Spatial Pyramid Research Articles

MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism

AbstractAccurate segmentation of brain tumor magnetic resonance imaging (MRI) is crucial for treatment planning. Addressing the challenges of complex tumor structures and inadequate cross‐channel information utilization in Unet‐based segmentation, this paper proposes the multi‐scale residual brain tumor MRI segmentation network (MRS‐Net) incorporating an attention mechanism to enhance segmentation accuracy. First, the double residual feature fusion module is utilized to enhance the fusion of feature information between different levels. Second, the Atrous Spatial Pyramid Pooling is introduced as a bridging module of the network to capture the features at different scales of the image, so as to enhance the extraction capability of the network for detailed features. Finally, the inverted residual coordinate attention module replaces the direct splicing in Unet to fuse the large feature information at each level and scale, thus enhancing the model's ability to recognize the spatial location information of brain tumors. The Dice coefficients, positive predictive values (PPVs), sensitivities (Sensitivity) and Hausdorff distance (HD), which are the four evaluation indexes, reach 84.54%, 87.43%, 88.37% and 2.248, respectively, which are improved by 1.85%, 2.11%, 2.88% and 6.0%, respectively, compared with Unet. The experimental results show that MRS‐Net achieves better brain tumor image segmentation.

MPE-HRNetL: A Lightweight High-Resolution Network for Multispecies Animal Pose Estimation

Animal pose estimation is crucial for animal health assessment, species protection, and behavior analysis. It is an inevitable and unstoppable trend to apply deep learning to animal pose estimation. In many practical application scenarios, pose estimation models must be deployed on edge devices with limited resource. Therefore, it is essential to strike a balance between model complexity and accuracy. To address this issue, we propose a lightweight network model, i.e., MPE-HRNet.L, by improving Lite-HRNet. The improvements are threefold. Firstly, we improve Spatial Pyramid Pooling-Fast and apply it and the improved version to different branches. Secondly, we construct a feature extraction module based on a mixed pooling module and a dual spatial and channel attention mechanism, and take the feature extraction module as the basic module of MPE-HRNet.L. Thirdly, we introduce a feature enhancement stage to enhance important features. The experimental results on the AP-10K dataset and the Animal Pose dataset verify the effectiveness and efficiency of MPE-HRNet.L.

Electric Trucks Pantograph-Catenary Interaction Condition Monitoring Method Based on Semantic Segmentation Network and Linear Fitting

Abstract The pantograph–catenary system (PCS) of dual source electric trucks is an important way for the vehicle to obtain electricity from the grid. Power quality depends on the reliability of the PCS contact. It is therefore necessary to monitor the PCS by detecting the contact point (CPT) between the pantograph and the catenary. However, due to structural variations between train PCS and electric truck PCS, existing CPT detection methods designed for trains are not suitable for electric trucks. To solve this problem, this paper proposes a CPT detection method that combines semantic segmentation and linear fitting. First, a lightweight pantograph and contact line segmentation network (PCSN) is proposed to extract the pantograph and contact line regions. The PCSN comprise a lightweight encoder, Cross-Attention Fusion decoder and Hybrid Atrous Spatial Pyramid Pooling (HASPP). The lightweight encoder comprise mainly of focus and lightweight feature extraction unit. The cross-attention fusion decoder is used to fuse low-level and high-level features, and the HASPP is used to obtain multi-scale context
information. Second, we use position correction and least squares linear fitting algorithm to detect the CPT of electric trucks. Experimental results show that the proposed method's detection error is concentrated around ±5 pixels. In terms of processing speed, the proposed method can reach a high speed of 76.9 FPS (Frames Per Second) on RTX 3080 desktop computer, 47.13 FPS on CPU I9-12900, and 11.63 FPS on embedded device Jeston TX2.

Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

YOLO-DroneMS: Multi-Scale Object Detection Network for Unmanned Aerial Vehicle (UAV) Images

