Deformable Convolutional Networks Research Articles

Non-Contact Blood Pressure Estimation from Radar Signals by a Stacked Deformable Convolution Network.

This study introduces a contactless blood pressure monitoring approach that combines conventional radar signal processing with novel deep learning architectures. During the preprocessing phase, datasets suitable for synchronization are created by integrating Kalman filtering, multiscale bandpass filters, and a periodic extraction method in the time domain. These data comprise data on chest micro variations, encapsulating a complex array of physiological and biomedical information reflective of cardiac micromotions. The Radar-based Stacked Deformable convolution Network (RSD-Net) integrates channel and spatial self attention mechanisms within a deformable convolutional framework to enhance feature extraction from radar signals. The network architecture systematically employs deformable convolutions for initial deep feature extraction from individual signals. Subsequently, continuous blood pressure estimation is conducted using self attention mechanisms on feature map from single source coupled with multi-feature map channel attention. The performance of model is corroborated via the open-source dataset procured using a non-invasive 24GHz six-port continuous wave radar system. The dataset, encompassing readings from 30 healthy individuals subjected to diverse conditions including rest, the Valsalva maneuver, apnea, and tilt-table examinations. It serves to substantiate the validity and resilience of the proposed method in the non-contact assessment of continuous blood pressure. Evaluation metrics reveal Pearson correlation coefficients of 0.838 for systolic and 0.797 for diastolic blood pressure predictions. The Mean Error (ME) and Standard Deviation (SD) for systolic and diastolic blood pressure measurements are -0.32 ±6.14mmHg and -0.20 ±5.50mmHg, respectively. The ablation study assesses the contribution of different structural components of the RSD-Net, validating their significance in the overall of model performance.

Research on Bearing Surface Scratch Detection Based on Improved YOLOV5

Bearings are crucial components of machinery and equipment, and it is essential to inspect them thoroughly to ensure a high pass rate. Currently, bearing scratch detection is primarily carried out manually, which cannot meet industrial demands. This study presents research on the detection of bearing surface scratches. An improved YOLOV5 network, named YOLOV5-CDG, is proposed for detecting bearing surface defects using scratch images as targets. The YOLOV5-CDG model is based on the YOLOV5 network model with the addition of a Coordinate Attention (CA) mechanism module, fusion of Deformable Convolutional Networks (DCNs), and a combination with the GhostNet lightweight network. To achieve bearing surface scratch detection, a machine vision-based bearing surface scratch sensor system is established, and a self-made bearing surface scratch dataset is produced as the basis. The scratch detection final Average Precision (AP) value is 97%, which is 3.4% higher than that of YOLOV5. Additionally, the model has an accuracy of 99.46% for detecting defective and qualified products. The average detection time per image is 263.4 ms on the CPU device and 12.2 ms on the GPU device, demonstrating excellent performance in terms of both speed and accuracy. Furthermore, this study analyzes and compares the detection results of various models, demonstrating that the proposed method satisfies the requirements for detecting scratches on bearing surfaces in industrial settings.

A bearing surface defect detection method based on multi-attention mechanism Yolov8

Surface defects in bearings not only affect the appearance but also impact the service life and performance. Therefore, it is imperative for bearing manufacturers to conduct quality inspections before bearings leave the factory. However, traditional visual inspection methods exhibit shortcomings such as high omission rates, insufficient feature fusion and oversized models when dealing with multiple target defects in bearings. To address these challenges, this paper proposes a surface defect detection method for bearings based on an improved Yolov8 algorithm (G-Yolov8). Firstly, a C3Ghost convolutional module based on the Ghost module is constructed in YOLOv8 to simplify model computational costs. Secondly, a global attention mechanism module is designed at the end of the backbone network to increase sensitivity to implicit small target area features and optimize feature extraction efficiency. Subsequently, a deep deformable convolution feature pyramid network is constructed by introducing the deformable convolutional networks version 2 (DCNv2) and the lightweight content-aware reassembly of features upsampling operator to reduce sampling information loss and improve the fusion of multi-scale target defects. Finally, different attention mechanisms are embedded in the detection network to construct a multi-attention detection head to replace the decoupled head, refining classification and localization tasks, reducing feature confusion, and improving the model’s detection accuracy. Experimental results demonstrate that the improved algorithm achieves a 3.5% increase in mean average precision on a self-made small-scale train bearing surface defect dataset, with a 17.3% reduction in model size. This improvement not only enhances accuracy but also addresses the requirement for lightweight deployment in subsequent stages.

