Small Object Detection Research Articles

SOD-YOLO: A High-Precision Detection of Small Targets on High-Voltage Transmission Lines

Wire clamps and vibration-proof hammers are key components of high-voltage transmission lines. The wire clips and vibration-proof hammers detected in Unmanned Aerial Vehicle (UAV) power inspections suffer from small size, scarce edge information, and low recognition accuracy. To address these problems, this paper proposes a small object detection (SOD) model based on the YOLOv8n, called SOD-YOLO. Firstly, an extra small target detection layer was added to YOLOv8, which significantly improves the small target detection accuracy. In addition, in order to enhance the detection speed of the model, the RepVGG/RepConv ShuffleNet (RCS) and a OneShot Aggregation of the RCS (RCSOSA) module were introduced to replace the C2f module in the model backbone and neck shallow networks. Finally, to address the excessive focus on low-quality sample bounding boxes during model training, we introduced Wise-CIoU loss instead of CIoU loss, which improved the detection accuracy of the model. The experimental results indicate that SOD-YOLO achieved a mean average precision of 90.1%, surpassing the YOLOv8n baseline model by 7.5% while maintaining a model parameter count of 3.4 M; the inference speed reached 88.7 frames/s, which meets the requirement of real-time recognition.

A Small-Object Detection Based Scheme for Multiplexed Frequency Hopping Recognition in Complex Electromagnetic Interference

A Small-Object Detection Based Scheme for Multiplexed Frequency Hopping Recognition in Complex Electromagnetic Interference

MBAN: multi-branch attention network for small object detection.

Recent years small object detection has seen remarkable advancement. However, small objects are difficult to accurately detect in complex scenes due to their low resolution. The downsampling operation inevitably leads to the loss of information for small objects. In order to solve these issues, this article proposes a novel Multi-branch Attention Network (MBAN) to improve the detection performance of small objects. Firstly, an innovative Multi-branch Attention Module (MBAM) is proposed, which consists of two parts, i.e. Multi-branch structure consisting of convolution and maxpooling, and the parameter-free SimAM attention mechanism. By combining these two parts, the number of network parameters is reduced, the information loss of small objects is reduced, and the representation of small object features is enhanced. Furthermore, to systematically solve the problem of small object localization, a pre-processing method called Adaptive Clustering Relocation (ACR) is proposed. To validate our network, we conducted extensive experiments on two benchmark datasets, i.e. NWPU VHR-10 and PASCAL VOC. The findings from the experiment demonstrates the significant performance gains of MBAN over most existing algorithms, the mAP of MBAN achieved 96.55% and 84.96% on NWPU VHR-10 and PASCAL VOC datasets, respectively, which proves that MBAN has significant performance in small object detection.

Enhancement of Small Ship Detection Using Polarimetric Combination from Sentinel−1 Imagery

Speckle noise and the spatial resolution of the Sentinel−1 Synthetic Aperture Radar (SAR) image can cause significant difficulties in the detection of small objects, such as small ships. Therefore, in this study, the Polarimetric Combination-based Ship Detection (PCSD) approach is proposed for enhancing small ship detection performance, which combines three different characteristics of polarization: newVH, enhanced VH, and enhanced VV. Employing the Radar Cross Section (RCS) value in three stages, the newVH was utilized to detect Automatic Identification System (AIS) -ships and small ships. In the first step, the adaptive threshold (AT) method was applied to newVH with a high RCS condition (>−10.36 (dB)) for detecting AIS-ships. Secondly, the first small ship target was detected with the maximum suppression of false alarms by using the AT with a middle RCS condition (>−16.98 (dB)). In the third step, a candidate group was identified by applying a condition to the RCS values (>−23.01 (dB)), where both small ships and speckle noise were present simultaneously. Subsequently, the enhanced VH and VV polarizations were employed, and an optimized threshold value was selected for each polarization to detect the second small ship while eliminating noise pixels. Finally, the results were evaluated using the AIS and small fishing vessel tracking system (V-Pass) based on the detected ship positions and ship lengths. The average matching results from 26 scenes in 2022 indicated a matching rate of over 86.67% for AIS-ships. Regarding small ships, the detection performance of PCSD was 42.27%, which was over twice as accurate as the previous Constant False Alarm Rate (CFAR) ship detection model. As a result, PCSD enhanced the detection rate of small ships while maintaining the capacity for detecting AIS-equipped ships.

