Multi-scale Feature Fused Single Shot Detector for Small Object Detection in UAV Images

Less effective information is obtained by the object detection network, due to the small size of the detection object in the entire image, the complex background, and the dense object in unmanned aerial vehicle (UAV) images. In response to the difficulties encountered, a small object detection method in UAV images is proposed as an improved YOLOv5-based algorithm in this paper. First, the space-to-depth(SPD) conv module is introduced into the basic feature extraction network, to improve significant loss of image information during downsampling. Then, various attention mechanisms are added, to intensify the acquisition of regions of interest in UAV images. Finally, the multiscale detection module is improved, to enhance the network's ability to detect small objects in UAV images. By conducting experiments on the VisDrone-DET2019 dataset, the test results of the established model show. The improved algorithm achieved a Mean Average Precision (mAP) of 41.8%, which is 7.8% better than the baseline network. In addition, the detection performance is better than most current mainstream target detection algorithms and is of some practical value.

Accurate object detection in unmanned aerial vehicle (UAV) images plays a crucial role in fields such as aviation, transportation, and agriculture. However, UAV images often contain a high proportion of small objects, and the limited resources of UAV platforms make it challenging for existing small object detection algorithms to balance detection performance and resource consumption. To address these issues, a lightweight small object detection algorithm called SRP-YOLO is proposed. Compared to the YOLOv8 network, the following improvements are made: first, a high-resolution detection head is designed; second, a receptive field attention convolution module tailored for small UAV objects is introduced to replace the standard convolution module, enhancing the detection capability for small objects and significantly improving their feature representation; Third, partial convolution is combined with C2f to replace some of the standard convolutions, fully leveraging the high-resolution information from shallow features. Finally, A normalized Gaussian Wasserstein Distance (NWD) metric is introduced to reduce the sensitivity of Intersection over Union (IoU) to minor positional deviations of small objects. On VisDrone-DET2019, SRP-YOLO reduces parameters while improving mAP 0.5 by 7.9%. Generalization tests on TinypersonV2 and RAIVD confirm significant gains in small object detection.

With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.

Unmanned aerial vehicles (UAVs) have been widely used in post-disaster search and rescue operations, object tracking, and other tasks. Therefore, the autonomous perception of UAVs based on computer vision has become a research hotspot in recent years. However, UAV images include dense objects, small objects, and arbitrary object directions, which bring about significant challenges to existing object detection methods. To alleviate these issues, we propose a global-local feature enhanced network (GLF-Net). Considering the difficulty of processing UAV images with complex scenes and dense objects, we designed a backbone based on an involution and self-attention that can extract effective features from complex objects. A multiscale feature fusion module is also proposed to address the presence of numerous small objects in UAV images through multiscale object detection and feature fusion. To accurately detect rotated objects, a rotated regional proposal network was designed based on the midpoint offset representation, which can apply a rotated box to determine the real direction and contour of an object. GLF-Net achieves a state-of-the-art detection accuracy (86.52% mAP) on our created RO-UAV dataset, while achieving 96.95% and 97% mAP on the public datasets HRSC2016 and UCAS-AOU, respectively. The experimental results demonstrate that our method achieves a high detection accuracy and generalization, which can meet the practical requirements of UAVs under various complex scenarios.

Object detection in images taken by unmanned aerial vehicles (UAVs) is drawing ever-increasing research interests. Due to the flexibility of UAVs, their shooting altitude often changes rapidly, which results in drastic changes in the scale size of the identified objects. Meanwhile, there are often many small objects obscured from each other in high-altitude photography, and the background of their captured images is also complex and variable. These problems lead to a colossal challenge with object detection in UAV aerial photography images. Inspired by the characteristics of eagles, we propose an Eagle-YOLO detection model to address the above issues. First, according to the structural characteristics of eagle eyes, we integrate the Large Kernel Attention Module (LKAM) to enable the model to find object areas that need to be focused on. Then, in response to the eagle’s characteristic of experiencing dramatic changes in its field of view when swooping down to hunt at high altitudes, we introduce a large-sized feature map with rich information on small objects into the feature fusion network. The feature fusion network adopts a more reasonable weighted Bi-directional Feature Pyramid Network (Bi-FPN). Finally, inspired by the sharp features of eagle eyes, we propose an IoU loss named Eagle-IoU loss. Extensive experiments are performed on the VisDrone2021-DET dataset to compare it with the baseline model YOLOv5x. The experiments showed that Eagle-YOLO outperformed YOLOv5x by 2.86% and 4.23% in terms of the mAP and AP50, respectively, which demonstrates the effectiveness of Eagle-YOLO for object detection in UAV aerial image scenes.

