Matching Regions Research Articles

Dynamic digital image correlation method for rolling convective contact

Digital image correlation (DIC) is an increasingly popular and effective non-contact method for measuring full-field displacements and strains of deformable bodies under load. Current DIC methods applied to bodies undergoing large displacements and rotations require a large measurement area for both the reference (i.e., undeformed) image and the deformed images. This can limit the resulting resolution of the displacement and strain fields. To address this issue, we propose a two-stage dynamic DIC method capable of measuring displacements and strains under material convection with high resolution. During the first stage, the reference image is assembled from smaller, high-resolution images of the undeformed object obtained using a spatially-fixed or moving frame. Following capture, each sub-image is rigidly translated and rotated into its appropriate place, thereby producing a full, high-resolution image of the reference body. In stage two, images of the loaded and deformed body, again obtained using a small camera frame with high resolution, are aligned with matching regions of the undeformed composite image using BRISK feature detection before performing DIC. We demonstrate the method on a contact problem whereby an elastomeric roller travels along a rigid surface. In doing so, we obtain fine-resolution measurements of the state of strain of the region of the roller sidewall in contact with the substrate, even as new material convects through the region of interest. We present these measurements as a series of images and videos capturing strain evolution as the roller transitions from static loads to a fully dynamic steady-state, documenting the effectiveness of the method.

A Robust Newton Iteration Method for Mixed-Cell-Height Circuit Legalization Under Technology and Region Constraints

The evolution of advanced technology nodes has prompted a shift toward mixed-cell-height circuit design, while the introduction of technology and fence region constraints further increases the complexity of placement. In this article, we innovatively transform the mixed-cell-height circuit legalization problem into a generalized absolute value equation (GAVE) and propose a novel and effective robust Newton (RN) iteration method to address the challenge of the legalization problem. 1 First, the window-based cell insertion technique is applied to obtain the initial cell row allocation and cell order, and the cells are allocated to the matching region based on the R-tree structure. Then, the legalization problem of cells within the region is transformed into a GAVE, and an RN iteration method is proposed to solve the GAVE. Finally, the maximum displacement cells and technology violation cells are optimized based on a greedy method. Experimental results confirm the efficiency and robustness of the proposed method compared with the state-of-the-art methods.

Breaking through the ‘‘200 nm deep-ultraviolet wall’’ of phase matching region by cation structural modulation

Adjusting birefringence to push the phase-matching (PM) of nonlinear optical (NLO) crystals blue-shifting to the deep-ultraviolet (DUV) region is the inorganic chemists and material scientists' pursuit, while refractive dispersion as an important but easily overlooked optical properties generally brings the unexpected result. Herein, two new Y-based borates, K2YB3O6F2 and Rb2YB3O6F2 have been synthesized by the modulation of A-site cation. In both structures, owing to the structure-directing properties of Y-based polyhedra, the natural advantage of π-conjugated [B3O6] groups was pushed to the greatest extent, theoretical calculations and structure analysis revealed that the coplanar arrangement of [B3O6] groups results in the large birefringence of K2YB3O6F2 and Rb2YB3O6F2. Importantly, the aligned orientation of [B3O6] rings makes Rb2YB3O6F2 possess a strong SHG response of 5.0 × KDP, meanwhile the small dispersion of the refractive indices makes Rb2YB3O6F2 the first borate crystal containing the strong π-conjugation [B3O6] rings with the PM limit breaking through the ‘‘200 nm DUV wall’’. This work indicates that refractive dispersion can be effectively reduced through the cation effect, thereby broadening the PM range.