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

Predicting future evapotranspiration based on remote sensing and deep learning

Study regionThe watersheds of the four flux sites in the United States were selected as the study areas for this research. Study focusThis study validates the efficiency of Convolutional Long Short-Term Memory Network (ConvLSTM) models for site-scale ETa prediction. We enhanced the ConvLSTM model by adding a Spatial Pyramid Pooling module (SPPM) and a Multi-head Self-Attention Module (MSA-Module), creating the Multi-head Self-Attention ConvLSTM (MSA-ConvLSTM) model, which we applied to predicting regional-scale actual evapotranspiration (ETa). This study aims to investigate whether the MSA-ConvLSTM model can enhance the accuracy of predicting regional-scale ETa, considering multiple feature variables. Furthermore, we evaluated different performance indicators, discussed possible reasons for errors in regional ETa prediction, and conducted sensitivity analysis of the model characteristics. New hydrological insights for the regionThe MSA-ConvLSTM model accurately predicts the future state of ETa. The average R2 was 0.81, which is 11.6 % and 5.5 % higher than those of the ConvLSTM and Self-Attention ConvLSTM (SA-ConvLSTM) models, respectively. The average RMSE is 11.94 mm/m, which is 21.5 % and 13.7 % lower than ConvLSTM and SA-ConvLSTM, respectively. The average MAE is 9.46 mm/m, which is 21.3 % and 13 % lower than ConvLSTM and SA-ConvLSTM, respectively. Incorporating of a multi-head self-attention module enhances the model’s capacity for comprehensive understanding of input data features. This improvement allows the model to better adapt to feature relationships at varying scales and angles, enhancing its representational capacity and enabling effective adaptation to complex environmental changes.

Road Defect Identification and Location Method Based on an Improved ML-YOLO Algorithm

The conventional method for detecting road defects relies heavily on manual inspections, which are often inefficient and struggle with precise defect localization. This paper introduces a novel approach for identifying and locating road defects based on an enhanced ML-YOLO algorithm. By refining the YOLOv8 object detection framework, we optimize both the traditional convolutional layers and the spatial pyramid pooling network. Additionally, we incorporate the Convolutional Block Attention to effectively capture channel and spatial features, along with the Selective Kernel Networks that dynamically adapt to feature extraction across varying scales. An optimized target localization algorithm is proposed to achieve high-precision identification and accurate positioning of road defects. Experimental results indicate that the detection accuracy of the improved ML-YOLO algorithm reaches 0.841, with a recall rate of 0.745 and an average precision of 0.817. Compared to the baseline YOLOv8 model, there is an increase in accuracy by 0.13, a rise in recall rate by 0.117, and an enhancement in average precision by 0.116. After the high detection accuracy of road defects was confirmed, generalization experiments were carried out on the improved ML-YOLO model in the public data set. The experimental results showed that compared with the original YOLOv8n, the average precision and recall rate of all types of ML-YOLO increased by 0.075, 0.121, and 0.035 respectively, indicating robust generalization capabilities. When applied to real-time road monitoring scenarios, this algorithm facilitates precise detection and localization of defects while significantly mitigating traffic accident risks and extending roadway service life. A high detection accuracy of road defects was achieved.

LT-DeepLab: an improved DeepLabV3+ cross-scale segmentation algorithm for Zanthoxylum bungeanum Maxim leaf-trunk diseases in real-world environments

IntroductionZanthoxylum bungeanum Maxim is an economically significant crop in Asia, but large-scale cultivation is often threatened by frequent diseases, leading to significant yield declines. Deep learning-based methods for crop disease recognition have emerged as a vital research area in agriculture.MethodsThis paper presents a novel model, LT-DeepLab, for the semantic segmentation of leaf spot (folium macula), rust, frost damage (gelu damnum), and diseased leaves and trunks in complex field environments. The proposed model enhances DeepLabV3+ with an innovative Fission Depth Separable with CRCC Atrous Spatial Pyramid Pooling module, which reduces the structural parameters of Atrous Spatial Pyramid Pooling module and improves cross-scale extraction capability. Incorporating Criss-Cross Attention with the Convolutional Block Attention Module provides a complementary boost to channel feature extraction. Additionally, deformable convolution enhances low-dimensional features, and a Fully Convolutional Network auxiliary header is integrated to optimize the network and enhance model accuracy without increasing parameter count.ResultsLT-DeepLab improves the mean Intersection over Union (mIoU) by 3.59%, the mean Pixel Accuracy (mPA) by 2.16%, and the Overall Accuracy (OA) by 0.94% compared to the baseline DeepLabV3+. It also reduces computational demands by 11.11% and decreases the parameter count by 16.82%.DiscussionThese results indicate that LT-DeepLab demonstrates excellent disease segmentation capabilities in complex field environments while maintaining high computational efficiency, offering a promising solution for improving crop disease management efficiency.

A Candy Defect Detection Method Based on StyleGAN2 and Improved YOLOv7 for Imbalanced Data.

