Multi-scale Target Detection Research Articles

LSR-Det: A Lightweight Detector for Ship Detection in SAR Images Based on Oriented Bounding Box

Convolutional neural networks (CNNs) have significantly advanced in recent years in detecting arbitrary-oriented ships in synthetic aperture radar (SAR) images. However, challenges remain with multi-scale target detection and deployment on satellite-based platforms due to the extensive model parameters and high computational complexity. To address these issues, we propose a lightweight method for arbitrary-oriented ship detection in SAR images, named LSR-Det. Specifically, we introduce a lightweight backbone network based on contour guidance, which reduces the number of parameters while maintaining excellent feature extraction capability. Additionally, a lightweight adaptive feature pyramid network is designed to enhance the fusion capability of the ship features across different layers with a low computational cost by incorporating adaptive ship feature fusion modules between the feature layers. To efficiently utilize the fused features, a lightweight rotating detection head is designed, incorporating the idea of sharing the convolutional parameters, thereby improving the network’s ability to detect multi-scale ship targets. The experiments conducted on the SAR ship detection dataset (SSDD) and the rotating ship detection dataset (RSDD-SAR) demonstrate that LSR-Det achieves an average precision (AP50) of 98.5% and 97.2% with 3.21 G floating point operations (FLOPs) and 0.98 M parameters, respectively, outperforming the current popular SAR arbitrary-direction ship target detection methods.

Improved YOLOv8 for Dangerous Goods Detection in X-ray Security Images

X-ray security images face significant challenges due to complex backgrounds, item overlap, and multi-scale target detection. Traditional methods often struggle to accurately identify objects, especially under cluttered conditions. This paper presents an advanced detection model, called YOLOv8n-GEMA, which incorporates several enhancements to address these issues. Firstly, the generalized efficient layer aggregation network (GELAN) module is employed to augment the feature fusion capabilities. Secondly, to tackle the problems of overlap and occlusion in X-ray images, the efficient multi-scale attention (EMA) module is utilized, effectively managing the feature capture and interdependencies among overlapping items, thereby boosting the model’s detection capability in such scenarios. Lastly, addressing the diverse sizes of items in X-ray images, the Inner-CIoU loss function uses auxiliary bounding boxes at varying scale ratios for loss calculation, ensuring faster and more effective bounding box predictions. The enhanced YOLOv8 model was tested on the public datasets SIXRay, HiXray, CLCXray, and PIDray, where the improved model’s mean average precision (mAP) reached 94.4%, 82.0%, 88.9%, and 85.9%, respectively, showing improvements of 3.6%, 1.6%, 0.9%, and 3.4% over the original YOLOv8. These results demonstrate the effectiveness and universality of the proposed method. Compared to current mainstream X-ray images of dangerous goods detection models, this model significantly reduces the false detection rate of dangerous goods in X-ray security images and achieves substantial improvements in the detection of overlapping and multi-scale targets, realizing higher accuracy in dangerous goods detection.

A Multi-Scale Target Detection Method Using an Improved Faster Region Convolutional Neural Network Based on Enhanced Backbone and Optimized Mechanisms.

Currently, existing deep learning methods exhibit many limitations in multi-target detection, such as low accuracy and high rates of false detection and missed detections. This paper proposes an improved Faster R-CNN algorithm, aiming to enhance the algorithm's capability in detecting multi-scale targets. This algorithm has three improvements based on Faster R-CNN. Firstly, the new algorithm uses the ResNet101 network for feature extraction of the detection image, which achieves stronger feature extraction capabilities. Secondly, the new algorithm integrates Online Hard Example Mining (OHEM), Soft non-maximum suppression (Soft-NMS), and Distance Intersection Over Union (DIOU) modules, which improves the positive and negative sample imbalance and the problem of small targets being easily missed during model training. Finally, the Region Proposal Network (RPN) is simplified to achieve a faster detection speed and a lower miss rate. The multi-scale training (MST) strategy is also used to train the improved Faster R-CNN to achieve a balance between detection accuracy and efficiency. Compared to the other detection models, the improved Faster R-CNN demonstrates significant advantages in terms of mAP@0.5, F1-score, and Log average miss rate (LAMR). The model proposed in this paper provides valuable insights and inspiration for many fields, such as smart agriculture, medical diagnosis, and face recognition.