This study presents a modified YOLOv5 algorithm specifically designed to enhance small‐object detection in unmanned aerial vehicle (UAV) images. Traditional object detection in UAV images is particularly challenging due to the high altitude of the cameras, which results in small object sizes and varying viewing angles. To address these challenges, the algorithm incorporates an additional prediction head to detect objects across a wide range of scales, a channel feature fusion with involution (CFFI) block to minimize information loss, a convolutional block attention module (CBAM) to highlight the crucial spatial and channel features, and a C3 structure with a Transformer block (C3TR) to capture contextual information. The algorithm additionally employs soft non‐maximum suppression to enhance the bounding box scoring of overlapping objects in dense scenes. Extensive experiments were conducted on the VisDrone‐DET2019 dataset, which demonstrated the effectiveness of the proposed algorithm. The results showed improvements with precision scores of 55.0%, recall scores of 44.6%, mean average precision scores of mAP50 = 50.9% and mAP50:95 = 33.0% on the VisDrone‐DET2019 validation set, and precision of 50.8%, recall of 37.3%, mAP50 = 44.2%, and mAP50:95 = 27.3% on the VisDrone‐DET2019 testing set. The improved performance is due to the incorporation of attention mechanisms, which allow the proposed model to stay lightweight while still extracting the features needed to detect small objects.

Real-time object detection is critical for unmanned aerial vehicles (UAVs) performing various tasks. However, efficiently deploying detection models on UAV platforms with limited storage and computational resources remains a significant challenge. To address this issue, we propose ELNet, an efficient and lightweight object detection model based on YOLOv12n. First, based on an analysis of UAV image characteristics, we strategically remove two A2C2f modules from YOLOv12n and adjust the size and number of detection heads. Second, we propose a novel lightweight detection head, EPGHead, to alleviate the computational burden introduced by adding the large-scale detection head. In addition, since YOLOv12n employs standard convolution for downsampling, which is inefficient for extracting UAV image features, we design a novel downsampling module, EDown, to further reduce model size and enable more efficient feature extraction. Finally, to improve detection in UAV imagery with dense, small, and scale-varying objects, we propose DIMB-C3k2, an enhanced module built upon C3k2, which boosts feature extraction under complex conditions. Compared with YOLOv12n, ELNet achieves an 88.5% reduction in parameter count and a 52.3% decrease in FLOPs, while increasing mAP50 by 1.2% on the VisDrone dataset and 0.8% on the HIT-UAV dataset, reaching 94.7% mAP50 on HIT-UAV. Furthermore, the model achieves a frame rate of 682 FPS, highlighting its superior computational efficiency without sacrificing detection accuracy.

Detecting small objects reliably is particularly difficult in modern neural architectures, where scale imbalance, background clutter, and high object density frequently degrade feature quality and prediction accuracy. To address these challenges, we propose YOLO-Super Resolution and Attention (YOLO-SRA), a multi-scale neural architecture enhanced with attention and super-resolution. The architecture introduces High-Resolution Feature Enhancement (HRFE) to better represent small objects without incurring high computational cost, a Grouped Multi-Scale Split Attention (GMSA) mechanism to efficiently extract features from densely distributed objects, and Weighted Fine-Grained Cross-Scale Fusion (WFCF) network for adaptive multi-scale feature integration with Unmanned Aerial Vehicle (UAV)-specific adjustments. The Spatial-Attentive Non-Maximum Suppression (SA-NMS) strategy is further employed to reduce missed detections in overlapping regions. Extensive experiments on the VisDrone dataset demonstrate that YOLO-SRA outperforms the baseline YOLOv11, achieving 12.5% and 11.3% increase in mAP 50 and mAP 50 : 95 , respectively, while reducing the parameter count by 6.0M. These results highlight the effectiveness of the proposed approach as a methodological contribution to neural systems for small object detection in aerial image.

RT-DETR (Real-Time DEtection TRansformer) has recently emerged as a promising model for object detection in images, yet its performance on small objects remains limited, particularly in terms of robustness. While various approaches have been explored, developing effective solutions for reliable small object detection remains a significant challenge. This paper introduces an adapted variant of RT-DETR, specifically designed to enhance robustness in small object detection. The model was first designed on one dataset and subsequently transferred to others to validate generalization. Key contributions include replacing components of the feed-forward neural network (FFNN) within a hybrid encoder with Hebbian, randomized, and Oja-inspired layers; introducing a modified loss function; and applying multi-scale feature fusion with fuzzy attention to refine encoder representations. The proposed model is evaluated on the Al-Cast Detection X-ray dataset, which contains small components from high-pressure die-casting machines, and the PCB quality inspection dataset, which features tiny hole anomalies. The results show that the optimized model achieves an mAP of 0.513 for small objects—an improvement from the 0.389 of the baseline RT-DETR model on the Al-Cast dataset—confirming its effectiveness. In addition, this paper contributes a mini-literature review of recent RT-DETR enhancements, situating our work within current research trends and providing context for future development.

In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters.

With the rapid development of deep learning, unmanned aerial vehicles (UAVs) have acquired intelligent perception capabilities, demonstrating efficient data collection across various fields. In UAV perspective scenarios, captured images often contain small and unevenly distributed objects, and are typically high-resolution. This makes object detection in UAV imagery more challenging compared to conventional detection tasks. To address this issue, we propose a lightweight object detection algorithm, BGF-YOLOv10, specifically designed for small object detection, based on an improved version of YOLOv10n. First, we introduce a novel YOLOv10 architecture tailored for small objects, incorporating BoTNet, variants of C2f and C3 in the backbone, along with an additional small object detection head, to enhance detection performance for small objects. Second, we embed GhostConv into both the backbone and head, effectively reducing the number of parameters by nearly half. Finally, we insert a Patch Expanding Layer module in the neck to restore the feature spatial resolution. Experimental results on the VisDrone-DET2019 and UAVDT datasets demonstrate that our method significantly improves detection accuracy compared to YOLO series networks. Moreover, when compared to other state-of-the-art networks, our approach achieves a substantial reduction in the number of parameters.