ISOD: improved small object detection based on extended scale feature pyramid network

ISOD: improved small object detection based on extended scale feature pyramid network

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.

Small object detection algorithm incorporating swin transformer for tea buds.

Accurate identification of small tea buds is a key technology for tea harvesting robots, which directly affects tea quality and yield. However, due to the complexity of the tea plantation environment and the diversity of tea buds, accurate identification remains an enormous challenge. Current methods based on traditional image processing and machine learning fail to effectively extract subtle features and morphology of small tea buds, resulting in low accuracy and robustness. To achieve accurate identification, this paper proposes a small object detection algorithm called STF-YOLO (Small Target Detection with Swin Transformer and Focused YOLO), which integrates the Swin Transformer module and the YOLOv8 network to improve the detection ability of small objects. The Swin Transformer module extracts visual features based on a self-attention mechanism, which captures global and local context information of small objects to enhance feature representation. The YOLOv8 network is an object detector based on deep convolutional neural networks, offering high speed and precision. Based on the YOLOv8 network, modules including Focus and Depthwise Convolution are introduced to reduce computation and parameters, increase receptive field and feature channels, and improve feature fusion and transmission. Additionally, the Wise Intersection over Union loss is utilized to optimize the network. Experiments conducted on a self-created dataset of tea buds demonstrate that the STF-YOLO model achieves outstanding results, with an accuracy of 91.5% and a mean Average Precision of 89.4%. These results are significantly better than other detectors. Results show that, compared to mainstream algorithms (YOLOv8, YOLOv7, YOLOv5, and YOLOx), the model improves accuracy and F1 score by 5-20.22 percentage points and 0.03-0.13, respectively, proving its effectiveness in enhancing small object detection performance. This research provides technical means for the accurate identification of small tea buds in complex environments and offers insights into small object detection. Future research can further optimize model structures and parameters for more scenarios and tasks, as well as explore data augmentation and model fusion methods to improve generalization ability and robustness.

DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection

The image-based backbone (feature extraction) networks downsample the feature maps not only to increase the receptive field but also to efficiently detect objects of various scales. The existing feature extraction networks in LiDAR-based 3D object detection tasks follow the feature map downsampling similar to image-based feature extraction networks to increase the receptive field. But, such downsampling of LiDAR feature maps in large-scale autonomous driving scenarios hinder the detection of small size objects, such as pedestrians. To solve this issue we design an architecture that not only maintains the same scale of the feature maps but also the receptive field in the feature extraction network to aid for efficient detection of small size objects. We resort to attention mechanism to build sufficient receptive field and we propose a Deep and Light-weight Voxel Transformer (DeLiVoTr) network with voxel intra- and inter-region transformer modules to extract voxel local and global features respectively. We introduce DeLiVoTr block that uses transformations with expand and reduce strategy to vary the width and depth of the network efficiently. This facilitates to learn wider and deeper voxel representations and enables to use not only smaller dimension for attention mechanism but also a light-weight feed-forward network, facilitating the reduction of parameters and operations. In addition to model scaling, we employ layer-level scaling of DeLiVoTr encoder layers for efficient parameter allocation in each encoder layer instead of fixed number of parameters as in existing approaches. Leveraging layer-level depth and width scaling we formulate three variants of DeLiVoTr network. We conduct extensive experiments and analysis on large-scale Waymo and KITTI datasets. Our network surpasses state-of-the-art methods for detection of small objects (pedestrians) with an inference speed of 20.5 FPS.