Multi-Scale Marine Object Detection in Side-Scan Sonar Images Based on BES-YOLO.

Aiming at the problem of low accuracy of multi-scale seafloor target detection in side-scan sonar images with high noise and complex background texture, a model for multi-scale target detection using the BES-YOLO network is proposed. First, an efficient multi-scale attention (EMA) mechanism is used in the backbone of the YOLOv8 network, and a bi-directional feature pyramid network (Bifpn) is introduced to merge the information of different scales, finally, a Shape_IoU loss function is introduced to continuously optimize the model and improve its accuracy. Before training, the dataset is preprocessed using 2D discrete wavelet decomposition and reconstruction to enhance the robustness of the network. The experimental results show that 92.4% of the mean average accuracy at IoU of 0.5 (mAP@0.5) and 67.7% of the mean average accuracy at IoU of 0.5 to 0.95 (mAP@0.5:0.95) are achieved using the BES-YOLO network, which is an increase of 5.3% and 4.4% compared to the YOLOv8n model. The research results can effectively improve the detection accuracy and efficiency of multi-scale targets in side-scan sonar images, which can be applied to AUVs and other underwater platforms to implement intelligent detection of undersea targets.

LRMSNet: A New Lightweight Detection Algorithm for Multi-Scale SAR Objects

In recent years, deep learning has found widespread application in SAR image object detection. However, when detecting multi-scale targets against complex backgrounds, these models often struggle to strike a balance between accuracy and speed. Furthermore, there is a continuous need to enhance the performance of current models. Hence, this paper proposes LRMSNet, a new multi-scale target detection model designed specifically for SAR images in complex backgrounds. Firstly, the paper introduces an attention module designed to enhance contextual information aggregation and capture global features, which is integrated into a backbone network with an expanded receptive field for improving SAR image feature extraction. Secondly, this paper develops an information aggregation module to effectively fuse different feature layers of the backbone network. Lastly, to better integrate feature information at various levels, this paper designs a multi-scale aggregation network. We validate the effectiveness of our method on three different SAR object detection datasets (MSAR-1.0, SSDD, and HRSID). Experimental results demonstrate that LRMSNet achieves outstanding performance with a mean average accuracy (mAP) of 95.2%, 98.9%, and 93.3% on the MSAR-1.0, SSDD, and HRSID datasets, respectively, with only 3.46 M parameters and 12.6 G floating-point operation cost (FLOPs). When compared with existing SAR object detection models on the MSAR-1.0 dataset, LRMSNet achieves state-of-the-art (SOTA) performance, showcasing its superiority in addressing SAR detection challenges in large-scale complex environments and across various object scales.

Multi-Scale Target Detection in Autonomous Driving Scenarios Based on YOLOv5-AFAM

Multi-scale object detection is critically important in complex driving environments within the field of autonomous driving. To enhance the detection accuracy of both small-scale and large-scale targets in complex autonomous driving environments, this paper proposes an improved YOLOv5-AFAM algorithm. Firstly, the Adaptive Fusion Attention Module (AFAM) and Down-sampling Module (DownC) are introduced to increase the detection precision of small targets. Secondly, the Efficient Multi-scale Attention Module (EMA) is incorporated, enabling the model to simultaneously recognize small-scale and large-scale targets. Finally, a Minimum Point Distance IoU-based Loss Function (MPDIou-LOSS) is introduced to improve the accuracy and efficiency of object detection. Experimental validation on the KITTI dataset shows that, compared to the baseline model, the improved algorithm increased precision by 2.4%, recall by 2.6%, mAP50 by 1.5%, and mAP50-90 by an impressive 4.8%.