Augmented reality and optical navigation assisted orbital surgery: a novel integrated workflow

Abstract Objectives Due to the close topographical relationship of functional relevant anatomic structures, limited space and cosmetic aspects orbital surgery will remain a challenging discipline. Therefore, novel technical capabilities are necessary for further surgical progress. We here tested the integration of augmented reality and optical navigation in one workflow for interdisciplinary decision-making, feasibility and intraoperative guidance. Methods High-resolution contrast-enhanced MRI and CT scans were automated and manual-assisted segmented to achieve a detailed three-dimensional (3D) model of the individual patho-anatomical relationships. Augmented reality was used for interdisciplinary preoperative planning and intraoperative intuitive navigation. Mayfield clamp head holder in combination with optical surface matching registration assured navigation assisted microsurgery. Results Combinations of different MRI-sequences and CT-scans were necessary for detailed 3D-modeling. Modeling was time consuming and only viable in the hands of medical, surgical and anatomical trained staff. Augmented reality assured a quick, intuitive interdisciplinary orientation. Intraoperative surface matching registration enabled precise navigation in the orbital space. Conclusions Optical Navigation and microscope integration achieved a straightforward microsurgical workflow and should be implemented regularly. Augmented reality represented a useful tool for preoperative interdisciplinary planning and intraoperative intuitive orientation. It further stated an excellent educational tool.

Hourglass cascaded recurrent stereo matching network

Stereo matching acts a crucial role in computer vision and robotics applications. An accurate cost volume and robust disparity regression method are essential for stereo matching of high accuracy. Following GCNet and PSMNet, constructing 4D cost volume and then using the soft argmin method to regress has been dominated. However, it will encounter many difficulties due to the multi-modal distribution of cost volume. One of the reasons for this multi-modal distribution is the occlusion area which not be possible to find a matching region on the reference image and rarely discussed. In this paper, we propose to use global context information could improve the performance of model in occluded regions. Recently, novel recurrent neural network regression methods are proposed, but most of them regress disparity maps from 3D cost volume. In this paper, we propose the new combinatorial paradigm that combine stacked hourglass modules and recurrent neural networks to further aggregate 4D cost volume and regress disparity respectively. The proposed method can be seamlessly integrated into most stereo matching networks, we improved the accuracy by 45% for PSMNet and 38% for GwcNet in our experiment. Experimental results on Scene Flow, KITTI2012, KITTI2015, and ETH3D datasets show our method is competitive. The code is available at: https://github.com/truman1211/HCRnet.

Reproducibility of Quantitative Double-Echo Steady-State T2 Mapping of Knee Cartilage.

Cartilage T2 can detect joints at risk of developing osteoarthritis. The quantitative double-echo steady state (qDESS) sequence is attractive for knee cartilage T2 mapping because of its acquisition time of under 5 minutes. Understanding the reproducibility errors associated with qDESS T2 is essential to profiling the technical performance of this biomarker. To examine the combined acquisition and segmentation reproducibility of knee cartilage qDESS T2 using two different regional analysis schemes: 1) manual segmentation of subregions loaded during common activities and 2) automatic subregional segmentation. Prospective. 11 uninjured participants (age: 28 ± 3 years; 8 (73%) female). 3-T, qDESS. Test-retest T2 maps were acquired twice on the same day and with a 1-week interval between scans. For each acquisition, average cartilage T2 was calculated in four manually segmented regions encompassing tibiofemoral contact areas during common activities and 12 automatically segmented regions from the deep-learning open-source framework for musculoskeletal MRI analysis (DOSMA) encompassing medial and lateral anterior, central, and posterior tibiofemoral regions. Test-retest T2 values from matching regions were used to evaluate reproducibility. Coefficients of variation (%CV), root-mean-square-average-CV (%RMSA-CV), and intraclass correlation coefficients (ICCs) assessed test-retest T2 reproducibility. The median of test-retest standard deviations was used for T2 precision. Bland-Altman (BA) analyses examined test-retest biases. The smallest detectable difference (SDD) was defined as the BA limit of agreement of largest magnitude. Significance was accepted for P < 0.05. All cartilage regions across both segmentation schemes demonstrated intraday and interday qDESS T2 CVs and RMSA-CVs of ≤5%. T2 ICC values >0.75 were observed in the majority of regions but were more variable in interday tibial comparisons. Test-retest T2 precision was <1.3 msec. The T2 SDD was 3.8 msec. Excellent CV and RMSA-CV reproducibility may suggest that qDESS T2 increases or decreases >5% (3.8 msec) could represent changes to cartilage composition. Stage 2.