Fire Smoke Target Detection Incorporating PBCA

Background: Fire incidents occur in complex scenarios, where the dynamic positions and varying scales of flames and smoke pose challenges for fire detection. To improve the stability, localization accuracy, and detection precision of small targets in fire detection, a fused PBCA method for fire and smoke object detection has been proposed in this paper, called FS-YOLOv8. Background: Fire incidents occur in complex scenarios, where the dynamic positions and varying scales of flames and smoke pose challenges for fire detection. To improve the stability, localization accuracy, and detection precision of small targets in fire detection, a fused PBCA method for fire and smoke object detection has been proposed in this paper, called FS-YOLOv8. Objective: The objective of this approach was to improve the detection accuracy of flames and smoke, enhance the robustness of the system, and strengthen the feature representation capability. It aimed to optimize the contribution of feature maps at different scales, allowing the network to capture inter-channel correlations while preserving precise localization information of the targets. Furthermore, it aimed to enhance the learning ability of small-scale flame and smoke objects. Method: Firstly, DCN (Deformable Convolutional Network) was integrated into the CSPDarknet backbone network to extract features from flame and smoke images. Subsequently, a module called PBCA was designed by combining BiFPN (Bidirectional Feature Pyramid Network) and coordinate attention. Finally, a small object detection layer, YOLO HEAD-4, was constructed. Results: The experimental results of our proposed FS-YOLOv8 method on a self-made dataset demonstrated improved detection accuracy compared to other conventional methods. Therefore, the FS-YOLOv8 method effectively enhanced the performance of object detection in fire and smoke scenarios. Conclusion: The FS-YOLOv8 method has been found to effectively improve the performance of object detection in fire and smoke scenarios, enhance the robustness of the system, strengthen the feature representation capability, and amplify the learning ability of small-scale flame and smoke objects. other: NO

An Integrated Gather-and-Distribute Mechanism and Attention-Enhanced Deformable Convolution Model for Pig Behavior Recognition.

The behavior of pigs is intricately tied to their health status, highlighting the critical importance of accurately recognizing pig behavior, particularly abnormal behavior, for effective health monitoring and management. This study addresses the challenge of accommodating frequent non-rigid deformations in pig behavior using deformable convolutional networks (DCN) to extract more comprehensive features by incorporating offsets during training. To overcome the inherent limitations of traditional DCN offset weight calculations, the study introduces the multi-path coordinate attention (MPCA) mechanism to enhance the optimization of the DCN offset weight calculation within the designed DCN-MPCA module, further integrated into the cross-scale cross-feature (C2f) module of the backbone network. This optimized C2f-DM module significantly enhances feature extraction capabilities. Additionally, a gather-and-distribute (GD) mechanism is employed in the neck to improve non-adjacent layer feature fusion in the YOLOv8 network. Consequently, the novel DM-GD-YOLO model proposed in this study is evaluated on a self-built dataset comprising 11,999 images obtained from an online monitoring platform focusing on pigs aged between 70 and 150 days. The results show that DM-GD-YOLO can simultaneously recognize four common behaviors and three abnormal behaviors, achieving a precision of 88.2%, recall of 92.2%, and mean average precision (mAP) of 95.3% with 6.0MB Parameters and 10.0G FLOPs. Overall, the model outperforms popular models such as Faster R-CNN, EfficientDet, YOLOv7, and YOLOv8 in monitoring pens with about 30 pigs, providing technical support for the intelligent management and welfare-focused breeding of pigs while advancing the transformation and modernization of the pig industry.