Multi-scale Target Detection Algorithm of Optical Remote Sensing Image Based on Improved YOLOv8

Abstract. With the progress of remote sensing sensors, the quality of optical remote sensing image is significantly improved, and target detection on it can extract rich feature information. However, due to the characteristics of remote sensing image with various target sizes and a large proportion of the number of small targets, increasing the difficulty in target detection for it. In response to this challenge, this paper proposes an improved YOLOv8 algorithm for multi-scale target detection of optical remote sensing images. First, we propose a PSPPF module, which improves the model's ability to adapt to different data distributions; Second, DSConv is introduced into the Backbone structure of YOLOv8 to reduce the complexity of the network while maintaining the performance of model detection; Finally, we replace the original loss function CIoU with MPDIoU to improve the localization accuracy of the prediction box. Applying the improved algorithm to the public dataset NWPU VHR-10, the mAP value of the our algorithm is 95.1%, which is 3.0% higher than that of the original YOLOv8, indicating that the proposed algorithm is able to effectively detect multi-scale targets in optical remote sensing images.

Detection of Gannan Navel Orange Ripeness in Natural Environment Based on YOLOv5-NMM

In order to achieve fast and accurate detection of Gannan navel orange fruits with different ripeness levels in a natural environment under all-weather scenarios and then to realise automated harvesting of Gannan navel oranges, this paper proposes a YOLOv5-NMM (YOLOv5 with Navel orange Measure Model) object detection model based on the improvement in the original YOLOv5 model. Based on the changes in the phenotypic characteristics of navel oranges and the Chinese national standard GB/T 21488-2008, the maturity of Gannan navel oranges is tested. And it addresses and improves the problems of occlusion, dense distribution, small target size, rainy days, and light changes in the detection of navel orange fruits. Firstly, a new detection head of 160 × 160 feature maps is constructed in the detection layer to improve the multi-scale target detection layer of YOLOv5 and to increase the detection accuracy of the different maturity levels of Gannan navel oranges of small sizes. Secondly, a convolutional block attention module is incorporated in its backbone layer to capture the correlations between features in different dimensions to improve the perceptual ability of the model. Then, the weighted bidirectional feature pyramid network structure is integrated into the Neck layer to improve the fusion efficiency of the network on the feature maps and reduce the amount of computation. Lastly, in order to reduce the loss of the target of the Gannan Navel Orange due to occlusion and overlapping, the detection frame is used to remove redundancy using the Soft-NMS algorithm to remove redundant candidate frames. The results show that the accuracy rate, recall rate, and average accuracy of the improved YOLOv5-NMM model are 93.2%, 89.6%, and 94.2%, respectively, and the number of parameters is only 7.2 M. Compared with the mainstream network models, such as Faster R-CNN, YOLOv3, the original model of YOLOv5, and YOLOv7-tiny, it is superior in terms of the accuracy rate, recall rate, and average accuracy mean, and also performs well in terms of the detection rate and memory occupation. This study shows that the YOLOv5-NMM model can effectively identify and detect the ripeness of Gannan navel oranges in natural environments, which provides an effective exploration of the automated harvesting of Gannan navel orange fruits.

CCHA YOLO for mycelium clamp connection (CC) and hyphae Autolysis(HA) detection under microscopy imaging and web deployment

