Small Object Detection Research Articles

Improve the Performance of SAR Ship Detectors by Small Object Detection Strategies

Although advanced deep learning techniques have significantly improved SAR ship detection, accurately detecting small ships remains challenging due to their limited size and the few appearance and geometric clues available. In order to solve this problem, we propose several small object detection strategies. The backbone network uses space-to-depth convolution to replace stride and pooling. It reduces information loss during down-sampling. The neck integrates multiple layers of features globally and injects global and local information into different levels. It avoids the inherent information loss of traditional feature pyramid networks and strengthens the information fusion ability without significantly increasing latency. The proposed intersection-of-union considers the center distance and scale of small ships specifically. It reduces the sensitivity of intersection-of-union to positional deviations of small ships, which is helpful for training toward small ships. During training, the smaller the localization loss of small ships, the greater their localization loss gains are. By this, the supervision of small ships is strengthened in the loss function, which can make the losses more biased toward small ships. A series of experiments are conducted on two commonly used datasets, SSDD and SAR-Ship-Dataset. The experimental results show that the proposed method can detect small ships successfully and thus improve the overall performance of detectors.

YOLO-PBESW: A Lightweight Deep Learning Model for the Efficient Identification of Indomethacin Crystal Morphologies in Microfluidic Droplets.

Crystallization is important to the pharmaceutical, the chemical, and the materials fields, where the morphology of crystals is one of the key factors affecting the quality of crystallization. High-throughput screening based on microfluidic droplets is a potent technique to accelerate the discovery and development of new crystal morphologies with active pharmaceutical ingredients. However, massive crystal morphologies' datum needs to be identified completely and accurately, which is time-consuming and labor-intensive. Therefore, effective morphologies' detection and small-target tracking are essential for high-efficiency experiments. In this paper, a new improved algorithm YOLOv8 (YOLO-PBESW) for detecting indomethacin crystals with different morphologies is proposed. We enhanced its capability in detecting small targets through the integration of a high-resolution feature layer P2, and the adoption of a BiFPN structure. Additionally, in this paper, adding the EMA mechanism before the P2 detection head was implemented to improve network attention towards global features. Furthermore, we utilized SimSPPF to replace SPPF to mitigate computational costs and reduce inference time. Lastly, the CIoU loss function was substituted with WIoUv3 to improve detection performance. The experimental findings indicate that the enhanced YOLOv8 model attained advancements, achieving AP metrics of 93.3%, 77.6%, 80.2%, and 99.5% for crystal wire, crystal rod, crystal sheet, and jelly-like phases, respectively. The model also achieved a precision of 85.2%, a recall of 83.8%, and an F1 score of 84.5%, with a mAP of 87.6%. In terms of computational efficiency, the model's dimensions and operational efficiency are reported as 5.46 MB, and it took 12.89 ms to process each image with a speed of 77.52 FPS. Compared with state-of-the-art lightweight small object detection models such as the FFCA-YOLO series, our proposed YOLO-PBESW model achieved improvements in detecting indomethacin crystal morphologies, particularly for crystal sheets and crystal rods. The model demonstrated AP values that exceeded L-FFCA-YOLO by 7.4% for crystal sheets and 3.9% for crystal rods, while also delivering a superior F1-score. Furthermore, YOLO-PBESW maintained a lower computational complexity, with parameters of only 11.8 GFLOPs and 2.65 M, and achieved a higher FPS. These outcomes collectively demonstrate that our method achieved a balance between precision and computational speed.

Urban traffic tiny object detection via attention and multi-scale feature driven in UAV-vision

The unmanned aerial vehicle (UAV) city patrol is of great significance in ensuring the safety of residents’ lives and properties, as well as maintaining the normal operation of the city. However, the detection of UAV images faces challenges such as numerous small-scale objects, complex backgrounds, and high requirements for detection speed. In response to these issues, we introduce a Real-time Small Object Detection network in UAV-vision (RTS-Net), tailored for UAV patrols. Initially, we introduce a multiscale feature fusion module (MFFM) designed to augment the expressiveness of features across scales, thereby enhancing the detection of smaller objects. Subsequently, leveraging attention mechanisms, we present the coordinated attention detection module (CADM), which bolsters the detection model’s ability to accurately segregate objects from the background in expansive, complex scenarios. Lastly, a lightweight real-time feature extraction module (RFEM) is crafted to diminish model computational complexity and boost inference speed. On the UAV road patrol image dataset we constructed, our proposed method attains a detection accuracy of 89.9%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} mAP, breaking previous records. It surpasses all prevailing detection methods, particularly for small-scale objects. Simultaneously, it achieves an inference speed of 163.9 FPS. The experimental results show that RTS-Net can satisfy the accurate and efficient detection of ground objects by various different UAV platforms in different complex scenarios.