Quality management in the candy industry is a vital part of food quality management. Defective candies significantly affect subsequent packaging and consumption, impacting the efficiency of candy manufacturers and the consumer experience. However, challenges exist in candy defect detection on food production lines due to the small size of the targets and defects, as well as the difficulty of batch sampling defects from automated production lines. A high-precision candy defect detection method based on deep learning is proposed in this paper. Initially, pseudo-defective candy images are generated based on Style Generative Adversarial Network-v2 (StyleGAN2), thereby enhancing the authenticity of these synthetic defect images. Following the separation of the background based on the color characteristics of the defective candies on the conveyor belt, a GAN is utilized for negative sample data enhancement. This effectively reduces the impact of data imbalance between complete and defective candies on the model's detection performance. Secondly, considering the challenges brought by the small size and random shape of candy defects to target detection, the efficient target detection method YOLOv7 is improved. The Spatial Pyramid Pooling Fast Cross Stage Partial Connection (SPPFCSPC) module, the C3C2 module, and the global attention mechanism are introduced to enhance feature extraction precision. The improved model achieves a 3.0% increase in recognition accuracy and a 3.7% increase in recall rate while supporting real-time recognition scenery. This method not only enhances the efficiency of food quality management but also promotes the application of computer vision and deep learning in industrial production.

Semantic Segmentation Model-Based Boundary Line Recognition Method for Wheat Harvesting

The wheat harvesting boundary line is vital reference information for the path tracking of an autonomously driving combine harvester. However, unfavorable factors, such as a complex light environment, tree shade, weeds, and wheat stubble color interference in the field, make it challenging to identify the wheat harvest boundary line accurately and quickly. Therefore, this paper proposes a harvest boundary line recognition model for wheat harvesting based on the MV3_DeepLabV3+ network framework, which can quickly and accurately complete the identification in complex environments. The model uses the lightweight MobileNetV3_Large as the backbone network and the LeakyReLU activation function to avoid the neural death problem. Depth-separable convolution is introduced into Atrous Spatial Pyramid Pooling (ASPP) to reduce the complexity of network parameters. The cubic B-spline curve-fitting method extracts the wheat harvesting boundary line. A prototype harvester for wheat harvesting boundary recognition was built, and field tests were conducted. The test results show that the wheat harvest boundary line recognition model proposed in this paper achieves a segmentation accuracy of 98.04% for unharvested wheat regions in complex environments, with an IoU of 95.02%. When the combine harvester travels at 0~1.5 m/s, the normal speed for operation, the average processing time and pixel error for a single image are 0.15 s and 7.3 pixels, respectively. This method could achieve high recognition accuracy and fast recognition speed. This paper provides a practical reference for the autonomous harvesting operation of a combine harvester.

An Improved Reptile Search Algorithm with Multiscale Adaptive Deep Learning Technique and Atrous Spatial Pyramid Pooling for IoT-based Smart Agriculture Management

Smart farming is an enhanced option for increasing food production, resource management and labour. Existing prediction methods need trained experts to analyse the data, which is a time-consuming process, and thus, there is a need for smart farming with the Internet of Things (IoT). Hence, a well-developed IoT-assisted smart agriculture model is proposed for managing agricultural needs to improve the economic value of farmers. The proposed framework constitutes four major aspects like Crop prediction, Crop yield prediction, Plant disease prediction and Smart irrigation. Initially, the crop images are taken as the input and fed to the Multi-scale Adaptive and Attention-based Convolution Neural Network with Atrous Spatial Pyramid Pooling (MACNN-ASPP), where the dissimilar crops are classified and obtained. In the second aspect, the crop image as well as crop-related data, are fetched from the data sources and given as input. Further, the deep features of the image are extracted that are added with soil and environment condition data. Then this feature is subjected to the Multi-scale Adaptive and Attention-based One-Dimensional Convolution Neural Network with Atrous Spatial Pyramid Pooling (MA1DCNN-ASPP) for crop yield prediction. While in the third aspect, the leaf images are assembled from the data file and fed as input to the MACNN-ASPP for detecting the variety of diseases affecting the plants. In the final aspect, smart irrigation is done by collecting field images with related data. Further, the deep features retrieved from the field images are applied to MA1DCNN-ASPP, where the different conditions of the field will be attained. In order to develop the model adaptively, the hyper-parameters in the network are optimised using the Improved Reptile Search Algorithm (IRSA). Finally, the investigation is done over the proposed methodology using multiple evaluation metrics. In contrast with other approaches, the proposed smart agriculture outperforms the performance of managing crops without any hazardous effects. Accuracy validation executed in the implemented IRSA-MACNN-ASSP-based crop yield prediction model accomplished better efficiency as 6.89%, 4.45%, 2.19% and 1.08% better than the classical techniques like CNN, LSTM, 1DCNN and MA1DCNN-ASPP.