Adaptively identify and refine ill-posed regions for accurate stereo matching

Stereo matching cost constrains the consistency between pixel pairs. However, the consistency constraint becomes unreliable in ill-posed regions such as occluded or ambiguous regions of the images, making it difficult to explore hidden correspondences. To address this challenge, we introduce an Error-area Feature Refinement Mechanism (EFR) that supplies context features for ill-posed regions. In EFR, we innovatively obtain the suspected error region according to aggregation perturbations, then a simple Transformer module is designed to synthesize global context and correspondence relation with the identified error mask. To better overcome existing texture overfitting, we put forward a Dual-constraint Cost Volume (DCV) that integrates supplementary constraints. This effectively improves the robustness and diversity of disparity clues, resulting in enhanced details and structural accuracy. Finally, we propose a highly accurate stereo matching network called Error-rectify Feature Guided Stereo Matching Network (ERCNet), which is based on DCV and EFR. We evaluate our model on several benchmark datasets, achieving state-of-the-art performance and demonstrating excellent generalization across datasets. The code is available at https://github.com/dean7liu/ERCNet_2023.

Cross-modal texture transformer for thermal infrared reference-based super-resolution reconstruction

The Reference-based super-resolution(RefSR) methods add a reference image as an extra information source, which effectively resolves the issue of poor reconstruction accuracy resulting from the limited data in single-image super-resolution (SISR). However, the significant differences in thermal infrared and visible imaging mechanisms and image textures make it challenging to accomplish cross-modal texture matching and transfer. To address these issues, we propose a cross-modal texture transfer method for thermal infrared reference super-resolution reconstruction. First, we introduce a pre-trained feature encoder based on contrastive learning, which equips the encoder with the capability to match textures between thermal infrared and visible images. Next, to decrease computational complexity when matching features, we suggest a new sparse feature matching approach that regards areas of the image with abundant textures as suitable matching regions. Ultimately, we introduce a feature mapping module to identify differences in the distribution between infrared and visible images and to remap visible features to the infrared feature distribution. Extensive experiments demonstrate that our method effectively transfers textures from visible reference images to infrared images, resulting in superior visual effects and evaluation metrics.

Alpine Rhododendron population contractions lead to spatial distribution mismatch with their pollinators under climate change

The effect of global climate change on plant–pollinator interaction is not limited to changes in phenology and richness within communities but also includes the spatial mismatch caused by the inconsistency of geographical distribution changes. Subsequently, the pollinator interaction network may be remodeled or even disrupted. In this study, we simulated the suitable habitat niche of 15 Rhododendron species and their eight pollinator species as well as their overlapping versus geographical mismatch under the current and three future climate change scenarios in 2090s, using MaxEnt. Results showed that the suitable habitat of all Rhododendron species would decrease in 2090s. In particular, 10, 8, and 13 Rhododendron–pollinator assemblages would have a reduced spatial match region under the climate change scenarios, mainly due to the contraction of the suitable habitat of Rhododendron species. The results provide novel insights into the response of plant–pollinator interactions to global warming, useful to prioritize conservation actions of alpine plant ecosystems.

Binocular Visual Measurement Method Based on Feature Matching.

