Search

The advancement of new energy vehicles has led to more demanding standards for detecting defects in cylindrical coated lithium batteries. The current research lacks robustness and has low performance. This paper seeks to provide real-time defect identification in cylindrical coated lithium batteries and improve the object detection method of the YOLOv5s model. This paper presents an MGSEC3 module with multi-scale feature extraction and integration of the SENet network in the YOLOv5 Backbone network. This module aims to reduce computational burden and enhance feature extraction efficiency as much as possible. At the same time, the CARAFE operator is utilized to enhance the up-sampling operator in order to reduce the loss of feature information. In addition, enhancements to the loss function enhance both the detection performance and convergence speed. The enhanced YOLOv5s model achieved an average detection rate of 82.4% on the custom cylindrical coated lithium battery dataset, 2.3% higher than the original YOLOv5s. This paper significantly enhances the precision and efficiency of flaw identification in cylindrical coated lithium batteries. [ABSTRACT FROM AUTHOR]

Small object detection has a broad application prospect in image processing of unmanned aerial vehicles, autopilot and remote sensing. However, some difficulties exactly exist in small object detection, such as aggregation, occlusion and insufficient feature extraction, resulting in a great challenge for small object detection. In this paper, we propose an improved algorithm for small object detection to address these issues. By using the spatial pyramid to extract multi-scale spatial features and by applying the multi-scale channel attention to capture the global and local semantic features, the spatial pooling pyramid and multi-scale channel attention module (SPP-MSCAM) is constructed. More importantly, the fusion of the shallower layer with higher resolution and a deeper layer with more semantic information is introduced to the neck structure for improving the sensitivity of small object features. A large number of experiments on the VisDrone2019 dataset and the NWPU VHR-10 dataset show that the proposed method significantly improves the Precision, mAP and mAP50 compared to the YOLOv5 method. Meanwhile, it still preserves a considerable real-time performance. Undoubtedly, the improved network proposed in this paper can effectively alleviate the difficulties of aggregation, occlusion and insufficient feature extraction in small object detection, which would be helpful for its potential applications in the future. [ABSTRACT FROM AUTHOR]

Since surface defect detection is significant to ensure the utility, integrality, and security of productions, and it has become a key issue to control the quality of industrial products, which arouses interests of researchers. However, deploying deep convolutional neural networks (DCNNs) on embedded devices is very difficult due to limited storage space and computational resources. In this paper, an efficient lightweight convolutional neural network (CNN) model is designed for surface defect detection of industrial productions in the perspective of image processing via deep learning. By combining the inverse residual architecture with coordinate attention (CA) mechanism, a coordinate attention mobile (CAM) backbone network is constructed for feature extraction. Then, in order to solve the small object detection problem, the multi-scale strategy is developed by introducing the CA into the cross-layer information flow to improve the quality of feature extraction and augment the representation ability on multi-scale features. Hereafter, the multi-scale feature is integrated to design a novel bidirectional weighted feature pyramid network (BWFPN) to improve the model detection accuracy without increasing much computational burden. From the comparative experimental results on open source datasets, the effectiveness of the developed lightweight CNN is evaluated, and the detection accuracy attains on par with the state-of-the-art (SOTA) model with less parameters and calculation. [ABSTRACT FROM AUTHOR]

