UAV Aerial Images Research Articles

SOD‐YOLO: Small Object Detection Network for UAV Aerial Images

With the rapid development of the UAV industry, object detection using UAV has become a research hotspot. However, most current object detection models based on deep learning have large parameter counts and are difficult to deploy on embedded devices with limited memory and computational power. To address this problem, a Small Object Detection network for UAV aerial images SOD‐YOLO based on YOLOv8 is proposed, which can meet the application requirements of resource‐constrained devices while ensuring the detection accuracy. First, cross‐domain fusion attention (CDFA) mechanism is proposed to build the C2f‐Attention module in this paper, which is embedded in the backbone network in order to improve the extraction capability of key object features. Meanwhile, the AIFI_LSPE feature fusion module with improved RT‐DETR and the IoU‐aware query selection mechanism are added to the path aggregation network to improve the accuracy of multi‐scale object detection. In addition, in order to balance the sample size ratio and improve the robustness of the network model, we make a new UAV image dataset named VisDrone2019 Extended Edition (VDEE) using images from the VisDrone2019 and UAVDT public datasets. Finally, Shape‐IoU is used as a loss function to reduce the difference between the object GT frame and the detection frame. Experiments show that SOD‐YOLO has a mAP@0.5 of 42.8% in the VDEE dataset, which is increased by 5.1% over YOLOv8. In the VisDrone2019 dataset mAP@0.5 is 39.2%, an improvement of 5.8% over YOLOv8. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

AMFEF-DETR: An End-to-End Adaptive Multi-Scale Feature Extraction and Fusion Object Detection Network Based on UAV Aerial Images

AMFEF-DETR: An End-to-End Adaptive Multi-Scale Feature Extraction and Fusion Object Detection Network Based on UAV Aerial Images

An Improved Instance Segmentation Method for Complex Elements of Farm UAV Aerial Survey Images.

Farm aerial survey layers can assist in unmanned farm operations, such as planning paths and early warnings. To address the inefficiencies and high costs associated with traditional layer construction, this study proposes a high-precision instance segmentation algorithm based on SparseInst. Considering the structural characteristics of farm elements, this study introduces a multi-scale attention module (MSA) that leverages the properties of atrous convolution to expand the sensory field. It enhances spatial and channel feature weights, effectively improving segmentation accuracy for large-scale and complex targets in the farm through three parallel dense connections. A bottom-up aggregation path is added to the feature pyramid fusion network, enhancing the model's ability to perceive complex targets such as mechanized trails in farms. Coordinate attention blocks (CAs) are incorporated into the neck to capture richer contextual semantic information, enhancing farm aerial imagery scene recognition accuracy. To assess the proposed method, we compare it against existing mainstream object segmentation models, including the Mask R-CNN, Cascade-Mask, SOLOv2, and Condinst algorithms. The experimental results show that the improved model proposed in this study can be adapted to segment various complex targets in farms. The accuracy of the improved SparseInst model greatly exceeds that of Mask R-CNN and Cascade-Mask and is 10.8 and 12.8 percentage points better than the average accuracy of SOLOv2 and Condinst, respectively, with the smallest number of model parameters. The results show that the model can be used for real-time segmentation of targets under complex farm conditions.

SkyNet: Multi-scale feature augmentation and diverse expert heads for UAV aerial image object detection

SkyNet: Multi-scale feature augmentation and diverse expert heads for UAV aerial image object detection

Improved YOLOv7-Tiny for Object Detection Based on UAV Aerial Images

Improved YOLOv7-Tiny for Object Detection Based on UAV Aerial Images

Application of Orthophoto Maps Created from UAV Aerial Images for Monitoring Historical and Cultural Heritage Lands

The study investigates the methodology of creating orthophotoplans for immovable historical and cultural heritage sites, beginning from aerial surveys using various UAVs to object vectorization and plan creation. This issue is highly relevant in Ukraine due to rapid reforms in all ministries, including the Ministry of Culture. The reforms are creating a constant need for updated graphical documentation. As immovable historical and cultural heritage sites are in tourist areas with changing infrastructure, traditional surveying methods are impractical due to time constraints. Additionally, the application of UAV aerial imaging for delineating object boundaries and protective zones is more cost-effective. Existing boundaries of heritage lands and those determined from archival materials were overlaid on the created pflans. Orthophotoplans were produced and vectorized at a scale of 1:500 for two research zones: the Holy Trinity Church in Liuboml and the New Jewish Cemetery in Lviv. For the New Jewish Cemetery, boundaries were delineated to assess alignment with the current protective zone. Protective buffer zones around heritage sites were outlined according to both historical and contemporary recommendations in Ukraine. For buffer zones measured from the centroid, development is permitted up to 300 meters for undeveloped areas, with negotiated distances for developed regions, using the 300-meter protective zone as a baseline. The study's uniqueness lies in using a known methodology for creating orthophotoplans based on UAV data to explore options for modeling protective zones based on varying legislative norms over time, incorporating specific nuances. This approach can benefit not only Ukraine but also other countries undergoing reforms in this field.