Radar Signal Classification with Multi-Frequency Multi-Scale Deformable Convolutional Networks and Attention Mechanisms

Radar Signal Classification with Multi-Frequency Multi-Scale Deformable Convolutional Networks and Attention Mechanisms

Series arc fault detection method based on a residual deformable convolutional network for complex branch circuit

Series arc fault detection method based on a residual deformable convolutional network for complex branch circuit

Analysis of interactive impact and student behavior of teaching online courses based on gamified learning

The potential of gamified learning as an emerging force for educational change has been widely recognized, to address the design deficiencies in the automatic recognition methods in traditional gamified learning models and the low accuracy of learning behavior recognition. Based on the improved gamified learning model, this paper jointly proposes an optimal design and recognition model of learning mode based on a deformable convolutional type network. Based on the gamified machine learning theory and interactive feedback theory, it comprehensively analyzes the procedural improvement of the gamified interactive intelligence model to provide a theoretical and practical basis for carrying out the analysis of the interactive impact and student behavior of teaching online courses based on gamified learning. The research results show that: (1) with the increase of the number of gamified learning samples, the value of iterative loss function decreases, the accuracy of recognition improves, and gradually converges and tends to be stable when the number of training times is 500; the 800 training samples setting can fully meet the network training requirements. (2) The deformable convolutional neural learning network constructed with the proposed joint algorithm reduces the network error during the training process and introduces the radical change function to improve the data processing capability. This improved gamified learning model is not only superior in recognition accuracy but also shows great advantages in recognition time.

Motion sensitive network for action recognition in control and decision-making of autonomous systems.

Spatial-temporal modeling is crucial for action recognition in videos within the field of artificial intelligence. However, robustly extracting motion information remains a primary challenge due to temporal deformations of appearances and variations in motion frequencies between different actions. In order to address these issues, we propose an innovative and effective method called the Motion Sensitive Network (MSN), incorporating the theories of artificial neural networks and key concepts of autonomous system control and decision-making. Specifically, we employ an approach known as Spatial-Temporal Pyramid Motion Extraction (STP-ME) module, adjusting convolution kernel sizes and time intervals synchronously to gather motion information at different temporal scales, aligning with the learning and prediction characteristics of artificial neural networks. Additionally, we introduce a new module called Variable Scale Motion Excitation (DS-ME), utilizing a differential model to capture motion information in resonance with the flexibility of autonomous system control. Particularly, we employ a multi-scale deformable convolutional network to alter the motion scale of the target object before computing temporal differences across consecutive frames, providing theoretical support for the flexibility of autonomous systems. Temporal modeling is a crucial step in understanding environmental changes and actions within autonomous systems, and MSN, by integrating the advantages of Artificial Neural Networks (ANN) in this task, provides an effective framework for the future utilization of artificial neural networks in autonomous systems. We evaluate our proposed method on three challenging action recognition datasets (Kinetics-400, Something-Something V1, and Something-Something V2). The results indicate an improvement in accuracy ranging from 1.1% to 2.2% on the test set. When compared with state-of-the-art (SOTA) methods, the proposed approach achieves a maximum performance of 89.90%. In ablation experiments, the performance gain of this module also shows an increase ranging from 2% to 5.3%. The introduced Motion Sensitive Network (MSN) demonstrates significant potential in various challenging scenarios, providing an initial exploration into integrating artificial neural networks into the domain of autonomous systems.

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.

Damage identification of wind turbine blades based on deep learning and ultrasonic testing

ABSTRACT Ultrasonic testing (UT) is an effective method for detecting internal damage in wind turbine blades. However, manual interpretation is time-consuming and subjective. To automate UT in the wind turbine industry, an image detection model based on deep learning called UCD-YOLO (Ultrasonic C-scan image Detection You Only Look Once) is proposed to detect internal damage such as stratified and lack of glue in wind turbine blades. In order to enhance the feature extraction ability under complex damage forms, the use of deformable convolutional networks and context augmentation module are proposed. Designing a lightweight cross stage partial spatial pyramid pool fast (LCSP_SPPF) module, which allows the model to learn more information and improve detection accuracy. The introduction of wise intersection over union (WIoU) improves the convergence speed while reducing the regression error. Using UT devices to collect damage images of wind turbine blades and conducting comprehensive evaluation experiments on the detection performance of the proposed method. Results show that compared to the YOLOv5, UCD-YOLO is not only lighter but also achieves a 7.5% increase in mean average precision (mAP50). And compared with other detection methods, further verifying that the proposed method can quickly and effectively detect wind turbine blade internal damage, improving power generation efficiency.