DCEF2-YOLO: Aerial Detection YOLO with Deformable Convolution–Efficient Feature Fusion for Small Target Detection

Deep learning technology for real-time small object detection in aerial images can be used in various industrial environments such as real-time traffic surveillance and military reconnaissance. However, detecting small objects with few pixels and low resolution remains a challenging problem that requires performance improvement. To improve the performance of small object detection, we propose DCEF 2-YOLO. Our proposed method enables efficient real-time small object detection by using a deformable convolution (DFConv) module and an efficient feature fusion structure to maximize the use of the internal feature information of objects. DFConv preserves small object information by preventing the mixing of object information with the background. The optimized feature fusion structure produces high-quality feature maps for efficient real-time small object detection while maximizing the use of limited information. Additionally, modifying the input data processing stage and reducing the detection layer to suit small object detection also contributes to performance improvement. When compared to the performance of the latest YOLO-based models (such as DCN-YOLO and YOLOv7), DCEF 2-YOLO outperforms them, with a mAP of +6.1% on the DOTA-v1.0 test set, +0.3% on the NWPU VHR-10 test set, and +1.5% on the VEDAI512 test set. Furthermore, it has a fast processing speed of 120.48 FPS with an RTX3090 for 512 × 512 images, making it suitable for real-time small object detection tasks.

A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7

Due to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones. We then select the widely used YOLOv7 algorithm as the foundation and conduct a comprehensive analysis of its limitations, proposing a targeted solution. In order to enhance the network’s ability to extract features from small objects, we introduce non-strided convolution modules and integrate modules that utilize attention mechanism principles into the baseline network. Additionally, we improve the semantic information expression for small targets by optimizing the feature fusion process in the network. During training, we adopt the latest Lion optimizer and MPDIoU loss to further boost the overall performance of the network. The improved network achieves impressive results, with mAP50 scores of 56.8% and 94.6% on the VisDrone2019 and NWPU VHR-10 datasets, respectively, particularly in detecting small objects.

Research on Improved Algorithm for Small Object Detection in Intelligent Surveillance Video based on YOLOv7

In order to address the issue of small objects being difficult to detect effectively in intelligent surveillance videos, this study proposes an improved scheme for the YOLOv7-tiny algorithm. This scheme integrates the Convolutional Block Attention Module (CBAM) into YOLOv7-tiny, effectively enhancing the model's feature extraction and small object detection capabilities in complex backgrounds, thereby improving the overall detection precision. Experimental evaluations indicate that the improved algorithm shows enhanced performance in specific small object detection tasks, achieving an accuracy of 85.6%, a recall rate of 85.2%, and a mean average precision (mAP) of 90.2%. These results demonstrate the effectiveness and practical value of the improved scheme in enhancing the performance of YOLOv7-tiny in small object detection tasks.

Post-secondary classroom teaching quality evaluation using small object detection model

The classroom video has a complex background and dense targets. This study utilizes small object detection technology to analyze and evaluate students’ behavior in the classroom, aiming to objectively and accurately assess classroom quality. Firstly, noise is removed from the images using a median filter, and the contrast of the images is enhanced through histogram equalization. Label smoothing is applied to reduce the model’s sensitivity to labels. Then, features are extracted from the preprocessed images, and multi-scale feature fusion is employed to enhance semantic expression across multiple scales. Finally, a combination loss function is utilized to improve the accuracy of multi-object recognition tasks. Real-time detection of students’ behaviors in the classroom is performed based on the small object detection model. The average head-up rate in the classroom is calculated, and the quality of teaching is evaluated and analyzed. This study explores the methods and applications of small object detection technology based on actual teaching cases and analyzes and evaluates its effectiveness in evaluating the quality of higher education classroom teaching. The research findings demonstrate the significant importance of small object detection technology in effectively evaluating students’ learning conditions in higher education classrooms, leading to improved teaching quality and personalized education.