Power line insulator defect identification usually suffers from complex backgrounds, small defect target sizes, and inconspicuous defect features. Traditional identification methods based on image processing, image analysis, and pattern classification have many limitations in solving the aforementioned problems. In recent decades, deep learning classification methods have gradually replaced traditional identification methods in the task of power line insulator defect identification. To accurately identify the locations of insulator defects, this paper proposes an insulator defect detection algorithm using an improved lightweight YOLOv4‐tiny network (ILYTN). First, the CBL (Conv‐BN‐LeakyReLU) modules of the backbone network are replaced with MobileViT blocks to enhance the feature extraction capability of the backbone network. Second, coordinate attention (CA) is introduced in the feature fusion part to improve the network's ability to focus on the location of defects. Finally, an EIOU (efficient intersection over union) loss function, instead of the original CIOU loss function, is used so that the convergence speed of the network can be improved. To verify the effectiveness of the proposed algorithm in this paper, the mViT‐yolo algorithm is compared with the mainstream Faster‐RCNN algorithm, SSD algorithm, YOLOv3 algorithm, and YOLOv4‐tiny algorithm. The experimental results show that the algorithm proposed in this paper outperforms all the above algorithms in terms of detection accuracy. Compared with the traditional YOLOv4‐tiny algorithm, the proposed algorithm increases the mean average precision (mAP) by 1.64%, the average precision (AP) of missing insulator defects by 0.32%, and the average precision (AP) of broken insulator defects by 4.96%. © 2023 The Authors. IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Since light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images; that is, the underwater polarization images are fused with intensity images using the deep learning method. To construct a training dataset, we establish an experimental setup to obtain underwater polarization images and perform appropriate transformations to expand the dataset. Next, an end-to-end learning framework based on unsupervised learning and guided by an attention mechanism is constructed for fusing polarization and light intensity images. The loss function and weight parameters are elaborated. The produced dataset is used to train the network under different loss weight parameters, and the fused images are evaluated based on different image evaluation metrics. The results show that the fused underwater images are more detailed. Compared with light intensity images, the information entropy and standard deviation of the proposed method increase by 24.48% and 139%. The image processing results are better than other fusion-based methods. In addition, the improved U-net network structure is used to extract features for image segmentation. The results show that the target segmentation based on the proposed method is feasible under turbid water. The proposed method does not require manual adjustment of weight parameters, has faster operation speed, and has strong robustness and self-adaptability, which is important for research in vision fields, such as ocean detection and underwater target recognition. [ABSTRACT FROM AUTHOR]

With the strengthening of worldwide counter-terrorism initiatives, it is increasingly important to detect contrabands such as controlled knives and flammable materials hidden in clothes and bags. Terahertz (THz) imaging technology is widely used in the field of contraband detection due to its advantages of high imaging speed and strong penetration. However, the terahertz images are of poor qualities and lack texture details. Traditional target detection methods suffer from low detection speeds, misdetection, and omission of contraband. This work pre-processes the original dataset using a variety of image processing methods and validates the effect of these methods on the detection results of YOLOv7. Meanwhile, the lightweight and multi-object detection YOLOv7 (LWMD-YOLOv7) algorithm is proposed. Firstly, to meet the demand of real-time for multi-target detection, we propose the space-to-depth mobile (SPD_Mobile) network as the lightweight feature extraction network. Secondly, the selective attention module large selective kernel (LSK) network is integrated into the output of the multi-scale feature map of the LWMD-YOLOv7 network, which enhances the effect of feature fusion and strengthens the network's attention to salient features. Finally, Distance Intersection over Union (DIOU) is used as the loss function to accelerate the convergence of the model and to have a better localisation effect for small targets. The experimental results show that the YOLOv7 algorithm achieves the best detection results on the terahertz image dataset after the non-local mean filtering process. The LWMD-YOLOv7 algorithm achieves a detection accuracy P of 98.5%, a recall R of 97.5%, and a detection speed of 112.4 FPS, which is 26.9 FPS higher than that of the YOLOv7 base network. The LWMD-YOLOv7 achieves a better balance between detection accuracy and detection speed. It provides a technological reference for the automated detection of contraband in terahertz images. [ABSTRACT FROM AUTHOR]