HSP-YOLOv8: UAV Aerial Photography Small Target Detection Algorithm

To address the larger numbers of small objects and the issues of occlusion and clustering in UAV aerial photography, which can lead to false positives and missed detections, we propose an improved small object detection algorithm for UAV aerial scenarios called YOLOv8 with tiny prediction head and Space-to-Depth Convolution (HSP-YOLOv8). Firstly, a tiny prediction head specifically for small targets is added to provide higher-resolution feature mapping, enabling better predictions. Secondly, we designed the Space-to-Depth Convolution (SPD-Conv) module to mitigate the loss of small target feature information and enhance the robustness of feature information. Lastly, soft non-maximum suppression (Soft-NMS) is used in the post-processing stage to improve accuracy by significantly reducing false positives in the detection results. In experiments on the Visdrone2019 dataset, the improved algorithm increased the detection precision mAP0.5 and mAP0.5:0.95 values by 11% and 9.8%, respectively, compared to the baseline model YOLOv8s.

Small Object Detection with lightweight PointNet Based on Attention Mechanisms

Abstract In response to the issue of subpar small object detection outcomes, the improved 3D object detection method for Point Net is proposed. First, multi-scale fusion method is added to the channel attention mechanism into the feature extraction stage of Point Net; then, the loss function is adjusted to optimize the backbone network and reduce the number of model parameters while improving the accuracy. The experimental results show that in the dataset, the proposed method has higher detection accuracy, the improved algorithm average accuracy improves 3.9%, the model size decreases 20%, effectively improves the detection effect of small objects, and realizes the lightweight of the network.

Improved Pedestrian Vehicle Detection for Small Objects Based on Attention Mechanism

Abstract This study aims to solve the low detection accuracy and susceptibility to false detection and omission in pedestrian and vehicle detection by proposing an improved YOLOv5s algorithm. Firstly, a small target detection module is added to better acquire and determine the information of pedestrians from long-range vehicles. Secondly, the multi-scale channel attention CBAM attention module is added, and the dual attention mechanism is not only flexible and convenient, but also improves the computational efficiency. Finally, the MPDIoU loss function based on minimum point distance is introduced to replace the original GIoU loss function, and this change not only enhances the regression accuracy of the model. At the same time, the convergence speed of the model is accelerated. KITTI data set was used for experiments, and the experimental results showed that the average accuracy of the model trained by the improved YOLOv5s algorithm on the data set reached 84.9%, which was 3.7% higher than that of the original YOLOv5s algorithm. It is verified that the model is suitable for high accuracy of pedestrian and vehicle recognition in complex environments, and has high value for promotion.

Toward High-Accuracy and Real-Time Two-Stage Small Object Detection on FPGA

Toward High-Accuracy and Real-Time Two-Stage Small Object Detection on FPGA

Assessment of Small Object Detection Algorithm Based on Improved YOLOv5s

Assessment of Small Object Detection Algorithm Based on Improved YOLOv5s

Dense Small Object Detection Based on an Improved YOLOv7 Model

Dense Small Object Detection Based on an Improved YOLOv7 Model

A Study of Classroom Behavior Recognition Incorporating Super-Resolution and Target Detection.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors, and complexity of character interactions. Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy. To address the dataset complexity and multi-targeting problems, feature extraction is optimized, and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of the YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students-raising their hands, reading, writing, playing on their cell phones, looking down, and leaning on the table-in high-definition images. And the accuracy and robustness of this network is verified. Compared with small-object detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network demonstrates good detection performance on low-resolution small objects, complex datasets with numerous targets, occlusion, and overlapping students.

Lightweight Single-Stage Ship Object Detection Algorithm for Unmanned Surface Vessels Based on Improved YOLOv5.