Deep learning‐based space debris detection for space situational awareness: A feasibility study applied to the radar processing

AbstractThe increasing number of space objects (SO), debris, and constellation of satellites in Low Earth Orbit poses a significant threat to the sustainability and safety of space operations, which must be carefully and efficiently addressed to avoid mutual collisions. The space situational awareness is currently addressed by an ensemble of radar and radio‐telescopes that detect and track SO. However, a large part of space debris is composed of very small and tiny metallic objects, very difficult to detect. The authors demonstrate the benefits of using deep learning (DL) architectures for small space object detection by radar observations. TIRA radio telescope has been simulated to generate range‐Doppler maps, then used as inputs for object detection exploiting You‐Only‐Look‐Once (YOLO) frameworks. The results demonstrate that the object detection by using YOLO algorithms outperform conventional target detection approaches, thus indicating the potential benefits of using DL techniques for space surveillance applications.

Enhance or Leave It: An Investigation of the Image Enhancement in Small Object Detection in Aerial Images

Recent years of object detection (OD), a fundamental task in computer vision, have witnessed the rise of numerous practical applications of this sub-field such as face detection, self-driving, security, and more. Although existing deep learning models show significant achievement in object detection, they are usually tested on datasets having mostly clean images. Thus, their performance levels were not measured on degraded images. In addition, images and videos in real-world scenarios often involve several natural artifacts such as noise, haze, rain, dust, and motion blur due to several factors such as insufficient light, atmospheric scattering, and faults in image sensors. This image acquisition-related problem becomes more severe when it comes to detecting small objects in aerial images. In this study, we investigate the small object identification performance of several state-of-the-art object detection models (Yolo 6/7/8) under three conditions (noisy, motion blurred, and rainy). Through this inspection, we evaluate the contribution of an image enhancement scheme so-called MPRNet. For this aim, we trained three OD algorithms with the original clean images of the VisDrone dataset. Followingly, we measured the detection performance of saved YOLO models against (1) clean, (2) degraded, and (3) enhanced counterparts. According to the results, MPRNet-based image enhancement promisingly contributes to the detection performance and YOLO8 outperforms its predecessors. We believe that this work presents useful findings for researchers studying aerial image-based vision tasks, especially under extreme weather and image acquisition conditions

Improving small object detection via context-aware and feature-enhanced plug-and-play modules

Improving small object detection via context-aware and feature-enhanced plug-and-play modules

Underwater object detection method based on learnable query recall mechanism and lightweight adapter.

With the rapid development of ocean observation technology, underwater object detection has begun to occupy an essential position in the fields of aquaculture, environmental monitoring, marine science, etc. However, due to the problems unique to underwater images such as severe noise, blurred objects, and multi-scale, deep learning-based target detection algorithms lack sufficient capabilities to cope with these challenges. To address these issues, we improve DETR to make it well suited for underwater scenarios. First, a simple and effective learnable query recall mechanism is proposed to mitigate the effect of noise and can significantly improve the detection performance of the object. Second, for underwater small and irregular object detection, a lightweight adapter is designed to provide multi-scale features for the encoding and decoding stages. Third, the regression mechanism of the bounding box is optimized using the combination loss of smooth L1 and CIoU. Finally, we validate the designed network against other state-of-the-art methods on the RUOD dataset. The experimental results show that the proposed method is effective.

