Search

In this study, we study the tracking of the molten metal region in the dross removal process during metal ingot casting, and propose a real-time tracking method based on adaptive feature selection and weighted histogram. This research is highly significant in metal smelting, as efficient molten metal tracking is crucial for effective dross removal and ensuring the quality of metal ingots. Due to the influence of illumination and temperature in the tracking environment, it is difficult to extract suitable features for tracking molten metal during the metal pouring process using industrial cameras. We transform the images captured by the camera into a multi-scale feature space and select the features with the maximum distinction between the molten metal region and its surrounding background for tracking. Furthermore, we introduce a weighted histogram based on the pixel values of the target region into the mean-shift tracking algorithm to improve tracking accuracy. During the tracking process, the target model updates based on changes in the molten metal region across frames. Experimental tests confirm that this tracking method meets practical requirements, effectively addressing key challenges in molten metal tracking and providing reliable support for the dross removal process. [ABSTRACT FROM AUTHOR]

Magnetic Resonance Fingerprinting (MRF) is a new quantitative technique of Magnetic Resonance Imaging (MRI). Conventionally, MRF requires sequential correlation of the acquired MRF signals with all the signals of (a large sized) MRF dictionary. This is a computationally intensive matching process and is a major challenge in MRF image reconstruction. This paper introduces the use of clustering techniques (to reduce the effective size of MRF dictionary) by splitting MRF dictionary into multiple small sized MRF dictionary components called MRF signal groups. The proposed method has been further optimized for parallel processing to reduce the computation time of MRF pattern matching. A multi-core GPU based parallel framework has been developed that enables the MRF algorithm to process multiple MRF signals simultaneously. Experiments have been performed on human head and phantom datasets. The results show that the proposed method accelerates the conventional MRF (MATLAB based) reconstruction time up to 25× with single-core CPU implementation, 300× with multi- core CPU implementation and 1035× with the proposed multi-core GPU based framework by keeping the SNR of the resulting images in a clinically acceptable range. Furthermore, experimental results show that the memory requirements of MRF dictionary get significantly reduced (due to efficient memory utilization) in the proposed method. • MRF is a new quantitative technique of acquiring and processing MRI data. • Major limitations of the MRF in its clinical utilization include long reconstruction time and significant memory requirement. • A new technique utilizing parallel architecture to reduce computation time as well as effective memory utilization of MRF. • Proposed method introduces clustering techniques to reduce the effective memory requirements of MRF dictionary. • Reduction in the memory requirements reduces the computation complexity, hence reduce the computation time of MRF. [ABSTRACT FROM AUTHOR]

Cooperative autonomous exploration is a challenging task for multi-robot systems, which can cover larger areas in a shorter time or path length. Using multiple mobile robots for cooperative exploration of unknown environments can be more efficient than a single robot, but there are also many difficulties in multi-robot cooperative autonomous exploration. The key to successful multi-robot cooperative autonomous exploration is effective coordination between the robots. This paper designs a multi-robot cooperative autonomous exploration strategy for exploration tasks. Additionally, considering the fact that mobile robots are inevitably subject to failure in harsh conditions, we propose a self-healing cooperative autonomous exploration method that can recover from robot failures.

Localizing stroke may be critical for elucidating underlying pathophysiology. This study proposes a ridge regression–meanshift (RRMS) framework using electromagnetic signals obtained from 16 antennas placed around the anthropomorphic head phantom. A total of 608 intracranial haemorrhage (ICH) and ischemic (IS) signals are collected and evaluated for RRMS, where each type of signal contains two different diameters of stroke phantoms. Subsequently, multiple ridge regression predictors then give the target distances from the antennas and mean shift is used to cluster the predicted stroke location based on these distances. The test results show that the training time and economic cost are significantly reduced as the average prediction time only takes 0.61 s to achieve an accurate result (average position error = 0.74 cm) using a conventional laptop. It has great potential to be used as an auxiliary standard medical method, or rapid diagnosis of stroke patients in underdeveloped areas, due to its rapidity, good deployability, and low hardware cost. [ABSTRACT FROM AUTHOR]

We propose a novel Mean-Shift method for data clustering, called Robust Mean-Shift (RMS). A new update equation for point iterates is proposed, mixing the ones of the standard Mean-Shift (MS) and the Blurring Mean-Shift (BMS). Despite its simplicity, the proposed method has not been studied so far. RMS can be set up in both a kernel-based and a nearest-neighbor (NN)-based fashion. Since the update rule of RMS is closer to BMS, the convergence of point iterates is conjectured based on the Chen’s BMS convergence theorem. Experimental results on synthetic and real datasets show that RMS in several cases outperforms MS and BMS in the clustering task. In addition, RMS exhibits larger attraction basins than MS and BMS for identical parametrization; consequently, its kernel variant requires a lower aperture of the kernel function, and its NN variant a lower number of nearest neighbors compared to MS or BMS, to achieve optimal clustering results. In addition, the NN version of RMS does not need to specify a convergence threshold to stop the iterations, contrarily to the NN-BMS algorithm.