Object detection is applied extensively in various domains, including industrial manufacturing, road traffic management, warehousing and logistics, and healthcare. In ship object detection tasks, detection networks are frequently deployed on devices with limited computational resources, e.g., unmanned surface vessels. This creates a need to balance accuracy with a low parameter count and low computational load. This paper proposes an improved object detection network based on YOLOv5. To reduce the model parameter count and computational load, we utilize an enhanced ShuffleNetV2 network as the backbone. In addition, a split-DLKA module is devised and implemented in the small object detection layer to improve detection accuracy. Finally, we introduce the WIOUv3 loss function to minimize the impact of low-quality samples on the model. Experiments conducted on the SeaShips dataset demonstrate that the proposed method reduces parameters by 71% and computational load by 58% compared to YOLOv5s. In addition, the proposed method increases the mAP@0.5 and mAP@0.5:0.95 values by 3.9% and 3.3%, respectively. Thus, the proposed method exhibits excellent performance in both real-time processing and accuracy.

An efficient model for small object detection in the maritime environment

Environmental perception is crucial for autonomous ships realizing autonomous navigation, in particular, the high-precision and low-latency detection of small objects on the sea surface is a key and challenging issue. To address this problem, this paper presents a model that improves the detection accuracy and delivers excellent real-time performance for autonomous ship navigation. The backbone of the proposed model enhances the modelling capabilities by expanding deformable convolution and introducing the self-designed attention mechanism. Additionally, an enhanced feature fusion structure is designed by the pixel shuffle based on super-resolution reconstruction to keep the integrity of feature information for small objects. This paper also presents an optimized model quantization strategy that alleviates the problem of low model efficiency caused by the limited resources onboard the ship. Compared to the earlier model, the present one has increased the mean average precision on the Rizhao Zhuimeng-3# maritime optical dataset by 4.5 % and by 21 % for small object detection. Furthermore, the real-time detection for high-resolution images can now reach a speed of 67 frames/s. Moreover, the present model outperforms existing methods concerning accuracy when the frames/s are similar. The results indicate that the proposed model can be potentially applied to autonomous ships.

Drone-DETR: Efficient Small Object Detection for Remote Sensing Image Using Enhanced RT-DETR Model.

Performing low-latency, high-precision object detection on unmanned aerial vehicles (UAVs) equipped with vision sensors holds significant importance. However, the current limitations of embedded UAV devices present challenges in balancing accuracy and speed, particularly in the analysis of high-precision remote sensing images. This challenge is particularly pronounced in scenarios involving numerous small objects, intricate backgrounds, and occluded overlaps. To address these issues, we introduce the Drone-DETR model, which is based on RT-DETR. To overcome the difficulties associated with detecting small objects and reducing redundant computations arising from complex backgrounds in ultra-wide-angle images, we propose the Effective Small Object Detection Network (ESDNet). This network preserves detailed information about small objects, reduces redundant computations, and adopts a lightweight architecture. Furthermore, we introduce the Enhanced Dual-Path Feature Fusion Attention Module (EDF-FAM) within the neck network. This module is specifically designed to enhance the network's ability to handle multi-scale objects. We employ a dynamic competitive learning strategy to enhance the model's capability to efficiently fuse multi-scale features. Additionally, we incorporate the P2 shallow feature layer from the ESDNet into the neck network to enhance the model's ability to fuse small-object features, thereby enhancing the accuracy of small object detection. Experimental results indicate that the Drone-DETR model achieves an mAP50 of 53.9% with only 28.7 million parameters on the VisDrone2019 dataset, representing an 8.1% enhancement over RT-DETR-R18.

