Small Object Detection Research Articles

Brain tumor detection using a MobileNetV2-SSD model with modified feature pyramid network levels

Brain tumors, a subset of these malignancies, demand accurate and efficient diagnosis. Traditional methods use non-invasive medical imaging like magnetic resonance imaging (MRI) and computed tomography (CT). Although necessary for diagnosis, manual brain MRI picture segmentation is tedious and time-consuming. Using deep learning is a promising solution. This study proposes an innovative approach for brain tumor detection, focusing on meningioma tumors. Utilizing threshold-based segmentation, the MobileNetV2 architecture, a modified feature pyramid network (FPN), and single shot MultiBox detector (SSD), our model achieves precise localization and object detection. Pre-processing techniques such as grayscale conversion, histogram equalization, and Gaussian filtering enhance the MRI image quality. Morphological operations and thresholding facilitate tumor segmentation. Data augmentation and a meticulous dataset division aid in model generalization. The architecture combines MobileNetV2 as a feature extractor, SSD for object detection, and FPN for detecting small objects. Modifications, including lowering the minimum FPN level, enhance small object detection accuracy. The proposed model achieved a recall value of around 98% and a precision value of around 89%. Additionally, the proposed model achieved approximately 93% on both the dice similarity coefficient (DSC) value and the index of similarity. Based on the promising results, our research holds significant advancements for the field of medical imaging and tumor detection.

Accurate UAV Small Object Detection Based on HRFPN and EfficentVMamba.

(1) Background: Small objects in Unmanned Aerial Vehicle (UAV) images are often scattered throughout various regions of the image, such as the corners, and may be blocked by larger objects, as well as susceptible to image noise. Moreover, due to their small size, these objects occupy a limited area in the image, resulting in a scarcity of effective features for detection. (2) Methods: To address the detection of small objects in UAV imagery, we introduce a novel algorithm called High-Resolution Feature Pyramid Network Mamba-Based YOLO (HRMamba-YOLO). This algorithm leverages the strengths of a High-Resolution Network (HRNet), EfficientVMamba, and YOLOv8, integrating a Double Spatial Pyramid Pooling (Double SPP) module, an Efficient Mamba Module (EMM), and a Fusion Mamba Module (FMM) to enhance feature extraction and capture contextual information. Additionally, a new Multi-Scale Feature Fusion Network, High-Resolution Feature Pyramid Network (HRFPN), and FMM improved feature interactions and enhanced the performance of small object detection. (3) Results: For the VisDroneDET dataset, the proposed algorithm achieved a 4.4% higher Mean Average Precision (mAP) compared to YOLOv8-m. The experimental results showed that HRMamba achieved a mAP of 37.1%, surpassing YOLOv8-m by 3.8% (Dota1.5 dataset). For the UCAS_AOD dataset and the DIOR dataset, our model had a mAP 1.5% and 0.3% higher than the YOLOv8-m model, respectively. To be fair, all the models were trained without a pre-trained model. (4) Conclusions: This study not only highlights the exceptional performance and efficiency of HRMamba-YOLO in small object detection tasks but also provides innovative solutions and valuable insights for future research.

Automated productivity analysis of cable crane transportation using deep learning-based multi-object tracking

The automated monitoring of construction equipment productivity has been a crucial research topic in intelligent construction, supporting refined construction management. This paper presents a vision-based monitoring method for automated productivity analysis of cable crane transportation in dam construction. It employs a deep learning-based Multi-Object Tracking (MOT) method to track the moving trajectories of crane buckets. Based on the trajectory data, the transportation productivity of cable cranes is calculated accurately. The MOT method integrates small object detection layers, tracklet information (short trajectory fragments), and global position relationships into the YOLO-DeepSORT framework to enhance tracking performance in the construction industry. Experimental results show improvements of 95.9% in IDF1 and 92.1% in MOTA on three long videos collected from dam construction sites. These results indicate that the proposed method captures moving trajectories accurately and analyzes transportation productivity effectively.