Local feature information plays an important role in image segmentation, however, the referring image segmentation task is dependent on the text expression, so it is impossible to extract local feature information directly from the original reference image. In order to solve this problem, this paper proposes a specific noun-guided local feature extraction deep neural network model（NgLFNet). The NgLFNet model can automatically mine the local feature information of the object to be segmented according to the key nouns in the input text expression. Specifically, the model first obtains key nouns in text through sentence analysis; secondly, extracting corresponding features through text and image encoders, and using the key nouns to obtain local features of high-interest regions through the multihead attention mechanism; then the multi-modal features are gradually fused to learn; Finally, the decoding and correction module uses the obtained local features to perform more detailed corrections on the prediction mask to obtain the final result. The method in this paper is compared with a variety of mainstream referring segmentation methods and the experimental results show that the proposed method improves the accuracy of text-based instance segmentation task. [ABSTRACT FROM AUTHOR]

The grade of wheat quality depends on the proportion of unsound kernels. Therefore, the rapid detection of unsound wheat kernels is important for wheat rating and evaluation. However, in practice, unsound kernels are hand-picked, which makes the process time-consuming and inefficient. Meanwhile, methods based on traditional image processing cannot divide adherent particles well. To solve the above problems, this paper proposed an unsound wheat kernel recognition algorithm based on an improved mask RCNN. First, we changed the feature pyramid network (FPN) to a bottom-up pyramid network to strengthen the low-level information. Then, an attention mechanism (AM) module was added between the feature extraction network and the pyramid network to improve the detection accuracy for small targets. Finally, the regional proposal network (RPN) was optimized to improve the prediction performance. Experiments showed that the improved mask RCNN algorithm could identify the unsound kernels more quickly and accurately while handling adhesion problems well. The precision and recall were 86% and 91%, respectively, and the inference time on the test set with about 200 targets for each image was 7.83 s. Additionally, we compared the improved model with other existing segmentation models, and experiments showed that our model achieved higher accuracy and performance than the other models, laying the foundation for wheat grading. [ABSTRACT FROM AUTHOR]

In foggy days, the color saturation and contrast of the image are reduced due to factors such as scattering and refraction of light. Aiming at the problems of fog residue and loss of detailed features after processed by the existing dehazing methods, a defogging model network APSA-DehazeNet (Adaptive Pyramid Split Attention-DehazeNet) based on split convolution is proposed in this paper. Firstly, the adaptive multi-scale feature fusion module is used to extract the features of the foggy image, capture the features of different scales, then perform weighted fusion and obtain the shallow features of the image. Secondly, the deep features of the image are further obtained by the split convolutional network (PSANet) based on attention mechanism, and a more thorough dehazing effect is obtained. Finally, to effectively solve the problem of detail loss caused by a single loss, a joint loss function of perceived loss and structural similarity loss is proposed. Compared with other algorithms, experimental results demonstrate that the PSNR and SSIM indexes on the synthetic fog map dataset are improved by an average of 4.7dB and 7.4%, respectively. [ABSTRACT FROM AUTHOR]

Change detection (CD) is a particularly important task in the field of remote sensing image processing. It is of practical importance for people when making decisions about transitional situations on the Earth's surface. The existing CD methods focus on the design of feature extraction network, ignoring the strategy fusion and attention enhancement of the extracted features, which will lead to the problems of incomplete boundary of changed area and missing detection of small targets in the final output change map. To overcome the above problems, we proposed a hierarchical attention residual nested U-Net (HARNU-Net) for remote sensing image CD. First, the backbone network is composed of a Siamese network and nested U-Net. We remold the convolution block in nested U-Net and proposed ACON-Relu residual convolution block (A-R), which reduces the missed detection rate of the backbone network in small change areas. Second, this paper proposed the adjacent feature fusion module (AFFM). Based on the adjacency fusion strategy, the module effectively integrates the details and semantic information of multi-level features, so as to realize the feature complementarity and spatial mutual enhancement between adjacent features. Finally, the hierarchical attention residual module (HARM) is proposed, which locally filters and enhances the features in a more fine-grained space to output a much better change map. Adequate experiments on three challenging benchmark public datasets, CDD, LEVIR-CD and BCDD, show that our method outperforms several other state-of-the-art methods and performs excellent in F1, IOU and visual image quality. [ABSTRACT FROM AUTHOR]