Attention-Guided Residual U-Net with SE Connection and ASPP for Watershed-Based Cell Segmentation in Microscopy Images.

Time-lapse microscopy imaging is a crucial technique in biomedical studies for observing cellular behavior over time, providing essential data on cell numbers, sizes, shapes, and interactions. Manual analysis of hundreds or thousands of cells is impractical, necessitating the development of automated cell segmentation approaches. Traditional image processing methods have made significant progress in this area, but the advent of deep learning methods, particularly those using U-Net-based networks, has further enhanced performance in medical and microscopy image segmentation. However, challenges remain, particularly in accurately segmenting touching cells in images with low signal-to-noise ratios. Existing methods often struggle with effectively integrating features across different levels of abstraction. This can lead to model confusion, particularly when important contextual information is lost or the features are not adequately distinguished. The challenge lies in appropriately combining these features to preserve critical details while ensuring robust and accurate segmentation. To address these issues, we propose a novel framework called RA-SE-ASPP-Net, which incorporates Residual Blocks, Attention Mechanism, Squeeze-and-Excitation connection, and Atrous Spatial Pyramid Pooling to achieve precise and robust cell segmentation. We evaluate our proposed architecture using an induced pluripotent stem cell reprogramming dataset, a challenging dataset that has received limited attention in this field. Additionally, we compare our model with different ablation experiments to demonstrate its robustness. The proposed architecture outperforms the baseline models in all evaluated metrics, providing the most accurate semantic segmentation results. Finally, we applied the watershed method to the semantic segmentation results to obtain precise segmentations with specific information for each cell.

Clinical target volume (CTV) automatic delineation using deep learning network for cervical cancer radiotherapy: A study with external validation.

To explore the accuracy and feasibility of a proposed deep learning (DL) algorithm for clinical target volume (CTV) delineation in cervical cancer radiotherapy and evaluate whether it can perform well in external cervical cancer and endometrial cancer cases for generalization validation. A total of 332 patients were enrolled in this study. A state-of-the-art network called ResCANet, which added the cascademulti-scale convolution in the skip connections to eliminate semantic differences between different feature layers based on ResNet-UNet. The atrous spatial pyramid pooling in the deepest feature layer combined the semantic information of different receptive fields without losing information. A total of 236 cervical cancer cases were randomly grouped into 5-fold cross-training (n=189) and validation (n=47) cohorts. External validations were performed ina separate cohort of 54 cervical cancer and 42 endometrial cancer cases. The performances of the proposed network were evaluated by dice similarity coefficient (DSC), sensitivity (SEN), positive predictive value (PPV), 95% Hausdorff distance (95HD), and oncologist clinical score when comparing them with manual delineation in validation cohorts. In internal validation cohorts, the mean DSC, SEN, PPV, 95HD for ResCANet achieved 74.8%, 81.5%, 73.5%, and 10.5mm. In external independent validation cohorts, ResCANet achieved 73.4%, 72.9%, 75.3%, 12.5mm for cervical cancer cases and 77.1%, 81.1%, 75.5%, 10.3mm for endometrial cancer cases, respectively. The clinical assessment score showed that minor and no revisions (delineation time was shortened to within 30min) accountedforabout 85% of all cases in DL-aided automatic delineation. We demonstrated the problem of model generalizability for DL-based automatic delineation. The proposed network can improve the performance of automatic delineation for cervical cancer and shorten manual delineation time at no expense to quality. The network showed excellent clinical viability, which can also be even generalized for endometrial cancer with excellent performance.

Pre-stack seismic inversion based on one-dimensional GRU combined with two-dimensional improved ASPP

Abstract Pre-stack seismic inversion is essential to detailed stratigraphic interpretation of seismic data. Recently, various deep learning methods have been introduced into pre-stack inversion, effectively capturing the vertical correlations of seismic data. However, existing deep learning methods face challenges such as insufficient feature extraction, poor lateral continuity, and unclear inversion details. We introduce the atrous spatial pyramid pooling (ASPP) module into the pre-stack inversion process, modifying the connection order and mode of its three components. Additionally, we incorporate a triplet attention module to extract features at different scales and utilize a gate recurrent unit (GRU) module to extract global information. During the network training stage, we employ a multi-gather simultaneous inversion method, combining one-dimensional and two-dimensional inversions. The proposed method is named as IGIT (I for Improved ASPP, G for GRU, I for Initial model and T for Triplet attention). To verify the feasibility of this network model, we evaluate it using the Marmousi2 model, SEAM model, and field data, comparing the results with other deep learning methods. Experimental results demonstrate that the IGIT not only improves lateral continuity but also delivers accurate and clear inversion details. Notably, the inversion effect for density parameters shows significant enhancement.

