Multi-scale Convolutional Feature Approximation for Defocus Blur Detection

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images is still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network(FCN) as our network structure. In each level of the decoder, we design the Selective Reception Field Block(SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works. The code is available at: this https URL

We propose a novel approach for detecting two kinds of partial blur, defocus and motion blur, by training a deep convolutional neural network. Existing blur detection methods concentrate on designing low‐level features, but those features have difficulty in detecting blur in homogeneous regions without enough textures or edges. To handle such regions, we propose a deep encoder‐decoder network with long residual skip‐connections and multi‐scale reconstruction loss functions to exploit high‐level contextual features as well as low‐level structural features. Another difficulty in partial blur detection is that there are no available datasets with images having both defocus and motion blur together, as most existing approaches concentrate only on either defocus or motion blur. To resolve this issue, we construct a synthetic dataset that consists of complex scenes with both types of blur. Experimental results show that our approach effectively detects and classifies blur, outperforming other state‐of‐the‐art methods. Our method can be used for various applications, such as photo editing, blur magnification, and deblurring.

Blur detection is aimed at estimating the probability of each pixel being blurred or non-blurred in an image affected by motion or defocus blur. This task has gained considerable attention due to its promising application fields in computer vision. Accurate differentiation of anomalous regions (including the sharp but homogeneous regions and pseudo-sharp backgrounds) and motion-blurred regions are main challenges in blur detection, in which both conventional and recently developed blur detection methods have limited performance and low time efficiency. To address these issues, this paper develops an accurate and fast blur detection method for both motion and defocus blur using a new end-to-end deep neural network. First, a novel multi-input multi-loss encoder-decoder network (M-shaped) is proposed to learn rich hierarchical representations related to blur. Then, to resolve the problem shows that blur degree is susceptible to scales, we construct a pyramid ensemble model (PM-Net) consisting of different scales of M-shaped subnets and a unified fusion layer. The experiments demonstrate that the proposed PM-Net can accurately handle those challenging scenarios with anomalous regions for both defocus and motion blur. Our method performs better than previous state-of-the-art methods. It achieves the $F_{1}$ -score of 0.893 for only defocus blur and 0.884 for joint motion and defocus blur, both of which significantly surpass previous methods on the benchmark BDD dataset. We also test our PM-Net on another public CDD dataset composed of challenging defocused images. The proposed method also outperforms other published methods with an $F_{1}$ -score of 0.885. In addition, our proposed method is hundreds of times faster (millisecond) than other state-of-the-art methods (second). Moreover, our experiments also demonstrate that the PM-Net is robust to noise and has a good generalization property.

Defocus blur detection using novel local directional mean patterns (LDMP) and segmentation via KNN matting

To enhance the intelligence of machining processes, accurate recognition of tool wear states has become a key issue in the manufacturing field. However, due to the non-stationary and high-dimensional nature of cutting signals, traditional methods face significant challenges in feature extraction and state classification. In the context of cutting processes, challenges such as difficulty in identifying tool wear states and the complex composition of monitoring information features persist. To address these issues, this paper proposes a deep learning model that integrates multi-scale feature extraction with a residual connection network (Multi-scale ResNet). Specifically, cutting vibration signals are processes using continuous wavelet transform (CWT), which enables the conversion of time-frequency information into images. The proposed deep learning model is then used for feature extraction and state identification. The proposed model is validated through cutting experiments conducted on γ -TiAl alloys. Experimental results show that the Multi-scale ResNet model achieves higher recognition accuracy than traditional models such as convolutional neural networks – support vector machines (CNN–SVM), Transformer, and ResNet in the initial and normal wear stages. It effectively mitigates misjudgments associated with initial and normal wear, achieving a prediction accuracy of 93.8 %, a recall rate of 94.2 %, and an F1 score of 94 %. This model offers a novel and effective approach for tool wear state monitoring, contributing to improved cutting processing efficiency and increased intelligence in production.

Cloud detection plays a vital role in remote sensing data preprocessing. Traditional cloud detection algorithms have difficulties in feature extraction and thus produce a poor detection result when processing remote sensing images with uneven cloud distribution and complex surface background. To achieve better detection results, a cloud detection method with multi-scale feature extraction and content-aware reassembly network (MCNet) is proposed. Using pyramid convolution and channel attention mechanisms to enhance the model’s feature extraction capability, MCNet can fully extract the spatial information and channel information of clouds in an image. The content-aware reassembly is used to ensure that sampling on the network can recover enough in-depth semantic information and improve the model cloud detection effect. The experimental results show that the proposed MCNet model has achieved good detection results in cloud detection tasks.

Wind turbine rolling bearings are crucial components for ensuring the reliability and stability of wind power systems. Their failure can lead to significant economic losses and equipment downtime. Therefore, the accurate diagnosis of bearing faults is of great importance. Although existing deep learning fault diagnosis methods have achieved certain results, they still face limitations such as inadequate feature extraction capabilities, insufficient generalization to complex working conditions, and ineffective multi-scale feature capture. To address these issues, this paper proposes an advanced fault diagnosis method named the two-stream feature fusion convolutional neural network (TSFFResNet-Net). Firstly, the proposed method combines the advantages of one-dimensional convolutional neural networks (1D-ResNet) and two-dimensional convolutional neural networks (2D-ResNet). It transforms one-dimensional vibration signals into two-dimensional images through the empirical wavelet transform (EWT) method. Then, parallel convolutional kernels in 1D-ResNet and 2D-ResNet are used to extract multi-scale features, respectively. Next, the Convolutional Block Attention Module (CBAM) is introduced to enhance the network’s ability to capture key features by focusing on important features in specific channels or spatial areas. After feature fusion, CBAM is introduced again to further enhance the effect of feature fusion, ensuring that the features extracted by different network branches can be effectively integrated, ultimately providing more accurate input features for the classification task of the fully connected layer. The experimental results demonstrate that the proposed method outperforms other traditional methods and advanced convolutional neural network models on different datasets. Compared with convolutional neural network models such as LeNet-5, AlexNet, and ResNet, the proposed method achieves a significantly higher accuracy on the test set, with a stable accuracy of over 99%. Compared with other models, it shows better generalization and stability, effectively improving the overall performance of rolling bearing vibration signal fault diagnosis. The method provides an effective solution for the intelligent fault diagnosis of wind turbine rolling bearings.

DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection

Convolutional neural network (CNN) has shown phenomenal results on several image classification applications. The performance of CNN is improved with deeper architectures. However, increasing depth comes with certain drawbacks like overfitting and need for more computational resources. Thus, it is necessary to choose optimal depth for a network. In this work, the empirical relation between model depth, capacity and complexity of data is estimated using proposed extended VGGNET (EVGGNET). The EVGGNET consists of feature extraction and classification network. The feature extraction network is divided into pre-trained and extended sections which extract the significant features. The classification network uses these features to classify input image into one of the categories. The basic idea behind EVGGNET is to extend the pre-trained feature extraction network by adding convolutional layers which help to establish the model capacity relationship. VGGNET is used as a pre-trained feature extraction network. The experiments are performed on benchmark datasets Caltech 101 and Caltech 256. The results show that the accuracy of EVGGNET is almost exponentially proportional to the complexity of data.

This paper proposes a multi-source data fusion algorithm for rail surface defect detection in both camera-based rail inspection images and ultrasound B-scan images. First, we design a rail surface segmentation algorithm based on image bilateral filtering, Sobel edge detection, and rail surface edge detection to extract the rail surface area. Second, we build a camera and ultrasound data fusion (CUFuse) model for rail surface defect detection, including two main networks: multi-source data feature extraction and multi-scale feature fusion networks. The multi-source data feature extraction network consists of two BoTNet 50 networks as feature extraction networks to extract five stages of features in camera-based images and ultrasound B-scan images. The multi-scale feature fusion network consists of five feature fusion modules to fuse the feature information output by the multi-source data feature extraction network. Finally, we use the CUFuse model to detect the rail surface defect dataset, and output five rail surface state types, including Light, Moderate, Severe, Normal, and Joint. The results show that the accuracy of the CUFuse model is 96.97%, which can accomplish the task of rail surface defect detection on railway sites.

In this paper, we present a model of a convolutional neural network for automatic extraction of several features of the rice kernels from a gray image. The system developed convolutional neural network which is consisted of 7 layers and receives a gray image that measures 200 × 200 pixels as its input. Therefore, there are 40000 neurons on the network at the input level. The following layer is convolutional with the set of 6 filters. Next is the subsampling layer with the maximumvalue function. Then, we have one more convolutional layer of 12 filters and the subsampling layer with the maximumvalue function. The final is the fully connected layer of 3 neurons. The convolutional Neural Networks detector developed were able to identify the grain samples at overall average accuracies of 99.52%. The study results have demonstrated the capability and potential of machine vision with well-trained convolutional neural network detector for varietal types identification of rice grain samples. With the comparably high accuracy of classification obtained, a machine vision together with the developed neural network architectures could be used as a tool to achieve better and more objective rice quality evaluation at trading points within the rice marketing system, and it also provide a superior alternative for other research.

A novel ensemble local graph structure based feature extraction network for EEG signal analysis

Deep feature extraction in lifetime prognostics of lithium-ion batteries: Advances, challenges and perspectives

Gait recognition is a distinctive biometric technique that can identify pedestrians by their walking patterns from considerable distances. A critical challenge in gait recognition lies in effectively acquiring discriminative spatial-temporal representations from silhouettes that exhibit invariance to disturbances. In this paper, we present a novel gait recognition network by aggregating features in the spatial-temporal and view domains, which consists of two-path spatial-temporal feature fusion module and view embedding module. Specifically, two-path spatial-temporal feature fusion module firstly utilizes multi-scale feature extraction (MSFE) to enrich the input features with multiple convolution kernels of various sizes. Then, frame-level spatial feature extraction (FLSFE) and multi-scale temporal feature extraction (MSTFE) are parallelly constructed to capture spatial and temporal gait features of different granularities and these features are fused together to obtain muti-scale spatial-temporal features. FLSFE is designed to extract both global and local gait features by employing a specially designed residual operation. Simultaneously, MSTFE is applied to adaptively interact multi-scale temporal features and produce suitable motion representations in temporal domain. Taking into account the view information, we introduce a view embedding module to reduce the impact of differing viewpoints. Through the extensive experimentation over CASIA-B and OU-MVLP datasets, the proposed method has achieved superior performance to the other state-of-the-art gait recognition approaches.

This paper addresses the problem of obtaining a blur-based segmentation map from a single image affected by motion or defocus blur. Since traditional hand-designed priors have fundamental limitations, we utilise deep neural networks to learn features related to blur and enable a pixel-level blur classification. Our approach mitigates the ambiguities present in blur detection task by introducing joint learning of global context and local features into the framework. Specifically, we train two sub-networks to perform the task at global (image) and local (patch) levels. We aggregate the pixel-level probabilities estimated by two networks and feed them to a MRF based framework which returns a refined and dense segmentation-map of the image with respect to blur. We also demonstrate via both qualitative and quantitative evaluation, that our approach performs favorably against state-of-the-art blur detection or segmentation works, and show its utility to applications of automatic image matting and blur magnification.