To address the issues of low measurement accuracy and unstable results when using binocular cameras to detect objects with sparse surface textures, weak surface textures, occluded surfaces, low-contrast surfaces, and surfaces with intense lighting variations, a three-dimensional measurement method based on an improved feature matching algorithm is proposed. Initially, features are extracted from the left and right images obtained by the binocular camera. The extracted feature points serve as seed points, and a one-dimensional search space is established accurately based on the disparity continuity and epipolar constraints. The optimal search range and seed point quantity are obtained using the particle swarm optimization algorithm. The zero-mean normalized cross-correlation coefficient is employed as a similarity measure function for region growing. Subsequently, the left and right images are matched based on the grayscale information of the feature regions, and seed point matching is performed within each matching region. Finally, the obtained matching pairs are used to calculate the three-dimensional information of the target object using the triangulation formula. The proposed algorithm significantly enhances matching accuracy while reducing algorithm complexity. Experimental results on the Middlebury dataset show an average relative error of 0.75% and an average measurement time of 0.82 s. The error matching rate of the proposed image matching algorithm is 2.02%, and the PSNR is 34 dB. The algorithm improves the measurement accuracy for objects with sparse or weak textures, demonstrating robustness against brightness variations and noise interference.

Automatic image registration on intraoperative CBCT compared to Surface Matching registration on preoperative CT for spinal navigation: accuracy and workflow

IntroductionSpinal navigation solutions have been slower to develop compared to cranial ones. To facilitate greater adoption and use of spinal navigation, the relatively cumbersome registration processes need to be improved upon. This study aims to validate a new solution for automatic image registration and compare it to a traditional Surface Matching method.MethodAdult patients undergoing spinal surgery requiring navigation were enrolled after providing consent. A registration matrix—Universal AIR (= Automatic Image Registration)—was placed in the surgical field and used for automatic registration based on intraoperative 3D imaging. A standard Surface Matching method was used for comparison. Accuracy measurements were obtained by comparing planned and acquired coordinates on the vertebrae.ResultsThirty-nine patients with 42 datasets were included. The mean accuracy of Universal AIR registration was 1.20 ± 0.42 mm, while the mean accuracy of Surface Matching registration was 1.94 ± 0.64 mm. Universal AIR registration was non-inferior to Surface Matching registration. Post hoc analysis showed a significantly greater accuracy for Universal AIR registration. In Surface Matching, but not automatic registration, user-related errors such as incorrect identification of the vertebral level were seen.ConclusionAutomatic image registration for spinal navigation using Universal AIR and intraoperative 3D imaging provided improved accuracy compared to Surface Matching registration. In addition, it minimizes user errors and offers a standardized workflow, making it a reliable registration method for navigated spinal procedures.

Directional region-based feature point matching algorithm based on SURF.

Feature point matching is one of the fundamental tasks in binocular vision. It directly affects the accuracy and quality of 3D reconstruction. This study proposes a directional region-based feature point matching algorithm based on the SURF algorithm to improve the accuracy of feature point matching. First, same-name points are selected as the matching reference points in the left and right images. Then, the SURF algorithm is used to extract feature points and construct the SURF feature point descriptors. During the matching process, the location relationship between the query feature point and the reference point in the left image is directed to determine the corresponding matching region in the right image. Then, the matching is completed within this region based on Euclidean distance. Finally, the grid-based motion statistics algorithm is used to eliminate mismatches. Experimental results show that the proposed algorithm can substantially improve the matching accuracy and the number of valid matched points, particularly in the presence of a large amount of noise and interference. It also exhibits good robustness and stability.

Unified and Real-Time Image Geo-Localization via Fine-Grained Overlap Estimation.

Image geo-localization aims to locate a query image from source platform (e.g., drones, street vehicle) by matching it with Geo-tagged reference images from the target platforms (e.g., different satellites). Achieving cross-modal or cross-view real-time (>30fps) image localization with the guaranteed accuracy in a unified framework remains a challenge due to the huge differences in modalities and views between the two platforms. In order to solve this problem, a novel fine-grained overlap estimation based image geo-localization method is proposed in this paper, the core of which is to estimate the salient and subtle overlapping regions in image pairs to ensure correct matching. Specifically, the high-level semantic features of input images are extracted by a deep convolutional neural network. Then, a novel overlap scanning module (OSM) is presented to mine the long-range spatial and channel dependencies of semantic features in various subspaces, thereby identifying fine-grained overlapping regions. Finally, we adopt the triplet ranking loss to guide the proposed network optimization so that the matching regions are as close as possible and the most mismatched regions are as far away as possible. To demonstrate the effectiveness of our FOENet, comprehensive experiments are conducted on three cross-view benchmarks and one cross-modal benchmark. Our FOENet yields better performance in various metrics and the recall accuracy at top 1 (R@1) is significantly improved, with a maximum improvement of 70.6%. In addition, the proposed model runs fast on a single RTX 6000, reaching real-time inference speed on all datasets, with the fastest being 82.3 FPS.