Unmanned Aerial Vehicle (UAV) image object detection plays a crucial role in various fields. However, compared with natural images, UAV images are characterized by significant target scale variations, complex backgrounds, dense small targets, and clustered target distributions, which pose serious challenges to object detection tasks. To address these issues, this study proposes an improved object detection algorithm named MFRA-YOLO, which combines multi-scale feature fusion and receptive-field attention-based convolution, built upon the baseline YOLOv8n algorithm. First, Monte Carlo attention is integrated into receptive-field attention-based convolution to enhance cross-scale information interaction capability, thereby forming a novel convolutional module for downsampling operations. Second, a multi-scale selective fusion module is incorporated into the feature fusion network to enable adaptive cross-scale integration of features. When coupled with the scale sequence feature fusion module, this integration significantly enhances the detection performance for small targets. Finally, the Focaler-PIoUv2 loss function is designed to replace the CIoU in the baseline algorithm. This replacement allows the algorithm to better balance hard and easy samples and improve detection accuracy. Experimental results on the public dataset VisDrone2019 show that MFRA-YOLO achieves superior accuracy-efficiency tradeoffs compared to the baseline YOLOv8n and other YOLO variants. Compared to YOLOv8n, MFRA-YOLO improves mAP50 by 3.5% and mAP50:95 by 2.3%, respectively. These performance gains are accompanied by only modest increases in parameter count and computational cost. Notably, while maintaining performance at 143 FPS, thereby satisfying the real-time deployment requirements for UAVs. Furthermore, compared with several state-of-the-art algorithms designed for UAV scenarios, MFRA-YOLO also offers distinct advantages. To verify the generalization ability and stability of MFRA-YOLO, comparative experiments are carried out on the RSOD dataset, where our algorithm consistently demonstrates excellent detection performance. Overall, these results confirm that MFRA-YOLO not only improves the detection performance for UAV imagery substantially but also achieves an excellent balance between detection accuracy and efficiency.

Unmanned Aerial Vehicles (UAVs), commonly known as drones, in recent years continue to gain popularity in various fields, ranging from the entertainment sector to the service industry. Their application areas are expanding every day, making them increasingly versatile. They are widely used in the defense industry, contributing to the have a voice of the countries that possess them. Given this context, object detection, tracking, and other customized tasks carried out using imagery obtained from UAVs have become significantly important. However, the images obtained from UAVs are generally low resolution and quality, as they need to be captured from a safe flight distance. This situation is a disadvantage for object detection applications. To reduce this disadvantage, various Super Resolution techniques have been developed. In this paper, the focus is on the critical importance of improvements in this field, especially within the defense sector, by utilizing ESRGAN and YOLO together to enhance the resolution of images captured from UAVs. The primary objective of this study is to enhance the efficacy of object detection by simultaneously augmenting the number of detected objects and improving the accuracy of the detection process. This research presents a comparative analysis of the outcomes achieved through two distinct approaches. Firstly, object detection is executed utilizing a pre-trained YOLO-V7 model on a LR image extracted from the VisDrone Dataset. Subsequently, the same YOLO-V7 model is deployed, but object detection is carried out on the SR version of the same LR image obtained from the ESRGAN network. The findings from this investigation unequivocally demonstrate that conducting object detection on the SR image not only results in a notable increase in the quantity of detected objects but also leads to a significant enhancement in the overall accuracy of the detection process.

An effective method for small object detection in low-resolution images

Object detection on unmanned aerial vehicle (UAV) images has been a hot research topic recently. However, object detection models for general scenarios struggle with UAV images due to the challenges of detecting small targets and handling complex image backgrounds. To solve the two issues, we proposed DPH-YOLOv8, an enhanced version of YOLOv8 tailored for UAV scenarios. First, we improved the prediction head from three prediction heads to double prediction heads (DPHs), reducing the model’s parameters by 42.9% while improving the mAP for small targets. Second, we designed a tiny-path feature fusion (TP-Fusion) module to fuse richer detailed information, enabling the detector to accurately match targets of different sizes and shapes. Third, we introduced a coordinate attention (CA) module to help the model reduce the interference of complex background information and focus on detecting foreground targets. Finally, bottleneck modules were added before the prediction heads to enhance the extraction of small target features. Extensive experimental results on both the VisDrone2021 and UAVDT benchmarks demonstrated that DPH-YOLOv8 not only improved the mAP by 4.5% on VisDrone2021 and 2.2% on UAVDT but also reduced localization error by 0.53%, confusion with objects by 0.69%, and confusion with background by 0.45%. These enhancements, along with a reduction in the model’s parameters, make DPH-YOLOv8 more suitable for UAV scenarios.