Research on the Pedestrian Re-Identification Method Based on Local Features and Gait Energy Images

The appearance of pedestrians can vary greatly from image to image,and different pedestrians may look similar in a given image.Such similarities and variabilities in the appearance and clothing of individuals make the task of pedestrian re-identification very challenging.Here,a pedestrian re-identification method based on the fusion of local features and gait energy image(GEI)features is proposed.In this method,the human body is divided into four regions according to joint points.The color and texture of each region of the human body are extracted as local features,and GEI features of the pedestrian gait are also obtained.These features are then fused with the local and GEI features of the person.Independent distance measure learning using the cross-view quadratic discriminant analysis(XQDA)method is used to obtain the similarity of the metric function of the image pairs,and the final similarity is acquired by weight matching.Evaluation of experimental results by cumulative matching characteristic(CMC)curves reveals that,after fusion of local and GEI features,the pedestrian re-identification effect is improved compared with existing methods and is notably better than the recognition rate of pedestrian re-identification with a single feature.

An Image Edge Detection Algorithm Based on Multi-Feature Fusion

Edge detection is one of the core steps of image processing and computer vision.Accurate and fine image edge will make further target detection and semantic segmentation more effective.Holistically-Nested edge detection(HED)edge detection network has been proved to be a deep-learning network with better performance for edge detection.However,it is found that when the HED network is used in overlapping complex multi-edge scenarios for automatic object identification.There will be detected edge incomplete,not smooth and other problems.To solve these problems,an image edge detection algorithm based on improved HED and feature fusion is proposed.On the one hand,features are extracted using the improved HED network:the HED convolution layer is improved.The residual variable convolution block is used to replace the normal convolution enhancement model to extract features from edges of different sizes and shapes.Meanwhile,the empty convolution is used to replace the original pooling layer to expand the receptive field and retain more global information to obtain comprehensive feature information.On the other hand,edges are extracted using Otsu algorithm:Otsu-Canny algorithm is used to adaptively adjust the threshold value in the global scene to achieve the edge detection under the optimal threshold value.Finally,the edge extracted by improved HED network and Otsu-Canny algorithm is fused to obtain the final edge.Experimental results show that on the Berkeley University Data Set(BSDS500)the optimal data set size(ODS)F-measure of the proposed algorithm is 0.793;the average precision(AP)of the algorithm is 0.849;detection speed can reach more than 25 frames per second(FPS),which confirms the effectiveness of the proposed method.

Underwater Terrain Image Stitching Based on Spatial Gradient Feature Block

At present,underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system.However,the processed underwater terrain images have inconspicuous and few feature points.In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed,we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block.First,the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information.The accelerated-KAZE(AKAZE)algorithm is used to combine the feature block information to match the reference image and the target image.Then,the random sample consensus(RANSAC)is applied to optimize the matching results.Finally,image fusion is performed with the global homography and the optimal seam-line method to improve the accuracy of image overlay fusion.The experimental results show that the proposed method in this paper effectively divides images into feature blocks by combining spatial information and gradient information,which not only solves the problem of stitching failure of underwater terrain images due to unobvious features,and further reduces the sensitivity to noise,but also effectively reduces the iterative calculation in the feature point matching process of the traditional method,and improves the stitching speed.Ghosting and shape warping are significantly eliminated by re-optimizing the overlap of the image.

Ultrasonic Characteristics and Severity Assessment of Lung Ultrasound in COVID-19 Pneumonia:A Retrospective,Observational Study

The clinical application of lung ultrasound(LS)in the assessment of coronavirus disease 2019(COVID-19)pneumonia severity remains limited,Herein,we investigated the role of LUS imaging in CoVID-19pneumonia patients and the relationship between LUS findings and disease severity.This was a retro-spective,observational study at Tongji Hospital,on 48 recruited patients with COVID-19 pneu-monia,including 32 non-critically ill patients and 16critically ill patients.LUS was performed and the respiratory rate oxygenation(ROX)index,disease severity,and confusion,blood urea nitrogen,respira-tory rate,blood pressure,and age(CURB-65)score were recorded on days 0-7,8-14,and 15-21 after symptomonset.Lung images were divided into 12 regions,and the luS score(0-36 points)was calcu-lated.hestcomputed tomography(CT)scores(0-20 points)were also recorded on days O-7.Coelations between the LUS score,ROX index,and CURB-65 scores were examined.LUS detected COVID-19 pneumonia in 38patients.LUS signs included B lines(34/38,89.5%),consolidations(6/38,15.8%),and pleural effusions(2/38,5.3%).Most cases showed more than one lesion(32/38,84.2%)and involved both lungs(28/38,73.7%).Compared with non-critically ill patients,the LUS scores of critically ill patients were higher(12(10-18)vs 2(0-5),p<0.001).The LUS score showed significant negative cor-relations with the ROX indexon days O-7(r=-0.85,p<0.001),days 8-14(r=-0.71,p<0.001),and days 15-21(r=-0.76,p<0.001)after symptom onset.However,the LUS score was positively correlated with the CT score(r=0.82,p<0.001).The number of patients with LUS-detected lesions decreased from 27 cases(81.8%)to 20 cases(46.5%),and the lus scores significantly decreased from 4(2-10)to 0(0-5),(p<0.001) from days O-7 to 17-21.We conclude that LUS can detect lunglesions in COVID-19 pneumo-nia patients in a portable,real-time,and safe manner.Thus,LUS is helpful in assessing COVID-19 pneu-monia severity in critically ill patients.