Image novelty detection is a repeating task in computer vision and describes the detection of anomalous images based on a training dataset consisting solely of normal reference data. It has been found that, in particular, neural networks are well-suited for the task. Our approach first transforms the training and test images into ensembles of patches, which enables the assessment of mean-shifts between normal data and outliers. As mean-shifts are only detectable when the outlier ensemble and inlier distribution are spatially separate from each other, a rich feature space, such as a pre-trained neural network, needs to be chosen to represent the extracted patches. For mean-shift estimation, the Hotelling T 2 test is used. The size of the patches turned out to be a crucial hyperparameter that needs additional domain knowledge about the spatial size of the expected anomalies (local vs. global). This also affects model selection and the chosen feature space, as commonly used Convolutional Neural Networks or Vision Image Transformers have very different receptive field sizes. To showcase the state-of-the-art capabilities of our approach, we compare results with classical and deep learning methods on the popular dataset CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario using the MVTec dataset. Because of the inexpensive design, our method can be implemented by a single additional 2D-convolution and pooling layer and allows particularly fast prediction times while being very data-efficient. [ABSTRACT FROM AUTHOR]

A wind turbine working in a harsh environment is prone to generate abnormal data. An efficient algorithm based on the combination of an Isolation Forest (I-Forest) and a mean-shift algorithm is proposed for data cleaning in wind power curves. The I-Forest is used for detecting the local anomalies in each power and wind speed interval after data preprocessing. The contamination of I-Forest can be flexibly adjusted according to the data distribution of the wind turbine data. The remaining stacked data is eliminated by the mean-shift algorithm. To verify the filtering performance of the proposed combined method, five different algorithms, including the quartile and k-means (QK), the quartile and density-based spatial clustering (QD), the mathematical morphology operation (MMO), the fast data cleaning algorithm (FA), and the proposed one, are applied to the wind power curves of a prototype wind farm for comparisons. The numerical results have positively confirmed the reliability of the universal framework provided by the proposed algorithm. [ABSTRACT FROM AUTHOR]

Based on the theory of computer vision, a new method for extracting ore from underground mines is proposed. This is based on a combination of RGB images collected by a color industrial camera and a point cloud generated by a 3D ToF camera. Firstly, the mean-shift algorithm combined with the embedded confidence edge detection algorithm is used to segment the RGB ore image into different regions. Secondly, the effective ore regions are classified into large pieces of ore and ore piles consisting of a number of small pieces of ore. The method applied in the classification process is to embed the confidence into the edge detection algorithm which calculates edge distribution around ore regions. Finally, the RGB camera and the 3D ToF camera are calibrated and the camera matrix transformation of the two cameras is obtained. Point cloud fragments are then extracted according to the cross-calibration result. The geometric properties of the ore point cloud are then analysed in the subsequent procedure. [ABSTRACT FROM AUTHOR]

Polarimetric SAR (PolSAR) image segmentation is a key step in its interpretation. For the targets with time series changes, the single-temporal PolSAR image segmentation algorithm is difficult to provide correct segmentation results for its target recognition, time series analysis and other applications. For this, a new algorithm for multi-temporal PolSAR image segmentation is proposed in this paper. Firstly, the over-segmentation of single-temporal PolSAR images is carried out by the mean-shift algorithm, and the over-segmentation results of single-temporal PolSAR are combined to get the over-segmentation results of multi-temporal PolSAR images. Secondly, the edge detectors are constructed to extract the edge information of single-temporal PolSAR images and fuse them to get the edge fusion results of multi-temporal PolSAR images. Then, the similarity measurement matrix is constructed based on the over-segmentation results and edge fusion results of multi-temporal PolSAR images. Finally, the normalized cut criterion is used to complete the segmentation of multi-temporal PolSAR images. The performance of the proposed algorithm is verified based on three temporal PolSAR images of Radarsat-2, and compared with the segmentation algorithm of single-temporal PolSAR image. Experimental results revealed the following findings: (1) The proposed algorithm effectively realizes the segmentation of multi-temporal PolSAR images, and achieves ideal segmentation results. Moreover, the segmentation details are excellent, and the region consistency is good. The objects which can't be distinguished by the single-temporal PolSAR image segmentation algorithm can be segmented. (2) The segmentation accuracy of the proposed multi-temporal algorithm is up to 86.5%, which is significantly higher than that of the singletemporal PolSAR image segmentation algorithm. In general, the segmentation result of proposed algorithm is closer to the optimal segmentation. The optimal segmentation of farmland parcel objects to meet the needs of agricultural production is realized. This lays a good foundation for the further interpretation of multi-temporal PolSAR image. [ABSTRACT FROM AUTHOR]