PVswin-YOLOv8s: UAV-Based Pedestrian and Vehicle Detection for Traffic Management in Smart Cities Using Improved YOLOv8

In smart cities, effective traffic congestion management hinges on adept pedestrian and vehicle detection. Unmanned Aerial Vehicles (UAVs) offer a solution with mobility, cost-effectiveness, and a wide field of view, and yet, optimizing recognition models is crucial to surmounting challenges posed by small and occluded objects. To address these issues, we utilize the YOLOv8s model and a Swin Transformer block and introduce the PVswin-YOLOv8s model for pedestrian and vehicle detection based on UAVs. Firstly, the backbone network of YOLOv8s incorporates the Swin Transformer model for global feature extraction for small object detection. Secondly, to address the challenge of missed detections, we opt to integrate the CBAM into the neck of the YOLOv8. Both the channel and the spatial attention modules are used in this addition because of how well they extract feature information flow across the network. Finally, we employ Soft-NMS to improve the accuracy of pedestrian and vehicle detection in occlusion situations. Soft-NMS increases performance and manages overlapped boundary boxes well. The proposed network reduced the fraction of small objects overlooked and enhanced model detection performance. Performance comparisons with different YOLO versions ( for example YOLOv3 extremely small, YOLOv5, YOLOv6, and YOLOv7), YOLOv8 variants (YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l), and classical object detectors (Faster-RCNN, Cascade R-CNN, RetinaNet, and CenterNet) were used to validate the superiority of the proposed PVswin-YOLOv8s model. The efficiency of the PVswin-YOLOv8s model was confirmed by the experimental findings, which showed a 4.8% increase in average detection accuracy (mAP) compared to YOLOv8s on the VisDrone2019 dataset.

YOLOv5 based object detection in reel package X-ray images of semiconductor component

The industrial manufacturing landscape is currently shifting toward the incorporation of technologies based on artificial intelligence (AI). This transition includes an evolution toward smart factory infrastructure, with a specific focus on AI-driven strategies in production and quality control. Specifically, AI-empowered computer vision has emerged as a potent tool that offers a departure from extant rule-based systems and provides enhanced operational efficiency at manufacturing sites. As the manufacturing sector embraces this new paradigm, the impetus to integrate AI-integrated manufacturing is evident. Within this framework, one salient application is AI deep learning–facilitated small-object detection, which is poised to have extensive implications for diverse industrial applications. This study describes an optimized iteration of the YOLOv5 model, which is known for its efficacious single-stage object-detection abilities underpinned by PyTorch. Our proposed “improved model” incorporates an additional layer to the model's canonical three-layer architecture, augmenting accuracy and computational expediency. Empirical evaluations using semiconductor X-ray imagery reveal the model's superior performance metrics. Given the intricate specifications of surface-mount technologies, which are characterized by a plethora of micro-scale components, our model makes a seminal contribution to real-time, in-line production assessments. Quantitative analyses show that our improved model attained a mean average precision of 0.622, surpassing YOLOv5's 0.349, and a marked accuracy enhancement of 0.865, which is a significant improvement on YOLOv5's 0.552. These findings bolster the model's robustness and potential applicability, particularly in discerning objects at reel granularities during real-time inferencing.

Improved small-object detection using YOLOv8: A comparative study

In the last decade or so, deep neural networks have evolved at a rapid pace, where computer vision has been constantly refreshing its best performance and has been integrated into our lives. In the field of target detection, YOLO model is a popular real-time target detection algorithm model that is fast, efficient, and accurate. This research aims to optimize the latest YOLOv8 model to improve its detection of small objects and compare it with another different version of YOLO models. To achieve this goal, we used the classical deep learning algorithm YOLOv8 as a benchmark and made several improvements and optimizations. We optimized the definition of the detection head, narrowed its perceptual field, and increased its number, allowing the model to better focus on the detailed information of small objects. We compared the optimized YOLOv8 model with other classical YOLO models, including YOLOv3 and YOLOv5n. The experimental results show that our optimized model improves small object detection with higher accuracy. This research provides an effective solution for small object detection with good application prospects. With the continuous development and improvement of the technology, we believe that the YOLO algorithm will continue to play an essential role in object detection and provide a reliable solution for various real-time applications.

Small Sample Object Detection Based on Improved YOLOv5

Small Sample Object Detection Based on Improved YOLOv5