GLU-YOLOv8: An Improved Pest and Disease Target Detection Algorithm Based on YOLOv8

In the contemporary context, pest detection is progressively moving toward automation and intelligence. However, current pest detection algorithms still face challenges, such as lower accuracy and slower operation speed in detecting small objects. To address this issue, this study presents a crop pest target detection algorithm, GLU-YOLOv8, designed for complex scenes based on an enhanced version of You Only Look Once version 8 (YOLOv8). The algorithm introduces the SCYLLA-IOU (SIOU) loss function, which enhances the model generalization to various pest sizes and shapes by ensuring smoothness and reducing oscillations during training. Additionally, the algorithm incorporates the Convolutional Block Attention Module (CBAM) and Locality Sensitive Kernel (LSK) attention mechanisms to boost the pest target features. A novel Gated Linear Unit CONV (GLU-CONV) is also introduced to enhance the model’s perceptual and generalization capabilities while maintaining performance. Furthermore, GLU-YOLOv8 includes a small-object detection layer with a feature map size of 160 × 160 to extract more features of small-target pests, thereby improving detection accuracy and enabling more precise localization and identification of small-target pests. The study conducted a comparative analysis between the GLU-YOLOv8 model and other models, such as YOLOv8, Faster RCNN, and RetinaNet, to evaluate detection accuracy and precision. In the Scolytidae forestry pest dataset, GLU-YOLOv8 demonstrated an improvement of 8.2% in mAP@0.50 for small-target detection compared to the YOLOv8 model, with a resulting mAP@0.50 score of 97.4%. Specifically, on the IP102 dataset, GLU-YOLOv8 outperforms the YOLOv8 model with a 7.1% increase in mAP@0.50 and a 5% increase in mAP@0.50:0.95, reaching 58.7% for mAP@0.50. These findings highlight the significant enhancement in the accuracy and recognition rate of small-target detection achieved by GLU-YOLOv8, along with its efficient operational performance. This research provides valuable insights for optimizing small-target detection models for various pests and diseases.

A Small-Object-Detection Algorithm Based on LiDAR Point-Cloud Clustering for Autonomous Vehicles.

3D object-detection based on LiDAR point clouds can help driverless vehicles detect obstacles. However, the existing point-cloud-based object-detection methods are generally ineffective in detecting small objects such as pedestrians and cyclists. Therefore, a small-object-detection algorithm based on clustering is proposed. Firstly, a new segmented ground-point clouds segmentation algorithm is proposed, which filters out the object point clouds according to the heuristic rules and realizes the ground segmentation by multi-region plane-fitting. Then, the small-object point cloud is clustered using an improved DBSCAN clustering algorithm. The K-means++ algorithm for pre-clustering is used, the neighborhood radius is adaptively adjusted according to the distance, and the core point search method of the original algorithm is improved. Finally, the detection of small objects is completed using the directional wraparound box model. After extensive experiments, it was shown that the precision and recall of our proposed ground-segmentation algorithm reached 91.86% and 92.70%, respectively, and the improved DBSCAN clustering algorithm improved the recall of pedestrians and cyclists by 15.89% and 9.50%, respectively. In addition, visualization experiments confirmed that our proposed small-object-detection algorithm based on the point-cloud clustering method can realize the accurate detection of small objects.

Transformer-CNN for small image object detection

Object recognition in computer vision technology has been a popular research field in recent years. Although the detection success rate of regular objects has achieved impressive results, small object detection (SOD) is still a challenging issue. In the Microsoft Common Objects in Context (MS COCO) public dataset, the detection rate of small objects is typically half that of regular-sized objects. The main reason is that small objects are often affected by multi-layer convolution and pooling, leading to insufficient details to distinguish them from the background or similar objects, resulting in poor recognition rates or even no results. This paper presents a network architecture, Transformer-CNN, that combines a self-attention mechanism-based transformer and a convolutional neural network (CNN) to improve the recognition rate of SOD. It captures global information through a transformer and uses the translation invariance and translation equivalence of CNN to maximize the retention of global and local features while improving the reliability and robustness of SOD. Our experiments show that the proposed model improves the small object recognition rate by 2∼5 % than the general transformer architectures.

YOLOv8s-NE: Enhancing Object Detection of Small Objects in Nursery Environments Based on Improved YOLOv8

