Standard Convolution Research Articles

MPCCN: A Symmetry-Based Multi-Scale Position-Aware Cyclic Convolutional Network for Retinal Vessel Segmentation

In medical image analysis, precise retinal vessel segmentation is crucial for diagnosing and managing ocular diseases as the retinal vascular network reflects numerous health indicators. Despite decades of development, challenges such as intricate textures, vascular ruptures, and undetected areas persist, particularly in accurately segmenting small vessels and addressing low contrast in imaging. This study introduces a novel segmentation approach called MPCCN that combines position-aware cyclic convolution (PCC) with multi-scale resolution input to tackle these challenges. By integrating standard convolution with PCC, MPCCN effectively captures both global and local features. A multi-scale input module enhances feature extraction, while a weighted-shared residual and guided attention module minimizes background noise and emphasizes vascular structures. Our approach achieves sensitivity values of 98.87%, 99.17%, and 98.88%; specificity values of 98.93%, 97.25%, and 99.20%; accuracy scores of 97.38%, 97.85%, and 97.75%; and AUC values of 98.90%, 99.15%, and 99.05% on the DRIVE, STARE, and CHASE_DB1 datasets, respectively. In addition, it records F1 scores of 90.93%, 91.00%, and 90.55%. Experimental results demonstrate that our method outperforms existing techniques, especially in detecting small vessels.

Improved Architecture and Training Strategies of YOLOv7 for Remote Sensing Image Object Detection

The technology for object detection in remote sensing images finds extensive applications in production and people’s lives, and improving the accuracy of image detection is a pressing need. With that goal, this paper proposes a range of improvements, rooted in the widely used YOLOv7 algorithm, after analyzing the requirements and difficulties in the detection of remote sensing images. Specifically, we strategically remove some standard convolution and pooling modules from the bottom of the network, adopting stride-free convolution to minimize the loss of information for small objects in the transmission. Simultaneously, we introduce a new, more efficient attention mechanism module for feature extraction, significantly enhancing the network’s semantic extraction capabilities. Furthermore, by adding multiple cross-layer connections in the network, we more effectively utilize the feature information of each layer in the backbone network, thereby enhancing the network’s overall feature extraction capability. During the training phase, we introduce an auxiliary network to intensify the training of the underlying network and adopt a new activation function and a more efficient loss function to ensure more effective gradient feedback, thereby elevating the network performance. In the experimental results, our improved network achieves impressive mAP scores of 91.2% and 80.8% on the DIOR and DOTA version 1.0 remote sensing datasets, respectively. These represent notable improvements of 4.5% and 7.0% over the original YOLOv7 network, significantly enhancing the efficiency of detecting small objects in particular.

Insulator Defect Detection Based on YOLOv5s-KE

To tackle the issue of low detection accuracy in insulator images caused by intricate backgrounds and small defect sizes, as well as the requirement for real-time detection on embedded and mobile devices, this research introduces the YOLOv5s-KE model. Integrating multiple strategies, YOLOv5s-KE aims to boost detection accuracy significantly. Initially, an enhanced anchor generation method utilizing the K-means++ algorithm is proposed to generate more appropriate anchor boxes for insulator defects. Moreover, an attention mechanism is integrated into both the backbone and neck networks to enhance the model’s capacity to focus on defect features and resist interference. To improve the detection of small defects, the EIoU loss function is implemented in place of the original CIoU loss function. In order to meet the real-time detection needs on embedded and mobile devices, the model is further refined through the integration of Ghost convolution for lightweight feature extraction and a linear transformation to reduce the computational burden of standard convolution. A channel pruning strategy is deployed to optimize the sparsely trained network, diminishing redundancy, and improving model generalization. Additionally, the CARAFE operator replaces the original upsampling operator to minimize model parameters and elevate detection speed. Experimental outcomes demonstrate that YOLOv5s-KE achieves a detection accuracy of 92.3% on the Chinese transmission line insulator dataset, marking a 5.2% enhancement over the original YOLOv5s. The streamlined version of YOLOv5s-KE achieves a detection speed of 94.3 frames per second, indicating an improvement of 30.1 frames per second compared to the original model. Model parameters are condensed to 9.6 M, resulting in a detection accuracy of 91.1%. This study underscores the precision and efficiency of the proposed approach, suggesting that the advanced strategies explored introduce novel possibilities for insulator defect detection.