Improved YOLOv7 Electric Work Safety Belt Hook Suspension State Recognition Algorithm Based on Decoupled Head

Safety is the eternal theme of power systems. In view of problems such as time-consuming and poor real-time performance in the correct use of seat belt hooks by manual supervision operators in the process of power operation, this paper proposes an improved YOLOv7 seat belt hook suspension state recognition algorithm. Firstly, the feature extraction part of the YOLOv7 backbone network is improved, and the M-Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (M-SPPCSPC) feature extraction module is constructed to replace the Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (SPPCSPC) module of the backbone network, which reduces the amount of computation and improves the detection speed of the backbone network while keeping the sensory field of the backbone network unchanged. Second, a decoupled head, which realizes the confidence and regression frames separately, is introduced to alleviate the negative impact of the conflict between the classification and regression tasks, consequently improving the network detection accuracy and accelerating the network convergence. Ultimately, a dynamic non-monotonic focusing mechanism is introduced in the output layer, and the Wise Intersection over Union (WioU) loss function is used to reduce the competitiveness of high-quality anchor frames while reducing the harmful gradient generated by low-quality anchor frames, which ultimately improves the overall performance of the detection network. The experimental results show that the mean Average Precision (mAP@0.5) value of the improved network reaches 81.2%, which is 7.4% higher than that of the original YOLOv7, therefore achieving better detection results for multiple-state recognition of hooks.

Computer vision based early fire-detection and firefighting mobile robots oriented for onsite construction

Fires are one of the most dangerous hazards and the leading cause of death in construction sites. This paper proposes a video-based firefighting mobile robot (FFMR), which is designed to patrol the desired territory and will constantly observe for fire-related events to make sure the camera without any occlusions. Once a fire is detected, the early warning system will send sound and light signals instantly and the FFMR moves to the right place to fight the fire source using the extinguisher. To improve the accuracy and speed of fire detection, an improved YOLOv3-Tiny (namely as YOLOv3-Tiny-S) model is proposed by optimizing its network structure, introducing a Spatial Pyramid Pooling (SPP) module, and refining the multi-scale anchor mechanism. The experiments show the proposed YOLOv3-Tiny-S model based FFMR can detect a small fire target with relatively higher accuracy and faster speed under the occlusions by outdoor environment. The proposed FFMR can be helpful to disaster management systems, avoiding huge ecological and economic losses, as well as saving a lot of human lives.

A lightweight defect detection algorithm for escalator steps

In this paper, we propose an efficient target detection algorithm, ASF-Sim-YOLO, to address issues encountered in escalator step defect detection, such as an excessive number of parameters in the detection network model, poor adaptability, and difficulties in real-time processing of video streams. Firstly, to address the characteristics of escalator step defects, we designed the ASF-Sim-P2 structure to improve the detection accuracy of small targets, such as step defects. Additionally, we incorporated the SimAM (Similarity-based Attention Mechanism) by combining SimAM with SPPF (Spatial Pyramid Pooling-Fast) to enhance the model’s ability to capture key information by assigning importance weights to each pixel. Furthermore, to address the challenge posed by the small size of step defects, we replaced the traditional CIoU (Complete-Intersection-over-Union) loss function with NWD (Normalized Wasserstein Distance), which alleviated the problem of defect missing. Finally, to meet the deployment requirements of mobile devices, we performed channel pruning on the model. The experimental results showed that the improved ASF-Sim-YOLO model achieved an average accuracy (mAP50) of 96.8% on the test data set, which was a 22.1% improvement in accuracy compared to the baseline model. Meanwhile, the computational complexity (in GFLOPS) of the model was reduced to a quarter of that of the baseline model, while the frame rate (FPS) was improved to 575.1. Compared with YOLOv3-tiny, YOLOv5s, YOLOv8s, Faster-RCNN, TOOD, RTMDET and other deep learning-based target recognition algorithms, ASF-Sim-YOLO has better detection accuracy and real-time processing capability. These results demonstrate that ASF-Sim-YOLO effectively balances lightweight design and performance improvement, making it highly suitable for real-time detection of step defects, which can meet the demands of escalator inspection operations.