The primary objective of this research investigation is to examine object detection within the specific environment of a nursery. The nursery environment presents a complex scene with a multitude of objects, varying in size and background. To simulate real-world conditions, we gathered data from a nursery. Our study is centered around the detection of small objects, particularly in nursery settings where objects that include stationery, toys, and small accessories are commonly present. These objects are of significant importance in facilitating cognition of the activities and interactions taking place within the confines of the room. Due to their small size and the possibility of occlusion by other objects or children, precisely detecting these objects is regrettably fraught with inherent challenges. This study introduces YOLOv8s-NE in an effort to enhance the detection of small objects found in the nursery. We improve the standard YOLOv8 by incorporating an extra detection head to effectively for small objects. We replace the C2f module with C2f_DCN to further improve the model’s ability to detect objects of varying sizes that can be deformed or occluded within the image. Furthermore, we introduce NAM attention to focus on the important features and ignore less informative ones, thereby improving the accuracy of our proposed model. We used the five-fold cross-validation approach to split the dataset in order to evaluate the performance of YOLOv8s-NE, thereby facilitating a more comprehensive model evaluation. Our model achieves 34.1% of APs, 45.1% of mAP50:90, and 76.7% of mAP50 detection accuracy at 37.55 FPS on the nursery dataset. In terms of APs, mAP50:90, and mAP50 metrics, our proposed YOLOv8s-NE model outperforms the standard YOLOv8s model, with improvements of 4.6%, 4.7%, and 3.9%, respectively. We apply our proposed YOLOv8s-NE model as a safety system by developing an algorithm to detect objects on top of cabinets that could be potentially risky to children.

Small object detection based on YOLOv8 in UAV perspective

Small object detection based on YOLOv8 in UAV perspective

Camera-Radar Fusion with Radar Channel Extension and Dual-CBAM-FPN for Object Detection.

When it comes to road environment perception, millimeter-wave radar with a camera facilitates more reliable detection than a single sensor. However, the limited utilization of radar features and insufficient extraction of important features remain pertinent issues, especially with regard to the detection of small and occluded objects. To address these concerns, we propose a camera-radar fusion with radar channel extension and a dual-CBAM-FPN (CRFRD), which incorporates a radar channel extension (RCE) module and a dual-CBAM-FPN (DCF) module into the camera-radar fusion net (CRF-Net). In the RCE module, we design an azimuth-weighted RCS parameter and extend three radar channels, which leverage the secondary redundant information to achieve richer feature representation. In the DCF module, we present the dual-CBAM-FPN, which enables the model to focus on important features by inserting CBAM at the input and the fusion process of FPN simultaneously. Comparative experiments conducted on the NuScenes dataset and real data demonstrate the superior performance of the CRFRD compared to CRF-Net, as its weighted mean average precision (wmAP) increases from 43.89% to 45.03%. Furthermore, ablation studies verify the indispensability of the RCE and DCF modules and the effectiveness of azimuth-weighted RCS.

An Efficient and Accurate Quality Inspection Model for Steel Scraps Based on Dense Small-Target Detection

Scrap steel serves as the primary alternative raw material to iron ore, exerting a significant impact on production costs for steel enterprises. With the annual growth in scrap resources, concerns regarding traditional manual inspection methods, including issues of fairness and safety, gain increasing prominence. Enhancing scrap inspection processes through digital technology is imperative. In response to these concerns, we developed CNIL-Net, a scrap-quality inspection network model based on object detection, and trained and validated it using images obtained during the scrap inspection process. Initially, we deployed a multi-camera integrated system at a steel plant for acquiring scrap images of diverse types, which were subsequently annotated and employed for constructing an enhanced scrap dataset. Then, we enhanced the YOLOv5 model to improve the detection of small-target scraps in inspection scenarios. This was achieved by adding a small-object detection layer (P2) and streamlining the model through the removal of detection layer P5, resulting in the development of a novel three-layer detection network structure termed the Improved Layer (IL) model. A Coordinate Attention mechanism was incorporated into the network to dynamically learn feature weights from various positions, thereby improving the discernment of scrap features. Substituting the traditional non-maximum suppression algorithm (NMS) with Soft-NMS enhanced detection accuracy in dense and overlapping scrap scenarios, thereby mitigating instances of missed detections. Finally, the model underwent training and validation utilizing the augmented dataset of scraps. Throughout this phase, assessments encompassed metrics like mAP, number of network layers, parameters, and inference duration. Experimental findings illustrate that the developed CNIL-Net scrap-quality inspection network model boosted the average precision across all categories from 88.8% to 96.5%. Compared to manual inspection, it demonstrates notable advantages in accuracy and detection speed, rendering it well suited for real-world deployment and addressing issues in scrap inspection like real-time processing and fairness.