The existing infrared image processing technology mainly relies on the traditional segmentation algorithm, which is not only inefficient, but also has problems such as blurred edges, poor segmentation accuracy, and insufficient extraction of key power equipment features for the infrared image defect segmentation of power equipment. A CS_DeeplabV3+ network for the accurate segmentation of the infrared image defect segmentation of power equipment is designed for the situation of leakage and false detection after segmentation by traditional algorithms. The ASPP module is improved in the encoder part to enable the network to obtain a denser pixel sampling, an improved attention mechanism is introduced to enhance the sensitivity and accuracy of the network for feature extraction, and a semantic segmentation feature enhancement module—the structured feature enhancement module (SFEM)—is introduced in the decoder part to enhance the feature processing to improve the segmentation accuracy. The CS_DeeplabV3+ network is validated using the dataset, and the experimental comparison proves that the improved model has finer contours compared with other models for segmenting infrared images of power equipment defects, and MPA is improved by 5.6% and MIOU is improved by 7.3% compared with the DeeplabV3+ network. [ABSTRACT FROM AUTHOR]

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Underwater fish image processing is one of the key technologies to realize intelligent aquaculture. However, due to the complexity of marine environments, underwater fish images usually have the characteristics of color cast, unbalanced contrast, and blur. Current underwater fish image segmentation methods lack adaptive models and have low segmentation accuracy. Hence, this paper constructs a convolutional neural network-based image segmentation model. This paper first proposes a fish image preprocessing method based on pixel threshold segmentation. To enhance the important features in a fish image, this method uses the minimum Euclidean distance between the original image peaks to redefine the threshold and fuses the thresholded image with the original image. Second, to strengthen the extraction of high-level semantic features of images, the multiscale attentional feature extraction module (MAFEM), which fuses the adaptive channel attention mechanism with the hybrid dilated convolutional pyramid pooling module, is proposed. In this paper, a data set in voc format is produced based on underwater fish images, and this data set is used to verify the model in this paper. The mean intersection over union (MIoU) reaches 92.6%. Compared with other traditional segmentation models, the MIoU, mean pixel accuracy (MPA), and balanced F score (F1-score) of the segmentation results of the model in this paper are increased by averages of 1.84%, 0.785%, and 1.18%, respectively. The experimental results show that this model has a better segmentation effect than other models and provides a theoretical basis for intelligent monitoring of underwater fish body length measurement, weight estimation, and discrimination of growth and health statuses. • An image segmentation model for underwater fish detection in aquaculture environment. • A multiscale attention model presents better extraction effect of fish image features. • A fish image preprocessing method reduces influence of irrelevant information. [ABSTRACT FROM AUTHOR]

