to improve the performance of the YOLOv8n model in small target detection. Firstly, traditional convolutions have poor recognition capabilities for certain geometric shapes. Therefore, in this paper, we introduce the Detection Refinement Module (DRmodule) into the backbone architecture. This module utilizes Deformable Convolutional Networks and the Hybrid Attention Transformer to strengthen the model’s capability for feature extraction from geometric shapes and blurred objects effectively. Meanwhile, based on the Feature Pyramid Network of YOLO, at the head of the model framework, this paper enhances the detection capability by introducing a Dynamic Head to strengthen the fusion of different scales features in the feature pyramid. Additionally, to address the issue of detecting small objects in remote sensing images, this paper specifically designs the OIoU loss function to finely describe the difference between the detection box and the true box, further enhancing model performance. Experiments on the VisDrone dataset show that OD-YOLO surpasses the compared models by at least 5.2% in mAP50 and 4.4% in mAP75, and experiments on the Foggy Cityscapes dataset demonstrated that OD-YOLO improved mAP by 6.5%, demonstrating outstanding results in tasks related to remote sensing images and adverse weather object detection. This work not only advances the research in remote sensing image analysis, but also provides effective technical support for the practical deployment of future remote sensing applications.

show abstract

“…Ref. [20] proposed an efficient rep-style Gaussian-Wasserstein network (ERGW-net), which effectively addressed the challenges of small object sizes and low contrast in infrared aerial imagery. Ref.…”

Section: Introductionmentioning

confidence: 99%

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Zhao,

Zhang,

Zhang

2024

Remote Sensing

View full text Add to dashboard Cite

Small object detection poses significant challenges in the realm of general object detection, primarily due to complex backgrounds and other instances interfering with the expression of features. This research introduces an uncomplicated and efficient algorithm that addresses the limitations of small object detection. Firstly, we propose an efficient cross-scale feature fusion attention module called ECFA, which effectively utilizes attention mechanisms to emphasize relevant features across adjacent scales and suppress irrelevant noise, tackling issues of feature redundancy and insufficient representation of small objects. Secondly, we design a highly efficient convolutional module named SEConv, which reduces computational redundancy while providing a multi-scale receptive field to improve feature learning. Additionally, we develop a novel dynamic focus sample weighting function called DFSLoss, which allows the model to focus on learning from both normal and challenging samples, effectively addressing the problem of imbalanced difficulty levels among samples. Moreover, we introduce Wise-IoU to address the impact of poor-quality examples on model convergence. We extensively conduct experiments on four publicly available datasets to showcase the exceptional performance of our method in comparison to state-of-the-art object detectors.

show abstract

An Efficient Rep-Style Gaussian–Wasserstein Network: Improved UAV Infrared Small Object Detection for Urban Road Surveillance and Safety

Cited by 6 publications

References 43 publications

Real-Time Recognition Algorithm of Small Target for UAV Infrared Detection

Real-Time Recognition Algorithm of Small Target for UAV Infrared Detection

OD-YOLO: Robust Small Object Detection Model in Remote Sensing Image with a Novel Multi-Scale Feature Fusion

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Contact Info

Product

Resources

About