Fast flow field prediction based on E(2)-equivariant steerable convolutional neural networks

In the field of flow field reconstruction, traditional deep learning models predominantly rely on standard convolutions, but their predictive accuracy remains limited. To address this issue, we explore the potential of E(2)-equivariant convolutions to enhance the predictive accuracy of deep learning models for fast flow field prediction. Unlike conventional convolutions, E(2)-equivariant convolutions offer a richer representation capability by better capturing geometric and structural information. Our neural network integrates an attention mechanism that leverages the signed distance function (SDF) to encode geometric details and an indicator matrix to incorporate boundary conditions. The model predicts velocity and pressure fields as outputs. We conducted experiments specifically targeting non-uniform steady laminar flows, and the results show a 16.1% reduction in overall error compared to models based on traditional convolutions while maintaining high efficiency. These findings indicate that E(2)-equivariant convolution, coupled with an attention mechanism, significantly improves flow field prediction by focusing on critical information and better representing complex geometries.

An efficient and lightweight banana detection and localization system based on deep CNNs for agricultural robots

Accurate detection and localization of fruits in natural environments is a key step for fruit picking robots to achieve precise harvesting. However, existing banana detection and positioning methods have two main limitations in practical applications: a large number of model parameters that make deployment difficult, and a need for performance improvement. To tackle the above issues, a high-precision and lightweight banana bunch recognition and localization method was proposed and deployed on edge devices for application. First, a Slim-Banana model was proposed based on the improvement of YOLOv8l. In order to reduce the model calculation amount and maintain high performance, GSConv was introduced in the Slim-Banana model to replace the standard convolution, and combined with grouped convolution and spatial convolution. At the same time, the cross-stage local network (GSCSP) module was designed to reduce the computational complexity and the complexity of the network structure through a single-stage aggregation method. Then, the RealSense depth sensor is combined with TOF technology to perform image registration and 3D localization of the banana. Finally, the pipeline is deployed on the Nvidia Orin NX edge device and its performance and resource consumption in actual work are deeply analyzed. Experimental results show that the detection precision, recall, mAP and inference time of our method are 0.947, 0.948, 0.98 and 113.6ms respectively, the network memory size required is 4449MiB, and the average localization errors in the X-axis, Y-axis and Z-axis directions are 13.47mm, 12.87mm and 13.87mm respectively. To our knowledge, this is the first work that implements banana detection and localization on edge devices. Experimental results show that compared with existing methods, our method achieves better performance in complex orchard environments, achieving efficient and lightweight banana recognition and localization.

Research on improvement strategies for a lightweight multi-object weed detection network based on YOLOv5

Traditional weed detection technology has several limitations, including low detection accuracy, substantial computational demands, and large-scale detection models. To meet the requirements of weed multi-target identification and portability, this study proposes the YOLO–WEED model for weed recognition. The proposed model has the following innovations: (1) The backbone standard convolution module in YOLOv5 was replaced by the lightweight MobileNetv3 network to simplify the network structure and reduce parameter complexity; (2) The addition of convolutional block attention module (CBAM) to the neck network enabled the model to focus on the most important features while filtering out noise and irrelevant information; (3) To further improve classification accuracy and reduce loss, the C2f module was employed to improve the C3 module in the neck network; and (4) During the model plot process, a coordinate variable was added in the box label to help the model accurately locate the weeds. In the study, six species of weeds and one crop were used as test subjects. After image enhancement techniques were used, ablation experiments were deployed. The experimental results indicated that the YOLO–WEED model achieved an average accuracy of 92.5% in identifying six types of weeds and one type of crop. The accuracies for each type of plant were 82.7%, 97.3%, 98.8%, 86%, 93.5%, 99.3% and 89.6%, respectively. The number of model parameters was reduced by 39.4% compared with YOLOv5s. Furthermore, the localisation, classification and object losses were reduced by 0.025, 0.005 and 0.014, respectively. The model optimisation and deployment of the Jetson mobile terminal for multi-target detection were realised, and the performance was better than six network models such as YOLOv5s.