Dual contrastive attention-guided deformable convolutional network for single image super-resolution

With its powerful ability to model geometric transformations, the deformable convolutional network brings great improvements for single image super-resolution (SISR). Nevertheless, its location-variant sampling method leads to an escalation in spatial variance as the deformable convolutional layers are stacked, consequently resulting in limited performance. Hence, we propose a novel and effective approach called dual contrastive attention-guided deformable convolutional network (DCADCN) for SISR modeling. Specifically, we propose an attention-guided deformable convolutional module with joint inner and external attention mechanisms to fully exploit the correspondences between input and deformation features and preserve spatial characteristics to the extent possible. Additionally, we propose a dual mixed feature extractor consisting of two parallel sub-paths. This design allows for the learning of diverse and complementary spatial features. Furthermore, contrastive learning is applied to further amplify the role of key features and mitigate the interference of noisy features. Extensive experimental results demonstrate that DCADCN is capable of effectively handling classic SISR, SISR with blind noise, and real-world SISR tasks. Moreover, our method achieves comparable or even better performance with lower computational cost compared to state-of-the-art methods.

Vision-Based Multiscale Construction Object Detection under Limited Supervision

Contemporary multiscale construction object detection algorithms rely predominantly on fully-supervised deep learning, requiring arduous and time-consuming labeling process. This paper presents a novel semisupervised multiscale construction objects detection (SS-MCOD) by harnessing nearly infinite unlabeled images along with limited labels, achieving more accurate and robust detection results. SS-MCOD uses a deformable convolutional network (DCN)-based teacher-student joint learning framework. DCN uses deformable advantages to extract and fuse multiscale construction object features. The teacher module generates pseudolabels for construction objects in unlabeled images, while the student module learns the location and classification of construction objects in both labeled images and unlabeled images with pseudolabels. Experimental validation using commonly used construction datasets demonstrates the accuracy and generalization performance of SS-MCOD. This research can provide insights for other detection tasks with limited labels in the construction domain.

A hyperspectral image classification method based on feature enhancement and a hybrid deformable convolution network

ABSTRACT In recent years, some hyperspectral image (HSI) classification methods based on deep models have shown excellent performance. Most deep models receive three-dimensional (3D) block structures as input to extract spectral-spatial features from HSI data. However, the existence of background pixel information in 3D blocks affects the spectral-spatial feature representation ability. In addition, directly performing overall dimension reduction on high-dimensional spectral information lacks analysis of the original data, which weakens the constraint relationship between spectral data and increases the difficulty of feature extraction. Therefore, an HSI classification method based on feature enhancement and hybrid deformable convolution network is proposed. Firstly, a novel 3D block is constructed to enhance spectral-spatial feature representation ability by replacing background pixel information with non-background pixel information. Secondly, based on the analysis results of the original spectral data, this paper proposes a regional dimension reduction mechanism to enhance the constraint relationship between HSI data. Finally, the proposed method is applied to hybrid deformable convolution network for experimental verification. The experimental results of three standard datasets show that the classification effect of the proposed method is better than that of several classification methods, which proves the effectiveness of the proposed method.

YOLOv5s maritime distress target detection method based on swin transformer

AbstractIn recent years, the task of maritime emergency rescue has increased, while the cost of time for traditional methods of search and rescue is pretty long with poor effect subject to the constraints of the complex circumstances around the sea, the effective conditions, and the support capability. This paper applies deep learning and proposes a YOLOv5s‐SwinDS algorithm for target detection in distress at sea. Firstly, the backbone network of the YOLOv5s algorithm is replaced by swin transformer, and a multi‐level feature fusion module is introduced to enhance the feature expression ability for maritime targets. Secondly, deformable convolutional networks v2 (DCNv2) is used instead of traditional convolution to improve the recognition capability for irregular targets when the neck network features are output. Finally, the CIoU loss function is replaced with SIoU to reduce the redundant box effectively while accelerating the convergence and regression of the predicted box. Experimenting on the publicly dataset SeaDronesSee, the , , and of YOLOv5s‐SwinDS model are 87.9%, 75.8%, 79.1% and 42.9%, respectively, which get higher results than the original YOLOv5s model, the YOLOv7 series of models, and the YOLOv8 series of models. The experiments verifies that the algorithm has good performance in detecting maritime distress targets.