Yolo-tla: An Efficient and Lightweight Small Object Detection Model based on YOLOv5

Yolo-tla: An Efficient and Lightweight Small Object Detection Model based on YOLOv5

Enhanced feature extraction YOLO industrial small object detection algorithm based on receptive-field attention and multi-scale features

Abstract To guarantee the stability and safety of industrial production, it is necessary to regulate the behavior of employees. However, the high background complexity, low pixel count, occlusion and fuzzy appearance can result in a high leakage rate and poor detection accuracy of small objects. Considering the above problems, this paper proposes the EFE-YOLO (Enhanced feature extraction-You Only Look Once) algorithm to improve the detection of industrial small objects. To enhance the detection of fuzzy and occluded objects, the PSRFA (PixelShuffle and Receptive-Field Attention) upsampling module is designed to preserve and reconstruct more detailed information and extract the receptive-field attention weights. Furthermore, the MSE (multi-scale and efficient) downsampling module is designed to merge global and local semantic features to alleviate the problem of false and missed detection. Subsequently, the AFAF (Adaptive Feature Adjustment and Fusion) module is designed to highlight the important features and suppress background information that is not beneficial for detection. Finally, the EIoU loss function is used to improve the convergence speed and localization accuracy. All experiments are conducted on homemade dataset. The improved YOLOv5 algorithm proposed in this paper improves mAP@0.50 (mean average precision at a threshold of 0.50) by 2.8\% compared to the YOLOv5 algorithm. The average precision and recall of small objects show an improvement of 8.1\% and 7.5\%, respectively. The detection performance is still leading in comparison with other advanced algorithms.

An improved YOLOv8 algorithm for small object detection in autonomous driving

An improved YOLOv8 algorithm for small object detection in autonomous driving

Improved 3D Object Detection Based on PointPillars

Despite the recent advancements in 3D object detection, the conventional 3D point cloud object detection algorithms have been found to exhibit limited accuracy for the detection of small objects. To address the challenge of poor detection of small-scale objects, this paper adopts the PointPillars algorithm as the baseline model and proposes a two-stage 3D target detection approach. As a cutting-edge solution, point cloud processing is performed using Transformer models. Additionally, a redefined attention mechanism is introduced to further enhance the detection capabilities of the algorithm. In the first stage, the algorithm uses PointPillars as the baseline model. The central concept of this algorithm is to transform the point cloud space into equal-sized columns. During the feature extraction stage, when the features from all cylinders are transformed into pseudo-images, the proposed algorithm incorporates attention mechanisms adapted from the Squeeze-and-Excitation (SE) method to emphasize and suppress feature information. Furthermore, the 2D convolution of the traditional backbone network is replaced by dynamic convolution. Concurrently, the addition of the attention mechanism further improves the feature representation ability of the network. In the second phase, the candidate frames generated in the first phase are refined using a Transformer-based approach. The proposed algorithm applies channel weighting in the decoder to enhance channel information, leading to improved detection accuracy and reduced false detections. The encoder constructs the initial point features from the candidate frames for encoding. Meanwhile, the decoder applies channel weighting to enhance the channel information, thereby improving the detection accuracy and reducing false detections. In the KITTI dataset, the experimental results verify the effectiveness of this method in small objects detection. Experimental results show that the proposed method significantly improves the detection capability of small objects compared with the baseline PointPillars. In concrete terms, in the moderate difficulty detection category, cars, pedestrians, and cyclists average precision (AP) values increased by 5.30%, 8.1%, and 10.6%, respectively. Moreover, the proposed method surpasses existing mainstream approaches in the cyclist category.