A defect detection method for Akidzuki pears based on computer vision and deep learning

To quickly and accurately detect defects in Akidzuki (Pyrus pyrifolia Nakai) pears after harvest, this study aims to develop a method for Akidzuki pear defect detection based on computer vision and deep learning models. It mainly consists of obtaining high-quality images using an image acquisition system and proposing a new YOLO-AP detection model to identify defects in Akidzuki pears. The model uses YOLOv5 as the main architecture. The GhostDynamicConv (GDC) module is obtained by replacing the standard convolution in the Ghost module with a dynamic convolution. The C3-GhostDynamicConv (C3-GDC) module is obtained by replacing the Bottleneck module of C3 in Neck with the GDC module, simplifying the network while improving the model's accuracy. Meanwhile, Bottleneck Attention Module (BAM) is introduced after C3-GDC to refine the intermediate features. In addition, the original bounding box loss function is replaced with Wise-IoUv3 (WIoUv3) to accelerate the model convergence. The results demonstrate that YOLO-AP performs better in Akidzuki pear defect detection, with a mAP@0.5 of 0.939, a recall of 0.921, and a detection speed of 454.5 fps (2.2 ms per image). These values represent a 4.2 %, 3.5 %, and 1.4 % improvement over the baseline model. Comparing YOLO-AP with the updated YOLOv9 and other detection models, YOLO-AP is more accurate and faster. These findings demonstrated that the proposed method can detect Akidzuki pear defects in real time, efficiently and accurately, providing technical support for post-harvest defect detection.

Improving YOLOv8 with parallel frequency channel attention for taxi passengers

AbstractDetecting taxi passengers is crucial for assessing taxi driver behavior, which plays a significant role in regulating the taxi industry. Despite the advancements in deep learning, object detection algorithms have not been extensively applied to this domain. In this article, an innovative taxi passenger detection algorithm is introduced based on YOLOv8, a lightweight and highly accurate method designed to automatically monitor driver behavior and regulate the taxi industry. To address the challenge of deploying complex object detection models on mobile devices, the ghost module is incorporated in place of standard convolutions within the C2f module, thereby making the model more lightweight. Furthermore, the model's performance is enhanced by integrating an improved version of Frequency Channel Attention (FCA), termed Parallel Frequency Channel Attention (PFCA), which boosts detection accuracy with minimal additional parameters and computational overhead. Experimental results on a specific taxi passenger dataset demonstrate that the proposed method significantly outperforms the baseline YOLOv8n model. Specifically, the model reduces the number of parameters and floating point operations by 12.96% and 8.18%, respectively, while achieving increases in mAP50 and mAP50‐95 by 0.27 and 0.73 percentage points, respectively.

Rolling bearing fault diagnosis method based on multi-scale pooling residual convolutional neural network under noisy environment

To address the issues of unstable performance and poor generalization ability of bearing fault diagnosis model caused by strong noise and variable operating conditions in actual production，this paper proposes a rolling bearing fault diagnosis method based on MSPRCNN model. By converting vibration signals to frequency domain with FTand utilizing wide convolution kernels for feature extraction, the approach aims to enhance fault detection. A MSPFE module captures information at different scales to simplify complexity, while an UPA module establishes correlations between frequency domain positions. To reduce the impact of noise and address the vanishing gradient problem, the MSPRCNN model employs GC instead of standard convolution, and utilizes the IReLU activation function to improve model feature representation. Experimental results on two datasets show that the fault recognition accuracy is 98.71% under variable loads and 98.2% under variable speeds. The MSPRCNN model outperforms other methods in fault recognition and generalization in noisy environments.

