- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Automatic signal quality check and equipment condition surveillance based on trivalent logic diagnosis theory
摘要： In the field of fault diagnosis, inadequate signals measured for equipment condition monitoring may cause incorrect diagnostic results and reduce the accuracy and reliability of the equipment diagnosis system. This paper proposes a method of signal quality check and equipment condition surveillance based on trivalent logic theory, signal histogram analysis and principal component analysis (PCA), in order to automatically evaluate the quality of measured signals to ensure that the signals are real and valid for the condition diagnosis of equipment, and automatically judge the equipment state for condition surveillance. The novelty of this paper are summarized as: (1) Trivalent logic has been expanded appropriately into the trivalent logic diagnosis theory, so that it can be applied to verify the signal quality in the acquisition process for fault diagnosis and equipment condition surveillance; (2) In order to directly and effectively extract features of a signal following any probability density distribution, the histograms of the signal measured for equipment condition diagnosis is used to substitute time domain symptom parameters which have been generally used in equipment diagnosis technology; (3) PCA is used to integrate the histograms to realize signal quality check and equipment condition surveillance on the basis of the trivalent logic diagnosis theory. By the method proposed in this paper, the moment when the signal for equipment condition diagnosis is relatively stable can be found, and the unfavorable signal can be avoided for ensuring the accuracy and reliability of the equipment condition diagnosis. Simulation signals and real signals measured in various conditions from a blower are respectively used to verify the effectiveness of the proposed method.
关键词： Condition monitoring,Fault diagnosis,Measurement errors,Histograms,Vibration measurement
更新于2025-09-23 15:23:52
-
Quaternion-Based Multiscale Analysis for Feature Extraction of Hyperspectral Images
摘要： This paper proposes a new method called multiscale quaternion Weber local descriptor histogram (MQWLDH) for feature extraction of hyperspectral images (HSIs), which is used to model spatial information based on the corresponding spectral features. The proposed method first transforms spectral data into an orthogonal space using principal component analysis, and extracts the first three principal components (PCs) based on the maximum variance theory. Then construct the MQWLDH to extract spatial features based on those first three PCs. The proposed method uses the algebraic structure of quaternions to unify the process of processing the first three PCs, which reduces the computational cost and the dimensionality of the extracted spatial feature vector. Moreover, the constructed quaternion Weber local descriptor effectively characterizes the variations of each pixel neighborhood and detects the edges of HSIs. To capture more intrinsic spatial information contained in homogeneous regions of different sizes and shapes, multiscale feature histograms are constructed. Finally, a feature fusion framework is proposed to fuse spectral and spatial features, so that spectral information can be fully utilized. The experimental results on three HSI data sets demonstrate that the proposed method provides effective features to different classifiers and achieves excellent classification performance.
关键词： multiscale feature histograms.,principal component analysis (PCA),Feature extraction,quaternion Weber local descriptor (QWLD)
更新于2025-09-23 15:22:29
-
Indoor Scene and Position Recognition Based on Visual Landmarks Obtained from Visual Saliency without Human Effect
摘要： Numerous autonomous robots are used not only for factory automation as labor saving devices, but also for interaction and communication with humans in our daily life. Although superior compatibility for semantic recognition of generic objects provides wide applications in a practical use, it is still a challenging task to create an extraction method that includes robustness and stability against environmental changes. This paper proposes a novel method of scene and position recognition based on visual landmarks (VLs) used for an autonomous mobile robot in an environment living with humans. The proposed method provides a mask image of human regions using histograms of oriented gradients (HOG). The VL features are described with accelerated KAZE (AKAZE) after extracting conspicuous regions obtained using saliency maps (SMs). The experimentally obtained results using leave-one-out cross validation (LOOCV) revealed that recognition accuracy of high-saliency feature points was higher than that of low-saliency feature points. We created our original benchmark datasets using a mobile robot. The recognition accuracy evaluated using LOOCV reveals 49.9% for our method, which is 3.2 percentage points higher than the accuracy of the comparison method without HOG detectors. The analysis of false recognition using a confusion matrix examines false recognition occurring in neighboring zones. This trend is reduced according to zone separations.