Localizing stroke may be critical for elucidating underlying pathophysiology. This study proposes a ridge regression–meanshift (RRMS) framework using electromagnetic signals obtained from 16 antennas placed around the anthropomorphic head phantom. A total of 608 intracranial haemorrhage (ICH) and ischemic (IS) signals are collected and evaluated for RRMS, where each type of signal contains two different diameters of stroke phantoms. Subsequently, multiple ridge regression predictors then give the target distances from the antennas and mean shift is used to cluster the predicted stroke location based on these distances. The test results show that the training time and economic cost are significantly reduced as the average prediction time only takes 0.61 s to achieve an accurate result (average position error = 0.74 cm) using a conventional laptop. It has great potential to be used as an auxiliary standard medical method, or rapid diagnosis of stroke patients in underdeveloped areas, due to its rapidity, good deployability, and low hardware cost.

Image novelty detection is a repeating task in computer vision and describes the detection of anomalous images based on a training dataset consisting solely of normal reference data. It has been found that, in particular, neural networks are well-suited for the task. Our approach first transforms the training and test images into ensembles of patches, which enables the assessment of mean-shifts between normal data and outliers. As mean-shifts are only detectable when the outlier ensemble and inlier distribution are spatially separate from each other, a rich feature space, such as a pre-trained neural network, needs to be chosen to represent the extracted patches. For mean-shift estimation, the Hotelling T2 test is used. The size of the patches turned out to be a crucial hyperparameter that needs additional domain knowledge about the spatial size of the expected anomalies (local vs. global). This also affects model selection and the chosen feature space, as commonly used Convolutional Neural Networks or Vision Image Transformers have very different receptive field sizes. To showcase the state-of-the-art capabilities of our approach, we compare results with classical and deep learning methods on the popular dataset CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario using the MVTec dataset. Because of the inexpensive design, our method can be implemented by a single additional 2D-convolution and pooling layer and allows particularly fast prediction times while being very data-efficient.

Cluster analysis can be used to organize samples and generate ideas regarding the multivariate geochemistry of given dataset. Traditional clustering techniques have the drawbacks of high computational complexity and poor adaptability to big data. Hence, there has recently been much focus on creating better clustering algorithms. Although many clustering algorithms have been applied, and some produce notable clustering results, the performance efficiency of algorithms is often highly dependent on the values the user chooses for the parameters. Currently, density-based spatial clustering of applications with noise clustering (DBSCAN) is widely utilized in image processing, bioinformatics, and social network analysis owing to its ability to detect clusters of various shapes. Even though partitional clustering techniques may be effective when the number of clusters K is known in advance, they cannot implement non-convex clustering and rapidly return to a local optimum. This study proposes the concept of DBSCAN clustering for stream sediment geochemical data. In this respect, the geochemical data collected from Varcheh district, SW Iran, were processed using the clr transformation before applying DBSCAN. Then, PCA was used to minimize the dimension of variables and specify the mineralization-related elements. In the following, one of the PCs connected with mineralization (PC2) was chosen for further analysis. DBSCAB, Mean-shift and Fuzzy K-means algorithms were used to monitor the multi-element geochemical anomalies linked to MVT Pb Zn deposits in the study area. According to Davies-Bouldin and Silhouette as two validation metrics, it can be deduced that the three SCB models are advantageous, however, the model generated by DBSCAN is preferable to the model generated by Mean-shift and Fuzzy K-means. • DBSCAN and Mean-shift extracted hidden geochemical patterns from complex dataset. • The methods did not necessitate a predefined number of clusters. • DBSCAN method demonstrates effectiveness in detecting clusters with various shapes. [ABSTRACT FROM AUTHOR]