EL-YOLO: An efficient and lightweight low-altitude aerial objects detector for onboard applications

Existing deep learning-based low-altitude small object detectors are typically complex in model architecture and demand substantial computational resources, making deployment for real-time detection tasks on edge computing devices challenging. To address this issue, we proposed EL-YOLO, an efficient and lightweight onboard applications object detector. Initially, in order to maintain a lightweight design and improve model accuracy, we propose a novel approach called Sparsely Connected Asymptotic Feature Pyramid Network(SCAFPN). This approach aims to eliminate inter-layer interference during feature fusion, thereby enhancing the model’s performance. Furthermore, to establish long-range contextual relationships for small object scale information, we devise a Cross-Space Learning Multi-Head Self-Attention mechanism (CSL-MHSA). To assess EL-YOLO capability for onboard small object detection, we deploy it on the embedded NVIDIA Jetson Xavier Nx platform and employ NVIDIA TensorRT FP16 quantization acceleration. On the VisDrone2019-DET and AI-TOD datasets, EL-YOLO demonstrates a 12.4% and 1.3% improvement in mAP50 compared to YOLOv5s. In comparison with the state-of-the-art YOLOv8s proposed in 2023, it achieves a respective 2.8% and 10.7% increase in mAP50. Moreover, the inference speed for the Small model reaches 24 frames per second, while the Nano model achieves 35 frames per second. This method holds promise for direct integration onto unmanned aerial vehicles for aerial small object detection tasks in the future.

An Algorithm for Ship Detection in Complex Observation Scenarios Based on Mooring Buoys

Marine anchor buoys, as fixed-point profile observation platforms, are highly susceptible to the threat of ship collisions. Installing cameras on buoys can effectively monitor and collect evidence from ships. However, when using a camera to capture images, it is often affected by the continuous shaking of buoys and rainy and foggy weather, resulting in problems such as blurred images and rain and fog occlusion. To address these problems, this paper proposes an improved YOLOv8 algorithm. Firstly, the polarized self-attention (PSA) mechanism is introduced to preserve the high-resolution features of the original deep convolutional neural network and solve the problem of image spatial resolution degradation caused by shaking. Secondly, by introducing the multi-head self-attention (MHSA) mechanism in the neck network, the interference of rain and fog background is weakened, and the feature fusion ability of the network is improved. Finally, in the head network, this model combines additional small object detection heads to improve the accuracy of small object detection. Additionally, to enhance the algorithm’s adaptability to camera detection scenarios, this paper simulates scenarios, including shaking blur, rain, and foggy conditions. In the end, numerous comparative experiments on a self-made dataset show that the algorithm proposed in this study achieved 94.2% mAP50 and 73.2% mAP50:95 in various complex environments, which is superior to other advanced object detection algorithms.

Small Object Detection in Medium–Low-Resolution Remote Sensing Images Based on Degradation Reconstruction

With the continuous development of space remote sensing technology, the spatial resolution of visible remote sensing images has been continuously improved, which has promoted the progress of remote sensing target detection. However, due to the limitation of sensor lattice size, it is still challenging to obtain a large range of high-resolution (HR) remote sensing images in practical applications, which makes it difficult to carry out target monitoring in a large range of areas. At present, many object detection methods focus on the detection and positioning technology of HR remote sensing images, but there are relatively few studies on object detection methods using medium- and low-resolution (M-LR) remote sensing images. Because of its wide coverage area and short observation period, M-LR remote sensing imagery is of great significance for obtaining information quickly in space applications. However, the small amount of fine-texture information on objects in M-LR images brings great challenges to detection and recognition tasks. Therefore, we propose a small target detection method based on degradation reconstruction, named DRADNet. Different from the previous methods that use super resolution as a pre-processing step and then directly input the image into the detector, we have designed an additional degenerate reconstruction-assisted framework to effectively improve the detector’s performance in detection tasks with M-LR remote sensing images. In addition, we introduce a hybrid parallel-attention feature fusion module in the detector to achieve focused attention on target features and suppress redundant complex backgrounds, thus improving the accuracy of the model in small target localization. The experimental results are based on the widely used VEDAI dataset and Airbus-Ships dataset, and verify the effectiveness of our method in the detection of small- and medium-sized targets in M-LR remote sensing images.