The detection of apple yield in complex orchards plays an important role in smart agriculture. Due to the large number of fruit trees in the orchard, improving the speed of apple detection has become one of the challenges of apple yield detection. Additional challenges in the detection of apples in complex orchard environments are vision obstruction by leaves, branches and other fruit, and uneven illumination. The YOLOv5 (You Only Look Once version 5) network structure has thus far been increasingly utilized for fruit recognition, but its detection accuracy and real-time detection speed can be improved. Thus, an upgraded lightweight apple detection method YOLOv5-PRE (YOLOv5 Prediction) is proposed for the rapid detection of apple yield in an orchard environment. The ShuffleNet and the GhostNet lightweight structures were introduced into the YOLOv5-PRE model to reduce the size of the model, and the CA (Coordinate Attention) and CBAM (Convolutional Block Attention Module) attention mechanisms were used to improve the detection accuracy of the algorithm. After applying this algorithm on PC with NVIDIA Quadro P620 GPU, and after comparing the results of the YOLOv5s (You Only Look Once version 5 small) and the YOLOv5-PRE models outputs, the following conclusions were obtained: the average precision of the YOLOv5-PRE model was 94.03%, which is 0.58% higher than YOLOv5s. As for the average detection time of a single image on GPU and CPU, it was 27.0 ms and 172.3 ms, respectively, which is 17.93% and 35.23% higher than YOLOV5s. Added to that, the YOLOv5-PRE model had a missed detection rate of 6.54% when being subject to back-light conditions, and a false detection rate of 4.31% when facing front-light conditions, which are 2.8% and 0.86% higher than YOLOv5s, respectively. Finally, the feature extraction process of the YOLOv5-PRE model was presented in the form of a feature map visualization, which enhances the interpretability of the model. Thus, the YOLOv5-PRE model is more suitable for transplanting into embedded devices and adapts well to different lighting conditions in the orchard, which provides an effective method and a theoretical basis for the rapid detection of apples in the process of rapid detection of apple yield. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have achieved tremendous success in the areas of image processing and computer vision. However, they experience problems with low-frequency information such as semantic and category content and background color, and high-frequency information such as edge and structure. We propose an efficient and accurate deep learning framework called the multi-frequency feature extraction and fusion network (MFFNet) to perform image processing tasks such as deblurring. MFFNet is aided by edge and attention modules to restore high-frequency information and overcomes the multiscale parameter problem and the low-efficiency issue of recurrent architectures. It handles information from multiple paths and extracts features such as edges, colors, positions, and differences. Then, edge detectors and attention modules are aggregated into units to refine and learn knowledge, and efficient multi-learning features are fused into a final perception result. Experimental results indicate that the proposed framework achieves state-of-the-art deblurring performance on benchmark datasets. [ABSTRACT FROM AUTHOR]

Image deraining is a significant problem that ensures the visual quality of images to prompt computer vision systems. However, due to the insufficiency of captured rain streaks features and global information, current image deraining methods often face the issues of rain streaks remaining and image blurring. In this paper, we propose a Multi-receptive Field Aggregation Network (MRFAN) to restore a cleaner rain-free image. Specifically, we construct a Multi-receptive Field Feature Extraction Block (MFEB) to capture rain features with different receptive fields. In MFEB, we design a Self-supervised Block (SSB) and an Aggregation Block (AGB). SSB can make the network adaptively focus on the critical rain features and rain-covered areas. AGB effectively aggregates and redistributes the multi-scale features to help the network simulate rain streaks better. Experiments show that our method achieves better results on both synthetic datasets and real-world rainy images. • Propose a Multi-receptive Field Aggregation Network for single image deraining. • Design a Multi-receptive Field Feature Extraction Block to extract rain features. • Design a Self-supervised Block to integrate the channel and spatial information. • Present an Aggregation Block to fuse multi-features adaptively. [ABSTRACT FROM AUTHOR]

With the rapid development of apparel e-commerce, the variety of apparel is increasing, and it becomes more and more important to classify the apparel according to its collar design. Traditional image processing methods have been difficult to cope with the increasingly complex image backgrounds. To solve this problem, an EMRes-50 classification algorithm is proposed to solve the problem of garment collar image classification, which is designed based on the ECA-ResNet50 model combined with the MC-Loss loss function method. Applying the improved algorithm to the Coller-6 dataset, and the classification accuracy obtained was 73.6%. To further verify the effectiveness of the algorithm, it was applied to the DeepFashion-6 dataset, and the classification accuracy obtained was 86.09%. The experimental results show that the improved model has higher accuracy than the existing CNN model, and the model has better feature extraction ability, which is helpful to solve the problem of the difficulty of fine-grained collar classification and promote the further development of clothing product image classification. [ABSTRACT FROM AUTHOR]