A wind turbine working in a harsh environment is prone to generate abnormal data. An efficient algorithm based on the combination of an Isolation Forest (I-Forest) and a mean-shift algorithm is proposed for data cleaning in wind power curves. The I-Forest is used for detecting the local anomalies in each power and wind speed interval after data preprocessing. The contamination of I-Forest can be flexibly adjusted according to the data distribution of the wind turbine data. The remaining stacked data is eliminated by the mean-shift algorithm. To verify the filtering performance of the proposed combined method, five different algorithms, including the quartile and k-means (QK), the quartile and density-based spatial clustering (QD), the mathematical morphology operation (MMO), the fast data cleaning algorithm (FA), and the proposed one, are applied to the wind power curves of a prototype wind farm for comparisons. The numerical results have positively confirmed the reliability of the universal framework provided by the proposed algorithm.

Most of the sequential importance resampling tracking algorithms use arbitrarily high number of particles to achieve better performance, with consequently huge computational costs. This article aims to address the problem of occlusion which arises in visual tracking, using fewer number of particles. To this extent, the mean-shift algorithm is incorporated in the probabilistic filtering framework which allows the smaller particle set to maintain multiple modes of the state probability density function. Occlusion is detected based on correlation coefficient between the reference target and the candidate at filtered location. If occlusion is detected, the transition model for particles is switched to a random walk model which enables gradual outward spread of particles in a larger area. This enhances the probability of recapturing the target post-occlusion, even when it has changed its normal course of motion while being occluded. The likelihood model of the target is built using the combination of both color distribution model and edge orientation histogram features, which represent the target appearance and the target structure, respectively. The algorithm is evaluated on three benchmark computer vision datasets: $\textit {OTB}100$ , $\textit {VOT}18$ and $\textit {TrackingNet}$. The performance is compared with fourteen state-of-the-art tracking algorithms. From the quantitative and qualitative results, it is observed that the proposed scheme works in real-time and also performs significantly better than state-of-the-arts for sequences involving challenges of occlusion and fast motions. [ABSTRACT FROM AUTHOR]

Least squares support vector machine (LSSVM) is a machine learning algorithm based on statistical theory. Its advantages include robustness and calculation simplicity, and it has good performance in the data processing of small samples. The LSSVM model lacks sparsity and is unable to handle large-scale data problem, this article proposes an LSSVM method based on mixture kernel learning and sparse samples. This algorithm reduces the initial training set to a sub-dataset using a sparse selection strategy. It converts the single kernel function in the LSSVM model into a mixed kernel function and optimizes its parameters. The reduced sub-dataset is used for training LSSVM. Finally, a group of datasets in the UCI Machine Learning Repository were used to verify the effectiveness of the proposed algorithm, which is applied to real-world power load data to achieve better fitting and improve the prediction accuracy. [ABSTRACT FROM AUTHOR]

Feature extraction and fault recognition of vibration signals are two important parts of bearing fault diagnosis. In this article, a fault diagnosis method based on teager energy entropy of each wavelet subband and improved fuzzy C-means is proposed. First, bearing vibration signal is decomposed into wavelet packet and normalized teager energy entropy feature matrix is constructed as clustering index. Principal component analysis is applied to the high-dimensional teager energy entropy feature matrix, and the principal components are determined by cumulative contribution rate to construct feature vectors. Then, the mean-shift method is used to search for the high probability density region of principal components so as to determine the cluster number and cluster center. Finally, fuzzy C-means is used to update the clustering center and membership value, and confirm the optimal clustering center and the type of clustering. Through simulated and experimental analysis, the proposed method has two advantages. The feature vector constructed by this method has better specificity than wavelet energy entropy. The initial clustering center of fuzzy C-means is confirmed by the mean-shift method, which can improve the clustering performance of fuzzy C-means and solve the misclassification without preknowing the number of categories. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications 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.)

The unmanned surface vehicle has the characteristics of high maneuverability and flexibility. Object detection and tracking skills are required to improve the ability of unmanned surface vehicle to avoid collisions and detect targets on the surface of the water. Mean-shift algorithm is a classic target tracking algorithm, but it may fail when pixel interference and occlusion occur. This article proposes a tracking algorithm for unmanned surface vehicle based on an improved mean-shift optimization algorithm. The method uses the self-organizing feature map spatial topology to reduce the interference of the background pixels on the target object and predicts the center position of the object when the target is heavily occluded according to the extended Kalman filter. First, a self-organizing feature map model is built to classify pixels in a rectangular frame and the background pixels are extracted. Then, the method optimizes the extended Kalman filter solution process to complete the prediction and correction of the target center position and introduces a similarity function to determine the target occlusion. Finally, numerical analyses based on a ship model sailing experiment are performed with the help of OpenCV library. The experimental results validated that the proposed method significantly reduces the cumulative error in the tracking process and effectively predicts the position of the target between continuous frames when temporary occlusion occurs. The research can be used for target detection and autonomous navigation of unmanned surface vehicle. [ABSTRACT FROM AUTHOR]