Design of a High Speed 360-degree Panoramic Video Acquisition System Based on FPGA and USB 3.0

This paper presents a FPGA-based hardware architecture for capturing real-time panoramic images and the parallel implementation of an image stitching algorithm based on the scale-invariant feature transform (SIFT) features. First, the system transfers the images captured by five CMOS sensors to the designed FPGA board through the FMC adapter plate. Then, the system employs the FPGA-based parallel computing to extract the SIFT features and detect the best matching region and points for image registration. Finally, in order to obtain the panoramic image with smooth changes at the junctions, images of the adjacent images are fused. Using the designed FPGA platform makes it possible to extract the SIFT and stitch the images in real-time, which is not realized in most panoramic imaging systems. The panoramic system, developed using the Xilinx Zynq®-7000 all programmable SOC, can capture video of 5*640*480 images at the speed of 60 fps. To enable high-speed image transfer from the imaging system to the host computer, the USB3.0 interface with the transmission speed of 359MB/s has been developed. The real-time efficiency of the parallel system will be demonstrated by the simulations and experiments.

Partition Based Algorithms for Rearrangement Distances with Flexible Intergenic Regions.

Genome Rearrangement distance problems are used in Computational Biology to estimate the evolutionary distance between genomes. These problems consist of minimizing the number of rearrangement events necessary to transform one genome into another. Two commonly used rearrangement events are reversal and transposition. The first studied problems ignored nucleotides outside genes (called intergenic regions), or assumed that genomes have a single copy of each gene. Recent works made advancements in more general problems considering the number of nucleotides in intergenic regions, and replicated genes. Nevertheless, genomes tend to have wildly different quantities of nucleotides on their intergenic regions, which poses a problem when comparing these regions exactly. To overcome this limitation, our work considers some flexibility when matching intergenic regions that do not have the same number of nucleotides. We propose new problems seeking the minimum number of reversals, or reversals and transpositions, necessary to transform one genome into another, while considering flexible intergenic region information. We show approximations for these problems by exploring their relationship with the Signed Minimum Common Flexible Intergenic String Partition problem. We also present different heuristics for the partition problem, and conduct experimental tests on simulated genomes to assess the performance of our algorithms.

A ROI-based quantitative pipeline for 18F-FDG PET metabolism and pCASL perfusion joint analysis: Validation of the 18F-FDG PET line

In Mild Cognitive Impairment (MCI), the study of brain metabolism, provided by 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) can be integrated with brain perfusion through pseudo-Continuous Arterial Spin Labeling Magnetic Resonance sequences (MR pCASL). Cortical hypometabolism identification generally relies on wide control group datasets; pCASL control groups are instead not publicly available yet, due to lack of standardization in the acquisition parameters. This study presents a quantitative pipeline to be applied to PET and pCASL data to coherently analyze metabolism and perfusion inside 16 matching cortical regions of interest (ROIs) derived from the AAL3 atlas. The PET line is tuned on 36 MCI patients and 107 healthy control subjects, to agree in identifying hypometabolic regions with clinical reference methods (visual analysis supported by a vendor tool and Statistical Parametric Mapping, SPM, with two parametrizations here identified as SPM-A and SPM-B). The analysis was conducted for each ROI separately. The proposed PET analysis pipeline obtained accuracy 78 % and Cohen's к 60 % vs visual analysis, accuracy 79 % and Cohen's к 58 % vs SPM-A, accuracy 77 % and Cohen's к 54 % vs SPM-B. Cohen's к resulted not significantly different from SPM-A and SPM-B Cohen's к when assuming visual analysis as reference method (p-value 0.61 and 0.31 respectively). Considering SPM-A as reference method, Cohen's к is not significantly different from SPM-B Cohen's к as well (p-value = 1.00). The complete PET-pCASL pipeline was then preliminarily applied on 5 MCI patients and metabolism-perfusion regional correlations were assessed. The proposed approach can be considered as a promising tool for PET-pCASL joint analyses in MCI, even in the absence of a pCASL control group, to perform metabolism-perfusion regional correlation studies, and to assess and compare perfusion in hypometabolic or normo-metabolic areas.