Evaluation of Deformable Convolution: An Investigation in Image and Video Classification

Convolutional Neural Networks (CNNs) present drawbacks for modeling geometric transformations, caused by the convolution operation’s locality. Deformable convolution (DCON) is a mechanism that solves these drawbacks and improves the robustness. In this study, we clarify the optimal way to replace the standard convolution with its deformable counterpart in a CNN model. To this end, we conducted several experiments using DCONs applied in the layers that conform a small four-layer CNN model and on the four-layers of several ResNets with depths 18, 34, 50, and 101. The models were tested in binary balanced classes with 2D and 3D data. If DCON is used on the first layers of the proposal of model, the computational resources will tend to increase and produce bigger misclassification than the standard CNN. However, if the DCON is used at the end layers, the quantity of Flops will decrease, and the classification accuracy will improve by up to 20% about the base model. Moreover, it gains robustness because it can adapt to the object of interest. Also, the best kernel size of the DCON is three. With these results, we propose a guideline and contribute to understanding the impact of DCON on the robustness of CNNs.

AEDN-YOLO: an efficient one-stage detection network for strip steel surface defects

Steel surface defect detection is one of the key tasks in industrial production and quality control. Research on defect detection using deep learning algorithms has shown promising results. However, due to the complex backgrounds, large differences in defect sizes, and diverse defect types present in steel strip surface defect images, existing deep learning algorithms struggle to achieve precise detection. To address these challenges, this paper proposes an efficient detection model named AEDN-YOLO. Firstly, an adaptive feature extraction (AFE) module is designed, embedded into C2f to better capture irregularly shaped objects. Secondly, the Triplet Attention module is incorporated into the bottom layer of the backbone network to enhance the model’s ability to locate defect features accurately. Additionally, replace the standard convolution in the neck network with GSConv, which not only accelerates feature fusion to improve detection speed but also enlarges the model’s receptive field to enhance detection accuracy. Finally, add a small target detection layer to enhance the detection capability for tiny defects. The model achieves mAP of 81.7% and 72.7% on the NEU-DET and GC10-DET datasets, respectively, with a detection speed of 72.1 FPS. Compared to mainstream defect detection algorithms, the proposed algorithm enables accurate and efficient detection of steel surface defects.

SE-CBAM-YOLOv7: An Improved Lightweight Attention Mechanism-Based YOLOv7 for Real-Time Detection of Small Aircraft Targets in Microsatellite Remote Sensing Imaging

Addressing real-time aircraft target detection in microsatellite-based visible light remote sensing video imaging requires considering the limitations of imaging payload resolution, complex ground backgrounds, and the relative positional changes between the platform and aircraft. These factors lead to multi-scale variations in aircraft targets, making high-precision real-time detection of small targets in complex backgrounds a significant challenge for detection algorithms. Hence, this paper introduces a real-time aircraft target detection algorithm for remote sensing imaging using an improved lightweight attention mechanism that relies on the You Only Look Once version 7 (YOLOv7) framework (SE-CBAM-YOLOv7). The proposed algorithm replaces the standard convolution (Conv) with a lightweight convolutional squeeze-and-excitation convolution (SEConv) to reduce the computational parameters and accelerate the detection process of small aircraft targets, thus enhancing real-time onboard processing capabilities. In addition, the SEConv-based spatial pyramid pooling and connected spatial pyramid convolution (SPPCSPC) module extracts image features. It improves detection accuracy while the feature fusion section integrates the convolutional block attention module (CBAM) hybrid attention network, forming the convolutional block attention module Concat (CBAMCAT) module. Furthermore, it optimizes small aircraft target features in channel and spatial dimensions, improving the model’s feature fusion capabilities. Experiments on public remote sensing datasets reveal that the proposed SE-CBAM-YOLOv7 improves detection accuracy by 0.5% and the mAP value by 1.7% compared to YOLOv7, significantly enhancing the detection capability for small-sized aircraft targets in satellite remote sensing imaging.