Microscopic examination is commonly employed to assess edible fungal mycelium vitality. However, this method can become time-intensive when evaluating a substantial volume of hyphae samples, which implies an urgent need to develop an accurate and automatic determination method. The challenges of mycelium detection come mostly from the multi-scale target detection under various magnifications. In this study, microscopic images of 10 edible fungi strains under different magnification scales or stain colors were collected to create a dataset. An improved multi-scale object detection model for mycelium vitality detection, CCHA YOLO, was proposed by enhancing the Backbone via combining Yolov8m and Swin Transformer (SwinT). Meanwhile, the Convolutional Block Attention Module (CBAM) was introduced to the Head, as well as optimized post-processing techniques to further promote model performance. The results indicated that CCHA YOLO achieved a mAP50:95 (mean average precision) of 89.02 % with a computational load of 98.61 GFLOPs. Additionally, it indicates a 16.67 % accuracy enhancement, needing only 11.3 more computational operations compared to the baseline YOLOv8m. In the meantime, CCHA YOLO was deployed on the web-based edge to facilitate the detection of microscopic images, highlighting the practical applicability of CCHA YOLO in determining mycelium vitality.

Power System to Prevent External Damage Detection Method

An improved YOLOv5s multi-scale target detection algorithm is proposed to address the increasingly threatening problem of foreign object intrusion in power transmission lines, which poses a risk to the safety and stable operation of the power grid. To enhance the model's ability to extract features of different sizes, a new C3 feature extraction module was designed. It uses deformable convolutional networks to replace the original fixed convolutional layers, and then introduces the ECA attention mechanism to take into account global context information, reducing the decrease in model detection accuracy caused by feature loss. An improved form of NWD fusion Wise IoU is proposed as the network's predicted box regression loss function, improving the model's generalization ability and its ability to detect features of small targets, and achieving faster network convergence speed. Experimental results show that the improved algorithm has increased the accuracy P, recall rate R, and average precision mAP by 5.21%, 4.71%, and 6.24%, respectively, compared to the original YOLOv5s model in detecting foreign object intrusion in power transmission lines, while also enhancing the detection performance of small targets.

An Improved YOLOv8 Detector for Multi-Scale Target Detection in Remote Sensing Images

An Improved YOLOv8 Detector for Multi-Scale Target Detection in Remote Sensing Images

An optimization method of multiscale storage tank target detection introducing an attention mechanism

Under the combined action of the expansion of the chemical industry zone and urban boundaries, urban areas exposed to danger are also increasing. As containers for chemical storage, storage tanks are potential sources of hazards. Conducting target detection for hazard risk analysis is essential. YOLOv5, a single-stage algorithm with good performance, accurately identifies most storage tanks with clear contours and evident positions; however, the identification effect is not good for storage tanks with small targets or unclear boundaries. This study proposes an optimized model based on the YOLOv5 model. First, the Coordinate Attention (CA) mechanism is introduced to make the model focus on the effective information of the target. Second, to improve the detection effect of small targets, the model adds a small target detection head and performs multiscale target detection. Finally, the EIOU loss function is employed instead of the CIOU loss function in the original model to improve the algorithm’s accuracy and speed. Experimental results show that the optimized model significantly improves the detection effect on small targets compared with the original YOLOv5 model. The number of small targets detected by the optimized model is significantly increased compared with the original model, and the size of the smallest targets detected by the optimized model is reduced by about twice compared with the original model. The model’s accuracy, recall rate, and mean average precision (mAP@0.5) are improved, which can be better applied to the detection of storage tanks.

Intelligent Gangue Sorting System Based on Dual-Energy X-ray and Improved YOLOv5 Algorithm

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform.

Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces.

Unmanned surface vessel (USV) target detection algorithms often face challenges such as misdetection and omission of small targets due to significant variations in target scales and susceptibility to interference from complex environments. To address these issues, we propose a small target enhanced YOLOv7 (STE-YOLO) approach. Firstly, we introduce a specialized detection branch designed to identify tiny targets. This enhancement aims to improve the multi-scale target detection capabilities and address difficulties in recognizing targets of different sizes. Secondly, we present the lite visual center (LVC) module, which effectively fuses data from different levels to give more attention to small targets. Additionally, we integrate the lite efficient layer aggregation networks (L-ELAN) into the backbone network to reduce redundant computations and enhance computational efficiency. Lastly, we use Wise-IOU to optimize the loss function definition, thereby improving the model robustness by dynamically optimizing gradient contributions from samples of varying quality. We conducted experiments on the WSODD dataset and the FIOW-Img dataset. The results on the comprehensive WSODD dataset demonstrate that STE-YOLO, when compared to YOLOv7, reduces network parameters by 14% while improving AP50 and APs scores by 2.1% and 1.6%, respectively. Furthermore, when compared to five other leading target detection algorithms, STE-YOLO demonstrates superior accuracy and efficiency.