Evaluation of quantitative measurements of tau pathology with semi‐quantitative ratings and age

AbstractBackgroundIt is assumed quantitative digital neuropathology methods will provide more information than semi‐quantitative ratings, but this presumption lacks formal assessment. Here, we compare quantitative, whole‐slide measurements of phosphorylated tau tangles and threads with semi‐quantitative tau pathology ratings. We evaluate whether quantitative measurements provide additional prediction beyond Braak stage for variables associated with tau pathology, examining the association of quantitative tau measurements in high Braak stages with age at death and measures of severity of TDP‐43 and alpha‐synuclein co‐pathologies. We hypothesized that even within the same high Braak stage, quantitative tau measurements would decrease with age at death, as younger patients often require more tau pathology for disease severity comparable to older patients, and increase with higher co‐pathology ratings, since prior work suggests co‐pathologies increase with disease severity.MethodWe scanned 6µm tissue sections stained with phosphorylated tau PHF1 in 14 brain regions from 215 patients with Alzheimer’s Disease continuum neuropathological diagnoses (53% male, age = 74.37 ± 11.51). A machine learning method (Figure 1) generated summary measures of tangle and thread pathology for each slide (Yushkevich et al., 2021, Sadaghiani et al., 2022). Semi‐quantitative tau ratings (0‐3) were also available in nine regions and compared to quantitative measurements in matching regions. In 150 patients with high Braak stages (V/VI), correlation analyses were performed using summary scores averaging semi‐quantitative ratings of TDP‐43 in medial temporal lobe regions (“TDP‐43 severity”), and alpha‐synuclein in commonly affected regions (“alpha‐synuclein severity”).ResultFigure 2 shows high overall agreement between quantitative tau measures and corresponding semi‐quantitative ratings. When evaluating quantitative tau measurements in high Braak stage patients, after Bonferroni correction we found significant negative associations between age and tangles in middle frontal cortex, orbital frontal cortex (OFC), and thalamus, and between age and threads in OFC. We found significant positive association between TDP‐43 severity and tangles in substantia nigra, but no associations with alpha‐synuclein severity (Figure 3).ConclusionQuantitative tau measurements largely agree with established semi‐quantitative ratings. Significant associations of quantitative tau measurements with TDP43 pathology and age were found within high Braak stage patients, suggesting quantitative pathology measurements can offer additional information beyond stage alone in these patients.

Evaluation of quantitative measurements of tau pathology with semi‐quantitative ratings and age