关键词： visual landmark,machine learning,saliency maps,semantic position recognition,histograms of oriented gradients
更新于2025-09-19 17:15:36
-
[IEEE 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE) - Shah Alam (2018.7.11-2018.7.12)] 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE) - Face recognition and detection using Random forest and combination of LBP and HOG features
摘要： the effective facial recognition method should perform well in unregulated environments based on video broadcast to satisfy the demands of applications in real-world However, this still remains a big challenge for most current face recognition algorithms that will affect the accuracy of the system. This study was conducted to develop face recognition method based on video broadcast under illumination variation, facial expressions, different pose, orientation, occlusion, nationality variation and motion. Viola-Jones algorithm was applied to improve face detection which is these method have proven to detect the faces in an uncontrolled environment in the real world simply and high accuracy. A combination of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) descriptors was conducted for faces features extraction purpose. These descriptors have proven to be lower computational time. The latest and accurate technique was applied for face classification based on Random Forest classifier (RF). To evaluate the efficiency of the Random Forest classifier, compared it with Support Vector Machine classifiers (SVM) is done with different existing feature extraction methods. Four experiments were implemented on Mediu staff database and excellent results have reported the efficiency of proposed algorithm average recognition accuracy 97.6% The Computer Vision and Image Processing MAT LAB 2016b Toolboxes was used for coding the desired system, dataset based on videos.
关键词： Viola &Jones,Face Recognition,Mediu Staff,Local Binary Pattern (LBP),Histograms of Oriented Gradients (HOG),Random Forest classifier (RF)
更新于2025-09-09 09:28:46
-
A new thermal infrared and visible spectrum images-based pedestrian detection system
摘要： In this paper, we propose a hybrid system for pedestrian detection, in which both thermal and visible images of the same scene are used. The proposed method is achieved in two basic steps: (1) Hypotheses generation (HG) where the locations of possible pedestrians in an image are determined and (2) hypotheses verification (HV), where tests are done to check the presence of pedestrians in the generated hypotheses. HG step segments the thermal image using a modified version of OTSU thresholding technique. The segmentation results are mapped into the corresponding visible image to obtain the regions of interests (possible pedestrians). A post-processing is done on the resulting regions of interests to keep only significant ones. HV is performed using random forest as classifier and a color-based histogram of oriented gradients (HOG) together with the histograms of oriented optical flow (HOOF) as features. The proposed approach has been tested on OSU Color-Thermal, INO Video Analytics and LITIV data sets and the results justify its effectiveness.
关键词： Thermal images,Random forests,Local binary pattern (LBP),Pedestrian detection,Histograms of oriented optical flow (HOOF),Support vector machines (SVMs),Visible images,Histogram of oriented gradients (HOG)
更新于2025-09-04 15:30:14
-
A stopping criterion to halt iterations at the Richardson-Lucy deconvolution of radiographic images
摘要： Radiographic images, as any experimentally acquired ones, are affected by spoiling agents which degrade their final quality. The degradation caused by agents of systematic character, can be reduced by some kind of treatment such as an iterative deconvolution. This approach requires two parameters, namely the system resolution and the best number of iterations in order to achieve the best final image. This work proposes a novel procedure to estimate the best number of iterations, which replaces the cumbersome visual inspection by a comparison of numbers. These numbers are deduced from the image histograms, taking into account the global difference G between them for two subsequent iterations. The developed algorithm, including a Richardson-Lucy deconvolution procedure has been embodied into a Fortran program capable to plot the 1st derivative of G as the processing progresses and to stop it automatically when this derivative - within the data dispersion - reaches zero. The radiograph of a specially chosen object acquired with thermal neutrons from the Argonauta research reactor at Instituto de Engenharia Nuclear - CNEN, Rio de Janeiro, Brazil, have undergone this treatment with fair results.
关键词： Richardson-Lucy deconvolution,iterative process,image histograms,radiographic images,stopping criterion
更新于2025-09-04 15:30:14