SGR: An Improved Point-Based Method for Remote Sensing Object Detection via Dual-Domain Alignment Saliency-Guided RepPoints

With the advancement of deep neural networks, several methods leveraging convolution neural networks (CNNs) have gained prominence in the field of remote sensing object detection. Acquiring accurate feature representations from feature maps is a critical step in CNN-based object detection methods. Previously, region of interest (RoI)-based methods have been widely used, but of late, deformable convolution network (DCN)-based approaches have started receiving considerable attention. A significant challenge in the use of DCN-based methods is the inefficient distribution patterns of sampling points, stemming from a lack of effective and flexible guidance. To address this, our study introduces Saliency-Guided RepPoints (SGR), an innovative framework designed to enhance feature representation quality in remote sensing object detection. SGR employs a dynamic dual-domain alignment (DDA) training strategy to mitigate potential misalignment issues between spatial and feature domains during the learning process. Furthermore, we propose an interpretable visualization method to assess the alignment between feature representation and classification performance in DCN-based methods, providing theoretical analysis and validation for the effectiveness of sampling points. In this study, we assessed the proposed SGR framework through a series of experiments conducted on four varied and rigorous datasets: DOTA, HRSC2016, DIOR-R, and UCAS-AOD, all of which are widely employed in remote sensing object detection. The outcomes of these experiments substantiate the effectiveness of the SGR framework, underscoring its potential to enhance the accuracy of object detection within remote sensing imagery.

Hyperspectral image classification based on channel perception mechanism and hybrid deformable convolution network

Hyperspectral image classification based on channel perception mechanism and hybrid deformable convolution network

Fusing DCN and BBAV for Remote Sensing Image Object Detection

At the oriented object detection in aerial remote sensing images, the perceptual field boundaries of ordinary convolutional kernels are often not parallel to the boundaries of the objects to be detected, affecting the model precision. Therefore, an object detection model (DCN-BBAV) that fuses deformable convolution networks (DCNs) and box boundary-aware vectors (BBAVs) is proposed. Firstly, a BBAV is used as the baseline, replacing the normal convolution kernels in the backbone network with deformable convolution kernels. Then, the spatial attention module (SAM) and channel attention mechanism (CAM) are used to enhance the feature extraction ability for a DCN. Finally, the dot product of the included angles of four adjacent vectors are added to the loss function of the rotation frame parameter, improving the regression precision of the boundary vector. The DCN-BBAV model demonstrates notable performance with a 77.30% mean average precision (mAP) on the DOTA dataset. Additionally, it outperforms other advanced rotating frame object detection methods, achieving impressive results of 90.52% mAP on VOC07 and 96.67% mAP on VOC12 for HRSC2016.

A high-precision jujube disease spot detection based on SSD during the sorting process.

The development of automated grading equipment requires achieving high throughput and precise detection of disease spots on jujubes. However, the current algorithms are inadequate in accomplishing these objectives due to their high density, varying sizes and shapes, and limited location information regarding disease spots on jujubes. This paper proposes a method called JujubeSSD, to boost the precision of identifying disease spots in jujubes based on a single shot multi-box detector (SSD) network. In this study, a diverse dataset comprising disease spots of varied sizes and shapes, varying densities, and multiple location details on jujubes was created through artificial collection and data augmentation. The parameter information obtained from transfer learning into the backbone feature extraction network of the SSD model, which reduced the time of spot detection to 0.14 s. To enhance the learning of target detail features and improve the recognition of weak information, the traditional convolution layer was replaced with deformable convolutional networks (DCNs). Furthermore, to address the challenge of varying sizes and shapes of disease spot regions on jujubes, the path aggregation feature pyramid network (PAFPN) and balanced feature pyramid (BFP) were integrated into the SSD network. Experimental results demonstrate that the mean average precision at the IoU (intersection over union) threshold of 0.5 (mAP@0.5) of JujubeSSD reached 97.1%, representing an improvement of approximately 6.35% compared to the original algorithm. When compared to existing algorithms, such as YOLOv5 and Faster R-CNN, the improvements in mAP@0.5 were 16.84% and 8.61%, respectively. Therefore, the proposed method for detecting jujube disease spot achieves superior performance in jujube surface disease detection and meets the requirements for practical application in agricultural production.

Motion recognition of football players based on deformable convolutional neural networks

Motion recognition of football players based on deformable convolutional neural networks