Spatial Information Enhancement with Multi-Scale Feature Aggregation for Long-Range Object and Small Reflective Area Object Detection from Point Cloud

Spatial Information Enhancement with Multi-Scale Feature Aggregation for Long-Range Object and Small Reflective Area Object Detection from Point Cloud

Underwater small and occlusion object detection with feature fusion and global context decoupling head-based YOLO

Underwater small and occlusion object detection with feature fusion and global context decoupling head-based YOLO

Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios

Object detection in road scenarios is crucial for intelligent transport systems and autonomous driving, but complex traffic conditions pose significant challenges. This paper introduces Z-You Only Look Once version 8 small (Z-YOLOv8s), designed to improve both accuracy and real-time efficiency under real-world uncertainties. By incorporating Revisiting Perspective Vision Transformer (RepViT) and C2f into the YOLOv8s framework, and integrating the Large Selective Kernel Network (LSKNet), the model enhances spatial feature extraction. Additionally, the YOLOv8s backbone is optimized with Space-to-Depth Convolution (SPD-Conv) for better small object detection. The Softpool-Spatial Pyramid Pooling Fast (SoftPool-SPPF) module ensures precise characteristic information preservation. Z-YOLOv8s improves mean average precision (mAP)@0.5 on the Berkeley Deep Drive 100 K (BDD100K) and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets by 7.3 % and 3.8 %, respectively. It also achieves accuracy increases of 5.7 % and 6.5 % in Average Precision (AP)-Small, and a real-time detection speed of 78.41 frames per second (FPS) on the BDD100K. Z-YOLOv8s balances detection precision and processing speed more effectively than other detectors, as demonstrated by experimental results and comparisons.

A Novel Approach to Detect Drones Using Deep Convolutional Neural Network Architecture.

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the "vanishing gradient" problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the "dying relu" problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters.

Small Object Detection via Scale-Adaptive Label Assignment and Localization Uncertainty

Small Object Detection via Scale-Adaptive Label Assignment and Localization Uncertainty

ODCS-YOLO detection algorithm for rail surface defects based on omni-dimensional dynamic convolution and context augmentation module

Abstract To solve the problems of easy miss and false detection on rail surface defects caused by small size, dense target, and high similarity between features and background, this paper proposed an improved detection algorithm in complex background. First, the conventional convolution of YOLOv5 backbone network is replaced with omni-dimensional dynamic convolution (ODConv), which improves the feature extraction capability of the network without increasing the computational cost; second, to improve the model's performance in detecting tiny objects, a two-layer context augmentation module(CAM) is introduced into the path aggregation network(PAN) structure; finally, the traditional non-maximum suppression(NMS) algorithm is replaced by the Soft-NMS algorithm in the network post-processing to reduce the false-alarm and miss-rate. The experimental results on the Railway Track Fault Detection public dataset show that the OD-YOLO (OD stands for ODConv) and C-PAN(CAM module is introduced into PAN) structures could achieve better performance in the same type of improved algorithms; compared with the baseline algorithm YOLOv5, the ODCS-YOLO (OD stands for ODConv, C stands for CAM, and S stands for Soft-NMS) algorithm improves the precision by 12.4%, the recall by 3.6%, the map50 by 8.6% and the GFLOPs is reduced by 0.6. Compared with seven classical object detection algorithms, the ODCS-YOLO algorithm achieves the highest detection accuracy, which makes it able to meet the real-time detection requirements of rail surface defects in real working conditions. The ODCS-YOLO model provides certain technical support for the defects detection and a new method for the detection of dense small objects.

SPA: Annotating Small Object with a Single Point in Remote Sensing Images

Detecting oriented small objects is a critical task in remote sensing, but the development of high-performance deep learning-based detectors is hindered by the need for large-scale and well-annotated datasets. The high cost of creating these datasets, due to the dense and numerous distribution of small objects, significantly limits the application and development of such detectors. To address this problem, we propose a single-point-based annotation approach (SPA) based on the graph cut method. In this framework, user annotations act as the origin of positive sample points, and a similarity matrix, computed from feature maps extracted by deep learning networks, facilitates an intuitive and efficient annotation process for building graph elements. Utilizing the Maximum Flow algorithm, SPA derives positive sample regions from these points and generates oriented bounding boxes (OBBOXs). Experimental results demonstrate the effectiveness of SPA, with at least a 50% improvement in annotation efficiency. Furthermore, the intersection-over-union (IoU) metric of our OBBOX is 3.6% higher than existing methods such as the “Segment Anything Model”. When applied in training, the model annotated with SPA shows a 4.7% higher mean average precision (mAP) compared to models using traditional annotation methods. These results confirm the technical advantages and practical impact of SPA in advancing small object detection in remote sensing.