Identification and detection of microplastic particles in marine environment by using improved faster R–CNN model

Microplastics refer to plastic particles measuring less than 5 mm, which has led to serious environmental problem and the detection of these tiny particles is crucial for understanding the corresponding distribution and impact on the marine environment. In this paper, an improved faster region-based convolutional neural network (R–CNN) model was developed for the identification and detection of microplastic particles. In the proposed model, the residual network-50 (ResNet-50) is employed as the backbone with the replacement of the traditional one to enhance the feature extraction capability and the feature pyramid networks (FPN) module is introduced together for solving the multi-scale target detection. By using the improved Faster R–CNN model, the network model performance is enhanced where the average confidence of detecting unique microplastic particles in the marine environment reaches as high as 99%. Moreover, the microparticles mixture was bounded precisely via the predicted bounding boxes without missing detection and wrong detection. In this way, the successful identification of polystyrene microplastic particles from the particles suspension with similar shapes but various conditions of backgrounds, brightness, distributions and object sizes, was achieved by employing the proposed improved Faster R–CNN model, enabling the accurate detection of microplastic particles in marine environment.

YOLO-ViT-Based Method for Unmanned Aerial Vehicle Infrared Vehicle Target Detection

The detection of infrared vehicle targets by UAVs poses significant challenges in the presence of complex ground backgrounds, high target density, and a large proportion of small targets, which result in high false alarm rates. To alleviate these deficiencies, a novel YOLOv7-based, multi-scale target detection method for infrared vehicle targets is proposed, which is termed YOLO-ViT. Firstly, within the YOLOV7-based framework, the lightweight MobileViT network is incorporated as the feature extraction backbone network to fully extract the local and global features of the object and reduce the complexity of the model. Secondly, an innovative C3-PANet neural network structure is delicately designed, which adopts the CARAFE upsampling method to utilize the semantic information in the feature map and improve the model’s recognition accuracy of the target region. In conjunction with the C3 structure, the receptive field will be increased to enhance the network’s accuracy in recognizing small targets and model generalization ability. Finally, the K-means++ clustering method is utilized to optimize the anchor box size, leading to the design of anchor boxes better suited for detecting small infrared targets from UAVs, thereby improving detection efficiency. The present article showcases experimental findings attained through the use of the HIT-UAV public dataset. The results demonstrate that the enhanced YOLO-ViT approach, in comparison to the original method, achieves a reduction in the number of parameters by 49.9% and floating-point operations by 67.9%. Furthermore, the mean average precision (mAP) exhibits an improvement of 0.9% over the existing algorithm, reaching a value of 94.5%, which validates the effectiveness of the method for UAV infrared vehicle target detection.

Automatic Recognition Reading Method of Pointer Meter Based on YOLOv5-MR Model.

Meter reading is an important part of intelligent inspection, and the current meter reading method based on target detection has problems of low accuracy and large error. In order to improve the accuracy of automatic meter reading, this paper proposes an automatic reading method for pointer-type meters based on the YOLOv5-Meter Reading (YOLOv5-MR) model. Firstly, in order to improve the detection performance of small targets in YOLOv5 framework, a multi-scale target detection layer is added to the YOLOv5 framework, and a set of Anchors is designed based on the lightning rod dial data set; secondly, the loss function and up-sampling method are improved to enhance the model training convergence speed and obtain the optimal up-sampling parameters; Finally, a new external circle fitting method of the dial is proposed, and the dial reading is calculated by the center angle algorithm. The experimental results on the self-built dataset show that the Mean Average Precision (mAP) of the YOLOv5-MR target detection model reaches 79%, which is 3% better than the YOLOv5 model, and outperforms other advanced pointer-type meter reading models.