Lightweight Object Detection Networks for UAV Aerial Images Based on YOLO

Lightweight Object Detection Networks for UAV Aerial Images Based on YOLO

A Lightweight Object Detection Network for UAV Aerial Images

In order to solve the problems of poor detection algorithms, high network model complexity, and difficult deployment of algorithms in the field of aerial image target detection. In this paper, based on YOLOv7-tiny algorithm, a lightweight target detection network for UAV aerial images is designed. Partial convolutional PConv is introduced into the network, and the feature extraction block ELAN is improved, which reduces the computational volume of convolution and the number of model parameters in the feature extraction process, thus solving the problem of model lightweight. The feature fusion part of the network is optimal to improve the feature extraction ability of the network for small targets. At the same time, the large target detection layer in the original network is replaced with the small target detection layer in the aerial images, and the attention mechanism is embedded in the backbone network, which solves the problem of imperfect detection algorithms in aerial images. The loss function of the network is improved so that the prediction frames generated by the detection network and the truth frames match each other in the regression process, thus improving the training process of the network. The experimental results on the publicly available dataset VisDrone2019 dataset show that compared with the YOLOv7-tiny algorithm, the detection accuracy of the proposed model is improved by 0.7%, the recall R is improved by 2.2%, the F1 value is improved by 1.6%, the average detection accuracy mean is improved by 2.3%, and the number of parameters is reduced by 52.1%. Moreover, the image detection speed FPS reaches 66/f.s-1, which meets the real-time requirements of the aerial image detection model detection, and provides a research idea for the field of UAV aerial image detection.

GD-PAN: a multiscale fusion architecture applied to object detection in UAV aerial images

GD-PAN: a multiscale fusion architecture applied to object detection in UAV aerial images

Domain Feature Decomposition for Efficient Object Detection in Aerial Images

Object detection in UAV aerial images faces domain-adaptive challenges, such as changes in shooting height, viewing angle, and weather. These changes constitute a large number of fine-grained domains that place greater demands on the network’s generalizability. To tackle these challenges, we initially decompose image features into domain-invariant and domain-specific features using practical imaging condition parameters. The composite feature can improve domain generalization and single-domain accuracy compared to the conventional fine-grained domain-detection method. Then, to solve the problem of the overfitting of high-frequency imaging condition parameters, we mixed images from different imaging conditions in a balanced sampling manner as input for the training of the detection network. The data-augmentation method improves the robustness of training and reduces the overfitting of high-frequency imaging parameters. The proposed algorithm is compared with state-of-the-art fine-grained domain detectors on the UAVDT and VisDrone datasets. The results show that it achieves an average detection precision improvement of 5.7 and 2.4, respectively. The airborne experiments validate that the algorithm achieves a 20 Hz processing performance for 720P images on an onboard computer with Nvidia Jetson Xavier NX.

A Bayesian framework for 3D point cloud filtering

ABSTRACT This paper introduces a novel Bayesian filtering technique for the filtration of ground points in complex terrain and steep inclines in remote sensing applications. The technique integrates LAStools and statistical techniques, generating a posterior distribution using prior probability and likelihood functions. It is applied to point cloud data from UAV aerial images and DSM formats. The study shows that the Bayesian method improves the outcome in sloping regions compared to other algorithms like LAStools, Statistical, and CSF. In flat terrain, the CSF approach produced the highest F1 score, while the Bayesian method showed degradation but outperformed statistical and LAStools approaches.

渭河干流甘肃段河岸线空间变化数据集（2008、2015、2022年）

As the largest tributary of the Yellow River, the Weihe River has an important influence on the Yellow River in terms of both its flow and sediment load. Carrying out spatial and temporal evolution monitoring of the river shorelines is an important basis for grasping the hydrological changes of the river in the basin. In this study, we used the high-frequency and resource satellite image data of the Gansu section of the Weihe River in 2008, 2015 and 2022 as the base map, and extracted the river shorelines of the Gansu section of the Weihe River through the processing of image ortho-correction, alignment, fusion, mosaicing and cropping; combining with the image characteristics of the image, we adopted the method of interactive deciphering, including the Weihe River management range line, the Weihe River waterfront boundary line, and the Weihe River outer edge boundary line. Additionally, high-precision UAV aerial image data were utilized, integrating typical areas and important markers on the image base map data to ensure the reliability of river shoreline extraction. This dataset can provide data support for studying the hydrological dynamic monitoring and driving mechanisms of the Weihe River main stream. Furthermore, it can serve as basis for making informed decisions regarding the protection of river and lake shorelines and the ecological management of the river.

Multi-scale object detection in UAV images based on adaptive feature fusion.

With the widespread use of UAVs, UAV aerial image target detection technology can be used for practical applications in the military, traffic planning, personnel search and rescue and other fields. In this paper, we propose a multi-scale UAV aerial image detection method based on adaptive feature fusion for solving the problem of detecting small target objects in UAV aerial images. This method automatically adjusts the convolution kernel receptive field and reduces the redundant background of the image by adding an adaptive feature extraction module (AFEM) to the backbone network. This enables it to obtain more accurately and effectively small target feature information. In addition, we design an adaptive feature weighted fusion network (SBiFPN) to effectively enhance the representation of shallow feature information of small targets. Finally, we add an additional small target detection scale to the original network to expand the receptive field of the network and strengthen the detection of small target objects. The training and testing are carried out on the VisDrone public dataset. The experimental results show that the proposed method can achieve 38.5% mAP, which is 2.0% higher than the baseline network YOLOv5s, and can still detect the UAV aerial image well in complex scenes.

Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery

The cost-effectiveness, compact size, and inherent flexibility of UAV technology have garnered significant attention. Utilizing sensors, UAVs capture ground-based targets, offering a novel perspective for aerial target detection and data collection. However, traditional UAV aerial image recognition techniques suffer from various drawbacks, including limited payload capacity, resulting in insufficient computing power, low recognition accuracy due to small target sizes in images, and missed detections caused by dense target arrangements. To address these challenges, this study proposes a lightweight UAV image target detection method based on YOLOv8, named Aero-YOLO. The specific approach involves replacing the original Conv module with GSConv and substituting the C2f module with C3 to reduce model parameters, extend the receptive field, and enhance computational efficiency. Furthermore, the introduction of the CoordAtt and shuffle attention mechanisms enhances feature extraction, which is particularly beneficial for detecting small vehicles from a UAV perspective. Lastly, three new parameter specifications for YOLOv8 are proposed to meet the requirements of different application scenarios. Experimental evaluations were conducted on the UAV-ROD and VisDrone2019 datasets. The results demonstrate that the algorithm proposed in this study improves the accuracy and speed of vehicle and pedestrian detection, exhibiting robust performance across various angles, heights, and imaging conditions.

Bayesian-based binary compression with bandwidth optimisation for UAV aerial images

Bayesian-based binary compression with bandwidth optimisation for UAV aerial images

Cross-Modal Oriented Object Detection of UAV Aerial Images Based on Image Feature

Cross-Modal Oriented Object Detection of UAV Aerial Images Based on Image Feature

Small object detection model for UAV aerial image based on YOLOv7

Small object detection model for UAV aerial image based on YOLOv7

Adaptive clustering object detection method for UAV images under long-tailed distributions

UAV images are characterized by small targets, difficult to identify in the background image, clustering and sparse distribution of targets, etc. Many researchers have proposed the clustering target detection method (ClusDet) for UAV images. However, due to the large differences in target scales and uneven distribution of targets in UAV images, showing long-tailed distribution, the traditional ClusDet algorithm tends to truncate large and medium targets in the process of clustering; in the detection process, the fixed-threshold NMS method in the ClusDet algorithm is difficult to adaptively detect targets of different sizes, clustering and mutual occlusion. To address the above problems, this paper proposes an adaptive clustered target detection algorithm based on UAV images under long-tail distribution. The method is divided into three sub-networks: the adaptive clustering sub-network, which outputs several segmented images of small target clustering regions by extracting potential small target clustering regions in UAV aerial images; the segmentation and filling sub-network, which fills the images with disproportionate aspect ratio for the output of the adaptive clustering network to keep the size of the images within the reasonable range required by the detection network; and the detection sub-network, which detects the targets within the reasonable range required by the detection network by introducing attention mechanism, using variable threshold NMS, and training using sample balancing strategy effectively improve the detection accuracy of targets in the clustered region. Trained in VisDrone 2019 dataset, the simulation results show that the UAV image adaptive clustering target detection method based on long-tailed distribution has a large improvement in the detection accuracy of small targets, and can effectively improve the detection accuracy of the model for targets in the aggregation region, while the model has good generalization ability.

ATS-YOLOv7: A Real-Time Multi-Scale Object Detection Method for UAV Aerial Images Based on Improved YOLOv7

The objects in UAV aerial images have multiple scales, dense distribution, and occlusion, posing considerable challenges for object detection. In order to address this problem, this paper proposes a real-time multi-scale object detection method based on an improved YOLOv7 model (ATS-YOLOv7) for UAV aerial images. First, this paper introduces a feature pyramid network, AF-FPN, which is composed of an adaptive attention module (AAM) and a feature enhancement module (FEM). AF-FPN reduces the loss of deep feature information due to the reduction of feature channels in the convolution process through the AAM and FEM, strengthens the feature perception ability, and improves the detection speed and accuracy for multi-scale objects. Second, we add a prediction head based on a transformer encoder block on the basis of the three-head structure of YOLOv7, improving the ability of the model to capture global information and feature expression, thus achieving efficient detection of objects with tiny scales and dense occlusion. Moreover, as the location loss function of YOLOv7, CIoU (complete intersection over union), cannot facilitate the regression of the prediction box angle to the ground truth box—resulting in a slow convergence rate during model training—this paper proposes a loss function with angle regression, SIoU (soft intersection over union), in order to accelerate the convergence rate during model training. Finally, a series of comparative experiments are carried out on the DIOR dataset. The results indicate that ATS-YOLOv7 has the best detection accuracy (mAP of 87%) and meets the real-time requirements of image processing (detection speed of 94.2 FPS).

Boundary refinement network with semantic embedding connections for UAV aerial image semantic segmentation

Boundary refinement network with semantic embedding connections for UAV aerial image semantic segmentation