Feature-Enhanced Attention and Dual-GELAN Net (FEADG-Net) for UAV Infrared Small Object Detection in Traffic Surveillance

With the rapid development of UAV and infrared imaging technology, the cost of UAV infrared imaging technology has decreased steadily. Small target detection technology in aerial infrared images has great potential for applications in many fields, especially in the field of traffic surveillance. Because of the low contrast and relatively limited feature information in infrared images compared to visible images, the difficulty involved in small road target detection in infrared aerial images has increased. To solve this problem, this study proposes a feature-enhanced attention and dual-GELAN net (FEADG-net) model. In this network model, the reliability and effectiveness of small target feature extraction is enhanced by a backbone network combined with low-frequency enhancement and a swin transformer. The multi-scale features of the target are fused using a dual-GELAN neck structure, and a detection head with the parameters of the auto-adjusted InnerIoU is constructed to improve the detection accuracy for small infrared targets. The viability of the method was proved using the HIT-UAV dataset and IRTS-AG dataset. According to a comparative experiment, the mAP50 of FEADG-net reached more than 90 percent, which was higher than that of any previous method and it met the real-time requirements. Finally, an ablation experiment was conducted to demonstrate that all three of the modules proposed in the method contributed to the improvement in the detection accuracy. This study not only designs a new algorithm for small road object detection in infrared remote sensing images from UAVs but also provides new ideas for small target detection in remote sensing images for other fields.

An analytical model of a pulse signal reflected from a small-sized object located in the covering layer

Formulation of the problem. Existing methods and devices implementing them do not provide the required probability of correct detection and a low level of false alarms when detecting and recognizing anti-personnel and anti-tank mines in the ground. Based on this, there is currently an objective need to solve the urgent scientific task of improving the scientific and methodological apparatus for detecting and recognizing small-sized objects located in the covering layer. Purpose. Improving the scientific and methodological apparatus for detecting and recognizing subsurface targets by refining the analytical model of a pulse signal reflected from a small-sized object located in the covering layer. Results. A refined analytical model of a pulse signal reflected from a small-sized object located in the covering layer is proposed. The results of mathematical modeling and assessment of the adequacy of the obtained model are presented. Practical significance. The results obtained can be used in the synthesis of algorithms for the search, detection and recognition of small objects located in the covering layer.

Feature aggregation network for small object detection

Due to the miniature scale and limited identifiable features, small objects pose a significant challenge in detection. Improving the accuracy of small object detection is a momentous issue of concern among researchers. Feature pyramid network employs a divide-and-conquer strategy for detecting small objects in low-level networks. However, the limited semantic information in these networks results in suboptimal performance in small object detection. To address this issue, we fully utilize information from all feature levels and propose a Feature Aggregation Network (FAN). We investigate information propagation pathways in neural networks, analyze early fusion and late fusion of features, and introduce a dual top-down pathway that utilizes high-level semantic information to consistently reinforce low-level spatial information. We design a Feature-Aware Module that narrows the semantic gap and steers the network toward learning features that favor small object detection. We employ deformable convolution to accurately locate the boundaries of objects with varying shapes and sizes. FAN can function as a plug-and-play component with minimal computational overhead and be trained end-to-end alongside backbone networks. Extensive experiments are conducted on the COCOs, TinyPerson, and VisDrone datasets. The highly competitive results demonstrate that our approach exhibits robust generalization capabilities and can further improve the accuracy of small object detection.