LDConv: Linear deformable convolution for improving convolutional neural networks

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information from other locations, and its sampled shapes is fixed. On the other hand, the size of the convolutional kernel is fixed to k × k, which is a fixed square shape, and the number of parameters tends to grow squarely with size. Although Deformable Convolution (Deformable Conv) address the problem of fixed sampling of standard convolutions, the number of parameters also tends to grow in a squared manner, and Deformable Conv do not explore the effect of different initial sample shapes on network performance. In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance. In LDConv, a novel coordinate generation algorithm is defined to generate different initial sampled positions for convolutional kernels of arbitrary size. To adapt to changing targets, offsets are introduced to adjust the shape of the samples at each position. LDConv corrects the growth trend of the number of parameters for standard convolution and Deformable Conv to a linear growth. Compared to Deformable Conv, LDConv provides richer choices and can be equivalent to deformable convolution when the number of parameters of LDConv is set to the square of K. Differently, this paper also explores the effect of neural networks by using LDConv with the same size and different initial sampling shapes. LDConv completes the process of efficient feature extraction by irregular convolutional operations and brings more exploration options for convolutional sampled shapes. Object detection experiments on representative datasets COCO2017, VOC 7 + 12, and VisDrone-DET2021 fully demonstrate the advantages of LDConv. LDConv is a plug-and-play convolutional operation that can replace the convolutional operation to improve network performance. The code for the relevant tasks can be found at https://github.com/CV-ZhangXin/LDConv.

Identifying rice field weeds from unmanned aerial vehicle remote sensing imagery using deep learning

BackgroundRice field weed object detection can provide key information on weed species and locations for precise spraying, which is of great significance in actual agricultural production. However, facing the complex and changing real farm environments, traditional object detection methods still have difficulties in identifying small-sized, occluded and densely distributed weed instances. To address these problems, this paper proposes a multi-scale feature enhanced DETR network, named RMS-DETR. By adding multi-scale feature extraction branches on top of DETR, this model fully utilizes the information from different semantic feature layers to improve recognition capability for rice field weeds in real-world scenarios.MethodsIntroducing multi-scale feature layers on the basis of the DETR model, we conduct a differentiated design for different semantic feature layers. The high-level semantic feature layer adopts Transformer structure to extract contextual information between barnyard grass and rice plants. The low-level semantic feature layer uses CNN structure to extract local detail features of barnyard grass. Introducing multi-scale feature layers inevitably leads to increased model computation, thus lowering model inference speed. Therefore, we employ a new type of Pconv (Partial convolution) to replace traditional standard convolutions in the model.ResultsCompared to the original DETR model, our proposed RMS-DETR model achieved an average recognition accuracy improvement of 3.6% and 4.4% on our constructed rice field weeds dataset and the DOTA public dataset, respectively. The average recognition accuracies reached 0.792 and 0.851, respectively. The RMS-DETR model size is 40.8 M with inference time of 0.0081 s. Compared with three classical DETR models (Deformable DETR, Anchor DETR and DAB-DETR), the RMS-DETR model respectively improved average precision by 2.1%, 4.9% and 2.4%.DiscussionThis model is capable of accurately identifying rice field weeds in complex real-world scenarios, thus providing key technical support for precision spraying and management of variable-rate spraying systems.