Band selection is a research hotspot in hyperspectral image processing. The continuity of the spectral bands causes the adjacent bands to be highly correlated, and correlation among long-range bands is possible with hundreds of spectral bands. Most existing deep learning methods fail to make full use of the inter-band correlation for band selection. In this paper, a novel dual-graph convolutional network based on band attention and a sparse constraint is proposed for band selection. The network consists of two branches. In the attention branch, band-based dual graphs are constructed to encode the contextual correlation of adjacent bands and the structural correlation of long-range bands into non-Euclidean space. Subsequently, the graph convolution-based band attention mechanism is devised to aggregate the band information in the band-based dual graphs and to generate the attention map for all bands. The band attention map is sparsely constrained and embedded as a mask into the trunk branch. In the trunk branch, sample-based dual graphs are constructed to represent the topological information of the samples in the spectral and spatial domains. Furthermore, a dense graph convolutional network is designed to extract and fuse the spatial–spectral and topological features from the shallow to deep layers for classification. A soft-shifting optimization strategy is implemented by defining a new loss from full bands and selected bands to solve the optimization problem caused by the sparse constraint. In this manner, band selection, feature extraction, and classification can be combined into an end-to-end trainable network. The experimental results on representative hyperspectral image datasets demonstrate the superiority of the proposed method over current state-of-the-art band selection methods. • An improved graph convolutional network is proposed for band selection. • Band-based and sample-based graphs are built with spatial and spectral information. • Design soft-shifting optimization strategy to overcome the optimization problem. • Mini batches of labeled and unlabeled samples are used for graph construction. [ABSTRACT FROM AUTHOR]

Model-based methods utilize atmospheric scattering model to effectively dehaze images but introduce unwanted artifacts. By contrast, recent model-free methods directly restore dehazed images by an end-to-end network and avoid artificial errors. However, their dehazing ability is limited. To address this problem, we combine the advantages of supervised and unsupervised learning and propose a semisupervised knowledge distillation network for single image dehazing named SSKDN. Specially, we respectively build a supervised learning branch and an unsupervised learning branch by four attention-guided feature extraction blocks. In the supervised learning branch, the network is optimized by synthetic images. In the unsupervised learning branch, we dehaze real-world images by dark channel prior and refine dehazing network (RefineDNet) (another dehazing method) and use these dehazed images as fake ground truths to optimize network using prior information and knowledge distillation. Experimental results on synthetic and real-world images demonstrate that the proposed SSKDN performs better than state-of-the-art methods and owns powerful generalization ability. [ABSTRACT FROM AUTHOR]

Optical remote sensing images are widely used in the fields of feature recognition, scene semantic segmentation, and others. However, the quality of remote sensing images is degraded due to the influence of various noises, which seriously affects the practical use of remote sensing images. As remote sensing images have more complex texture features than ordinary images, this will lead to the previous denoising algorithm failing to achieve the desired result. Therefore, we propose a novel remote sensing image denoising network (RSIDNet) based on a deep learning approach, which mainly consists of a multi-scale feature extraction module (MFE), multiple local skip-connected enhanced attention blocks (ECA), a global feature fusion block (GFF), and a noisy image reconstruction block (NR). The combination of these modules greatly improves the model's use of the extracted features and increases the model's denoising capability. Extensive experiments on synthetic Gaussian noise datasets and real noise datasets have shown that RSIDNet achieves satisfactory results. RSIDNet can improve the loss of detail information in denoised images in traditional denoising methods, retaining more of the higher-frequency components, which can have performance improvements for subsequent image processing. [ABSTRACT FROM AUTHOR]

Person reidentification (ReID) is an important issue in the field of image processing and computer vision. Because pedestrian images are often affected by various interference factors, such as occlusion, illumination changes, posture changes, and background changes, extracting discriminative features is an important method to improve the accuracy of ReID. Based on the two existing methods of pose-sensitive embedding and batch feature erasing, a new feature extraction model for person ReID tasks is proposed. The model uses the view information as global features and uses the batch feature erasure method to extract fine-grained features. The mutual complementarity of the two features improves the accuracy of person ReID. In addition, by introducing the attention module, the structure of the complex network becomes concise and the amount of calculation becomes smaller. Through a large number of experiments on three public datasets, it can be seen that the proposed model can effectively deal with the occlusion environment, and it can also obtain competitive results when compared with other state-of-the-art models. [ABSTRACT FROM AUTHOR]