AbstractBackgroundIt is assumed quantitative digital neuropathology methods will provide more information than semi‐quantitative ratings, but this presumption lacks formal assessment. Here, we compare quantitative, whole‐slide measurements of phosphorylated tau tangles and threads with semi‐quantitative tau pathology ratings. We evaluate whether quantitative measurements provide additional prediction beyond Braak stage for variables associated with tau pathology, examining the association of quantitative tau measurements in high Braak stages with age at death and measures of severity of TDP‐43 and alpha‐synuclein co‐pathologies. We hypothesized that even within the same high Braak stage, quantitative tau measurements would decrease with age at death, as younger patients often require more tau pathology for disease severity comparable to older patients, and increase with higher co‐pathology ratings, since prior work suggests co‐pathologies increase with disease severity.MethodWe scanned 6µm tissue sections stained with phosphorylated tau PHF1 in 14 brain regions from 215 patients with Alzheimer’s Disease continuum neuropathological diagnoses (53% male, age = 74.37 ± 11.51). A machine learning method (Figure 1) generated summary measures of tangle and thread pathology for each slide (Yushkevich et al., 2021, Sadaghiani et al., 2022). Semi‐quantitative tau ratings (0‐3) were also available in nine regions and compared to quantitative measurements in matching regions. In 150 patients with high Braak stages (V/VI), correlation analyses were performed using summary scores averaging semi‐quantitative ratings of TDP‐43 in medial temporal lobe regions (“TDP‐43 severity”), and alpha‐synuclein in commonly affected regions (“alpha‐synuclein severity”).ResultFigure 2 shows high overall agreement between quantitative tau measures and corresponding semi‐quantitative ratings. When evaluating quantitative tau measurements in high Braak stage patients, after Bonferroni correction we found significant negative associations between age and tangles in middle frontal cortex, orbital frontal cortex (OFC), and thalamus, and between age and threads in OFC. We found significant positive association between TDP‐43 severity and tangles in substantia nigra, but no associations with alpha‐synuclein severity (Figure 3).ConclusionQuantitative tau measurements largely agree with established semi‐quantitative ratings. Significant associations of quantitative tau measurements with TDP43 pathology and age were found within high Braak stage patients, suggesting quantitative pathology measurements can offer additional information beyond stage alone in these patients.

Vertical nonlinear vibration analysis of cold rolling mill considering structural gap and dynamic rolling force

To reveal the impact of vertical nonlinear vibration on the stabilization of the precision cold rolling system, the vertical nonlinear vibration model with consideration of structural gap and dynamic rolling force has been established. Utilizing the Magnus series method with high accuracy and long-term numerical stabilization, we calculate the vibration response of the cold rolling system and conduct numerical simulations to determine the bifurcation characteristics, maximum Lyapunov exponent, and two-parameter dynamical behavior. The results reveal the parameter regions of bifurcation and chaos that cause the vibration instability of the cold rolling system. It has also been found that the system has the nonlinear phenomenon of transition from period-3 motion to chaotic motion. More importantly, two-parameter matching regions for the cold rolling system performing periodic and chaotic motions are determined. Two-parameter matching solutions for improving and deteriorating the stabilization of the cold rolling system are clarified, and the preferred matching regions for the parameters coupling with the structural gap and dynamic rolling force are revealed. The results reveal the impact of system parameters upon the vertical nonlinear vibration of the cold rolling mill, which can serve as an academic reference for reducing the vibration and enhancing the stabilization of the cold rolling system.

ARCTIC: A knowledge distillation approach via attention-based relation matching and activation region constraint for RGB-to-Infrared videos action recognition

The recognition effect of existing infrared-based action recognition is greatly reduced when clear appearance and texture are required. To address this limitation, the amalgamation of RGB data presents an opportunity to compensate for this deficiency. However, effectively leveraging RGB data to bridge the gap between RGB and infrared modalities poses a significant challenge. In this paper, we propose a knowledge distillation method based on attention relation matching and activation region consistency constraint (ARCTIC) for RGB-to-Infrared action recognition, which guides infrared data for recognition by acquiring the information of RGB data modality. To enhance the precision of knowledge screening across different modalities at various feature levels and ensure accurate information transfer, we constructed attention-based relation matching modules between different feature layers of the teacher and student networks. To minimize the dissimilarity between the two modalities and obtain more advantageous complementary information, we consider the spatial activation region consistency constraint to maintain the consistency between the most salient features of the teacher network and the student network, and employ knowledge distillation loss to favor the selection of accurate predictions while judiciously mitigating the occurrence of erroneous logical outputs. Our experimentation substantiates that the ARCTIC method surpasses the performance of state-of-the-art action recognition techniques across the NTU RGB+D and PKU-MMD datasets.