A semantic segmentation model for road cracks combining channel-space convolution and frequency feature aggregation

In transportation, roads sometimes have cracks due to overloading and other reasons, which seriously affect driving safety, and it is crucial to identify and fill road cracks in time. Aiming at the defects of existing semantic segmentation models that have degraded the segmentation performance of road crack images and the standard convolution makes it challenging to capture the spatial and channel coupling relationship between pixels. It is difficult to differentiate crack pixels from background pixels in complex backgrounds; this paper proposes a semantic segmentation model for road cracks that combines channel-spatial convolution with the aggregation of frequency features. A new convolutional block is proposed to accurately identify cracked pixels by grouping spatial displacements and convolutional kernel weight dynamization while modeling pixel spatial relationships linked to channel features. To enhance the contrast of crack edges, a frequency domain feature aggregation module is proposed, which uses a simple windowing strategy to solve the problem of mismatch of frequency domain inputs and, at the same time, takes into account the effect of the frequency imaginary part on the features to model the deep frequency features effectively. Finally, a feature refinement module is designed to refine the semantic features to improve the segmentation accuracy. Many experiments have proved that the model proposed in this paper has better performance and more application potential than the current popular general model.

Defect detection of photovoltaic modules based on improved VarifocalNet

Detecting and replacing defective photovoltaic modules is essential as they directly impact power generation efficiency. Many current deep learning-based methods for detecting defects in photovoltaic modules focus solely on either detection speed or accuracy, which limits their practical application. To address this issue, an improved VarifocalNet has been proposed to enhance both the detection speed and accuracy of defective photovoltaic modules. Firstly, a new bottleneck module is designed to replace the first bottleneck module of the last stage convolution group in the backbone. This new module includes both standard convolution and dilated convolution, enabling an increase in network depth and receptive field without reducing the output feature map size. This improvement can help to enhance the accuracy of defect detection for photovoltaic modules. Secondly, another bottleneck module is also designed and used to replace the original bottleneck module used in the fourth stage convolution group of the backbone. This new module has smaller parameters than the original bottleneck module, which is useful to improve the defect detection speed of the photovoltaic module. Thirdly, a feature interactor is designed in the detection head to enhance feature expression in the classification branch. This helps improve detection accuracy. Besides, an improved intersection over union is proposed and introduced into the loss function to measure the difference between the predicted and ground truth boxes. This is useful for improving defect detection accuracy. Compared to other methods, the proposed method has the highest detection accuracy. Additionally, it also has a faster detection speed than other methods except for the DDH-YOLOv5 method and the improved YOLOv7 method.

MobileDepth: Monocular Depth Estimation Based on Lightweight Vision Transformer

ABSTRACT As deep learning takes off, monocular depth estimation based on convolutional neural networks (CNNs) has made impressive progress. CNNs are superior at extracting local characteristics from a single image; however, they are unable to manage long-range dependence and thus have a substantial impact on the performance of monocular depth estimation. In addition to this, as architectures based on CNNs frequently utilize down sampling operations, numbers of pixel-level features, which are extremely crucial for dense prediction tasks, are lost in the encoder phase. Unlike CNNs, ViT is capable of capturing global feature information, but it requires numbers of parameters and data augmentation owing to its lack of inductive bias. To address the aforementioned difficulties, in this study, we propose a Dilated Self Attention Block (DSAB) as well as a Local and Global Feature Extraction (LGFE) module. The former resolves the inference speed issue of standard ViT models, and we accomplish this by limiting the number of self-attention computations among tokens. The latter combines the advantages of CNNs and ViT, first extracting local representation information in low-dimensional space through standard convolution and then mapping the input tensor to high-dimensional space to capture global information, achieving the simultaneous extraction of global and local characteristics.