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark. [ABSTRACT FROM AUTHOR]

Visual tracking is an art of tracking a moving object over video frames using non-stationary cameras, for which feature descriptors of the target are computed and applied to a motion model. In this paper, SURF is used to compute the feature descriptors and Mean-Shift algorithm as a motion model. M ean - shift algorithm is fundamentally a logical approach to track the object on an image frame where the appearance is described by histograms. Mean-Shift tracking can directly be applied to SURF features but there is a big constraint of availability of an adequate number of feature keypoints for a given object. To get over this limitation, the re-projection technique is implemented in this paper for tracking an object in any video recorded from a mobile or stationary camera. Re-projection, online updates the histogram of object template for every frame by superimposing the feature keypoints from upcoming frames to the first frame. The object can be tracked using SURF descriptors without using any secondary information (color, texture, optical flow, gradient, etc.) regarding the object, which makes it computationally inexpensive to be used in real-time systems. Also, the SURF feature is calculated only for the target object that is to be tracked, this further reduces computational complexity. The simulation results prove the effectiveness of the work. [ABSTRACT FROM AUTHOR]

This paper proposed an algorithm of extracting feature points based on multiple criterions, which aimed to extract boundary feature points and sharp feature points efficiently. Firstly, the algorithm built the point cloud topological structure based on a modified k-d tree approach to search for the K-nearest neighborhood of the sample point. Then, according to each K-nearest neighborhood points, it calculated three feature parameters based on vector angle criteria, kernel density criteria and field power criteria. Finally, according to the three parameters.it obtained feature discriminant parameters and the global fixed threshold. It recognized a point as the feature point when its value of discriminant parameter was bigger than the threshold. The experimental results show that the proposed algorithm can extract boundary points and sharp feature points effectively. [ABSTRACT FROM AUTHOR]

Depth cameras have recently become popular and many vision problems can be better solved with depth information. But, how to integrate depth information into a visual tracker to overcome the challenges such as occlusion and background distraction is still underinvestigated in current literature on visual tracking. In this paper, we investigate a 3-D extension of a classical mean-shift tracker whose greedy gradient ascend strategy is generally considered as unreliable in conventional 2-D tracking. However, through careful study of the physical property of 3-D point clouds, we reveal that objects which may appear to be adjacent on a 2-D image will form distinctive modes in the 3-D probability distribution approximated by kernel density estimation, and finding the nearest mode using 3-D mean-shift can always work in tracking. Based on the understanding of 3-D mean-shift, we propose two important mechanisms to further boost the tracker's robustness: one is to enable the tracker to be aware of potential distractions and make corresponding adjustments to the appearance model; and the other is to enable the tracker to detect and recover from tracking failures caused by total occlusion. The proposed method is both effective and computationally efficient. On a conventional personal computer, it runs at more than 60 FPS without graphical processing unit acceleration. [ABSTRACT FROM AUTHOR]

This research aims to determine the similarities in groups of people to build a film recommender system for users. Users often have difficulty in finding suitable movies due to the increasing amount of movie information. The recommender system is very useful for helping customers choose a preferred movie with the existing features. In this study, the recommender system development is established by using several algorithms to obtain groupings, such as the K-Means algorithm, birch algorithm, mini-batch K-Means algorithm, mean-shift algorithm, affinity propagation algorithm, agglomerative clustering algorithm, and spectral clustering algorithm. We propose methods optimizing K so that each cluster may not significantly increase variance. We are limited to using groupings based on Genre and Tags for movies. This research can discover better methods for evaluating clustering algorithms. To verify the quality of the recommender system, we adopted the mean square error (MSE), such as the Dunn Matrix and Cluster Validity Indices, and social network analysis (SNA), such as Degree Centrality, Closeness Centrality, and Betweenness Centrality. We also used average similarity, computational time, association rule with Apriori algorithm, and clustering performance evaluation as evaluation measures to compare method performance of recommender systems using Silhouette Coefficient, Calinski-Harabaz Index, and Davies−Bouldin Index.