A Novel YOLOv5_ES based on lightweight small object detection head for PCB surface defect detection

In the manufacturing process of printed circuit boards (PCBs), surface defects have a significant negative impact on product quality. Considering that traditional object detection algorithms have low accuracy in handling PCB images with complex backgrounds, various types, and small-sized defects, this paper proposes a PCB defect detection algorithm based on a novel YOLOv5 multi-scale attention mechanism(EMA) spatial pyramid dilated Convolution (SPD-Conv) (YOLOv5_ES) network improved YOLOv5s framework. Firstly, the detection head is optimized by removing medium and large detection layers, fully leveraging the capability of the small detection head to identify minor target defects. This approach not only improves model accuracy but also achieves lightweighting. Secondly, in order to further reduce the number of parameters and computational costs, the SPD-Conv is introduced to improve the feature extraction capability by reducing information loss. Thirdly, a EMA module is introduced to fuse context information of different scales, enhancing the model’s generalization ability. Compared to the YOLOv5s model, there is a 3.1% improvement in mean average precision (mAP0.5), a 55.8% reduction in model parameters, and a 4.8% reduction in giga floating-point operations per second (GFLOPs). These results demonstrate a significant improvement in both accuracy and model parameter efficiency.

Efficient Optimized YOLOv8 Model with Extended Vision.

In the field of object detection, enhancing algorithm performance in complex scenarios represents a fundamental technological challenge. To address this issue, this paper presents an efficient optimized YOLOv8 model with extended vision (YOLO-EV), which optimizes the performance of the YOLOv8 model through a series of innovative improvement measures and strategies. First, we propose a multi-branch group-enhanced fusion attention (MGEFA) module and integrate it into YOLO-EV, which significantly boosts the model's feature extraction capabilities. Second, we enhance the existing spatial pyramid pooling fast (SPPF) layer by integrating large scale kernel attention (LSKA), improving the model's efficiency in processing spatial information. Additionally, we replace the traditional IOU loss function with the Wise-IOU loss function, thereby enhancing localization accuracy across various target sizes. We also introduce a P6 layer to augment the model's detection capabilities for multi-scale targets. Through network structure optimization, we achieve higher computational efficiency, ensuring that YOLO-EV consumes fewer computational resources than YOLOv8s. In the validation section, preliminary tests on the VOC12 dataset demonstrate YOLO-EV's effectiveness in standard object detection tasks. Moreover, YOLO-EV has been applied to the CottonWeedDet12 and CropWeed datasets, which are characterized by complex scenes, diverse weed morphologies, significant occlusions, and numerous small targets. Experimental results indicate that YOLO-EV exhibits superior detection accuracy in these complex agricultural environments compared to the original YOLOv8s and other state-of-the-art models, effectively identifying and locating various types of weeds, thus demonstrating its significant practical application potential.

High-precision and lightweight small-target detection algorithm for low-cost edge intelligence

The proliferation of edge devices driven by advancements in Internet of Things (IoT) technology has intensified the challenge of achieving high-precision small target detection, as it demands extensive computational resources. This amplifies the conflict between the need for precise detection and the requirement for cost-efficiency across numerous edge devices. To solve this problem, this paper introduces an enhanced target detection algorithm, MSGD-YOLO, built upon YOLOv8. The Faster Implementation of CSP Bottleneck with 2 convolutions (C2f) module is enhanced through the integration of the Ghost module and dynamic convolution, resulting in a more lightweight architecture while enhancing feature generation. Additionally, Spatial Pyramid Pooling with Enhanced Local Attention Network (SPPELAN) replaces Spatial Pyramid Pooling Fast (SPPF) to expand the receptive field, optimizing multi-level feature aggregation for improved performance. Furthermore, a novel Multi-Scale Ghost Convolution (MSGConv) and Multi-Scale Generalized Feature Pyramid Network (MSGPFN) are introduced to enhance feature fusion and integrate multi-scale information. Finally, four optimized dynamic convolutional detection heads are employed to capture target features more accurately and improve small target detection precision. Evaluation on the VisDrone2019 dataset shows that compared with YOLOv8-n, MSGD-YOLO improves mAP@50 and mAP@50–95 by 14.1% and 11.2%, respectively. In addition, the model not only achieves a 16.1% reduction in parameters but also attains a processing speed of 24.6 Frames Per Second (FPS) on embedded devices, thereby fulfilling real-time detection requirements.