A Faster and Lightweight Lane Detection Method in Complex Scenarios

Lane detection is a crucial visual perception task in the field of autonomous driving, serving as one of the core modules in advanced driver assistance systems (ADASs).To address the insufficient real-time performance of current segmentation-based models and the conflict between the demand for high inference speed and the excessive parameters in resource-constrained edge devices (such as onboard hardware, mobile terminals, etc.) in complex real-world scenarios, this paper proposes an efficient and lightweight auxiliary branch network (CBGA-Auxiliary) to tackle these issues. Firstly, to enhance the model’s capability to extract feature information in complex scenarios, a row anchor-based feature extraction method based on global features was adopted. Secondly, employing ResNet as the backbone network and CBGA (Conv-Bn-GELU-SE Attention) as the fundamental module, we formed the auxiliary segmentation network, significantly enhancing the segmentation training speed of the model. Additionally, we replaced the standard convolutions in the branch network with lightweight GhostConv convolutions. This reduced the parameters and computational complexity while maintaining accuracy. Finally, an additional enhanced structural loss function was introduced to compensate for the structural defect loss issue inherent in the row anchor-based method, further improving the detection accuracy. The model underwent extensive experimentation on the Tusimple dataset and the CULane dataset, which encompass various road scenarios. The experimental results indicate that the model achieved the highest F1 scores of 96.1% and 71.0% on the Tusimple and CULane datasets, respectively. At a resolution of 288 × 800, the ResNet18 and ResNet34 models achieved maximum inference speeds of 410FPS and 280FPS, respectively. Compared to existing SOTA models, it demonstrates a significant advantage in terms of inference speed. The model achieved a good balance between accuracy and inference speed, making it suitable for deployment on edge devices and validates the effectiveness of the model.

Research on Intelligent Recognition for Plant Pests and Diseases Based on Improved YOLOv8 Model

Plant pests and diseases are important parts of insect disease control and the high-quality development of agriculture. Traditional methods for identifying plant diseases and pests suffer from low accuracy and slow speed, while the existing machine learning methods are constrained by environmental and technological factors, leading to low recognition efficiency. To address the issue of the above problems, this paper has proposed an intelligent recognition algorithm based on the improved YOLOv8 model, which has high recognition accuracy and speed. Firstly, in the Backbone network, the Global Attention Mechanism (GAM) is adopted to weigh the important feature information, thereby improving the accuracy of the model. Secondly, in the mixed feature part of the Neck network, the Receptive-Field Attention Convolutional (RFA Conv) operation is used instead of standard convolution operations to enhance the processing ability for feature information and to reduce computational complexity and costs, thus improving the network performance. After verifying the rice and cotton datasets, the accuracy indicator mean average precision (mAP) reaches 71.27% and 82.91%, respectively, in the two different datasets. Comparing these indices with those of the Faster R-CNN, YOLOv7, and the original YOLOv8 model, the results fully demonstrate the effectiveness and superiority of the improved model in terms of detection accuracy.

FCNet: Flexible Convolution Network for Infrared Small Ship Detection

The automatic monitoring and detection of maritime targets hold paramount significance in safeguarding national sovereignty, ensuring maritime rights, and advancing national development. Among the principal means of maritime surveillance, infrared (IR) small ship detection technology stands out. However, due to their minimal pixel occupancy and lack of discernible color and texture information, IR small ships have persistently posed a formidable challenge in the realm of target detection. Additionally, the intricate maritime backgrounds often exacerbate the issue by inducing high false alarm rates. In an effort to surmount these challenges, this paper proposes a flexible convolutional network (FCNet), integrating dilated convolutions and deformable convolutions to achieve flexible variations in convolutional receptive fields. Firstly, a feature enhancement module (FEM) is devised to enhance input features by fusing standard convolutions with dilated convolutions, thereby obtaining precise feature representations. Subsequently, a context fusion module (CFM) is designed to integrate contextual information during the downsampling process, mitigating information loss. Furthermore, a semantic fusion module (SFM) is crafted to fuse shallow features with deep semantic information during the upsampling process. Additionally, squeeze-and-excitation (SE) blocks are incorporated during upsampling to bolster channel information. Experimental evaluations conducted on two datasets demonstrate that FCNet outperforms other algorithms in the detection of IR small ships on maritime surfaces. Moreover, to propel research in deep learning-based IR small ship detection on maritime surfaces, we introduce the IR small ship dataset (Maritime-SIRST).