Lightweight Object Detection Algorithm for UAV Aerial Imagery

Addressing the challenges of low detection precision and excessive parameter volume presented by the high resolution, significant scale variations, and complex backgrounds in UAV aerial imagery, this paper introduces MFP-YOLO, a lightweight detection algorithm based on YOLOv5s. Initially, a multipath inverse residual module is designed, and an attention mechanism is incorporated to manage the issues associated with significant scale variations and abundant interference from complex backgrounds. Then, parallel deconvolutional spatial pyramid pooling is employed to extract scale-specific information, enhancing multi-scale target detection. Furthermore, the Focal-EIoU loss function is utilized to augment the model’s focus on high-quality samples, consequently improving training stability and detection accuracy. Finally, a lightweight decoupled head replaces the original model’s detection head, accelerating network convergence speed and enhancing detection precision. Experimental results demonstrate that MFP-YOLO improved the mAP50 on the VisDrone 2019 validation and test sets by 12.9% and 8.0%, respectively, compared to the original YOLOv5s. At the same time, the model’s parameter volume and weight size were reduced by 79.2% and 73.7%, respectively, indicating that MFP-YOLO outperforms other mainstream algorithms in UAV aerial imagery detection tasks.

Target detection for remote sensing based on the enhanced YOLOv4 with improved BiFPN

To solve problems for false detection, inadequate regression performance of anchor frames, and the inability to detect small targets in traditional multiscale target detection methods based on YOLOv4, we propose a novel target detection framework named as Enhanced YOLOv4. Firstly, our improved BiFPN replaced the original PANet as the feature fusion module, which can achieve multi-scale feature fusion by way of shared weights. Secondly, the channel attention mechanism (CAM) was embedded before the detection head to highlight the correlation between channels so that small targets can be get more attention. At last, to improve the anchor box regression effect and accelerate the training speed of YOLOv4, we improved the net training loss function, in which the original CIoU was replaced by CDIoU. The experimental results on the DOTA dataset validate our improvement. The mAP of our method is 90.88%, and the frame rate reached 58.76 FPS, at the same time, the speed of detection is not affected significantly.

Research on laparoscopic surgical instrument detection technology based on multi-attention-enhanced feature pyramid network

Laparoscopic surgery is a very active area of research in clinical medicine. Detection of tools in surgical videos can help physicians operate surgical instruments, reduce complications, and ensure patient safety. However, the size of laparoscopic surgical instruments is highly variable, leading to poor detection. Feature pyramid networks (FPNs) can effectively solve the problem of multi-scale target detection, but FPNs still have some problems that limit the full utilization of multi-scale features. By analyzing the FPN design problem, we propose the Multi-Attention Augmented Feature Pyramid Network (MAFPN), which can fully utilize the multi-scale features. First, we replace the convolutional block with feature selection module (FSM) that combines channel attention and global attention, which selectively maintains important information and enhances the expressiveness of features at each scale. Second, the global contextual information is captured by the self-attentive augmented fusion module (AAFM), which enriches the high-level feature information in the FPN and enhances the feature fusion effect. Finally, we use Dynamic Convolution Decomposition (DCD) to alleviate the impact of upsampling while enhancing the feature expression ability. The experimental results on the laparoscopic surgical instrument detection dataset m2cai16-tool-locations show that the average precision of MAFPN is 96.5 when the IOU is 0.5, which is 1.8% better than the baseline method RetinaNet, and the average precision is more than 1.6% better than the comparison network. Compared with the state-of-the-art method, the performance of laparoscopic surgical instrument detection is superior.