Research on Facial Expression Capture Based on Two-Stage Neural Network

To generate realistic three-dimensional animation of virtual character,capturing real facial expression is the primary task.Due to diverse facial expressions and complex background,facial landmarks recognized by existing strategies have the problem of deviations and low accuracy.Therefore,a method for facial expression capture based on two-stage neural network is proposed in this paper which takes advantage of improved multi-task cascaded convolutional networks(MTCNN)and high-resolution network.Firstly,the convolution operation of traditional MTCNN is improved.The face information in the input image is quickly filtered by feature fusion in the first stage and Octave Convolution instead of the original ones is introduced into in the second stage to enhance the feature extraction ability of the network,which further rejects a large number of false candidates.The model outputs more accurate facial candidate windows for better landmarks recognition and locates the faces.Then the images cropped after face detection are input into high-resolution network.Multi-scale feature fusion is realized by parallel connection of multi-resolution streams,and rich high-resolution heatmaps of facial landmarks are obtained.Finally,the changes of facial landmarks recognized are tracked in real-time.The expression parameters are extracted and transmitted to Unity3D engine to drive the virtual character’s face,which can realize facial expression synchronous animation.Extensive experimental results obtained on the WFLW database demonstrate the superiority of the proposed method in terms of accuracy and robustness,especially for diverse expressions and complex background.The method can accurately capture facial expression and generate three-dimensional animation effects,making online entertainment and social interaction more immersive in shared virtual space.

Research on Forecasting Flowering Phase of Pear Tree Based on Neural Network

Predicting the blooming season of ornamental plants is significant for guiding adjustments in production decisions and providing viewing periods and routes.The current strategies for observation of ornamental plant booming periods are mainly based on manpower and experience,which have problems such as inaccurate recognition time,time-consuming and energy sapping.Therefore,this paper proposes a neural network-based method for predicting the flowering phase of pear tree.Firstly,based on the meteorological observation data of Shijiazhuang Meteorological Station from 2000 to 2019,three principal components(the temperature factor,weather factor,and humidity factor)with high correlation coefficient with the flowering phase of pear tree are obtained by using the principal component analysis method.Then,the three components are used as input factors for the BP neural network.A BP neural network prediction model is constructed based on genetic algorithm optimization.The crossover operator and mutation operator in the adaptive genetic algorithm are improved.Finally,the meteorological sample data from 2013 to 2019 are used to test and verify the algorithm in this paper.The results demonstrate that,the model can solve the local optimization problem of the BP neural network model.The prediction results of the flowering phase of pear tree are evaluated in terms of relevance and prediction accuracy.Both are superior to the traditional effective accumulated temperature and the prediction results of the stepwise regression method.This method can provide more reliable forecast information for the blooming period,which can provide decision-making reference for improving the development of tourism industry.

A Pupil-Positioning Method Based on the Starburst Model

Human eye detection has become an area of interest in the field of computer vision with an extensive range of applications in human-computer interaction,disease diagnosis,and psychological and physiological studies.Gaze-tracking systems are an important research topic in the human-computer interaction field.As one of the core modules of the head-mounted gaze-tracking system,pupil positioning affects the accuracy and stability of the system.By tracking eye movements to better locate the center of the pupil,this paper proposes a method for pupil positioning based on the starburst model.The method uses vertical and horizontal coordinate integral projections in the rectangular region of the human eye for accurate positioning and applies a linear interpolation method that is based on a circular model to the reflections in the human eye.In this paper,we propose a method for detecting the feature points of the pupil edge based on the starburst model,which clusters feature points and uses the RANdom SAmple Consensus(RANSAC)algorithm to perform ellipse fitting of the pupil edge to accurately locate the pupil center.Our experimental results show that the algorithm has higher precision,higher efficiency and more robustness than other algorithms and excellent accuracy even when the image of the pupil is incomplete.

Speed Control of Motor Based on Improved Glowworm Swarm Optimization

To better regulate the speed of brushless DC motors,an improved algorithm based on the original Glowworm Swarm Optimization is proposed.The proposed algorithm solves the problems of poor robustness,slow convergence,and low accuracy exhibited by traditional PID controllers.When selecting the glowworm neighborhood set,an optimization scheme based on the growth and competition behavior of weeds is applied to a single glowworm to prevent falling into a local optimal solution.After the glowworm’s position is updated,the league selection operator is introduced to search for the global optimal solution.Combining the local search ability of the invasive weed optimization with the global search ability of the league selection operator enhances the robustness of the algorithm and also accelerates the convergence speed of the algorithm.The mathematical model of the brushless DC motor is established,the PID parameters are tuned and optimized using improved Glowworm Swarm Optimization algorithm,and the speed of the brushless DC motor is adjusted.In a Simulink environment,a double closed-loop speed control model was established to simulate the speed control of a brushless DC motor,and this simulation was compared with a traditional PID control.The simulation results show that the model based on the improved Glowworm Swarm Optimization algorithm has good robustness and a steady-state response speed for motor speed control.

Structural insights into Deinococcus radiodurans BamA:extracellular loop diversity and its evolutionary implications

Diderm bacteria,characterized by an additional lipid membrane layer known as the outer membrane,fold their outer membrane proteins(OMPs)via theβ-barrel assembly machinery(BAM)complex.Understanding how the BAM complex,particularly its key component BamA,assists in OMP folding remains crucial in bacterial cell biology.Recent research has focused primarily on the structural and functional characteristics of BamA within the Gracilicutes clade,such as in Escherichia coli(E.coli).However,another major evolutionary branch,Terrabacteria,has received comparatively less attention.An example of a Terrabacteria is Deinococcus radiodurans(D.radiodurans),a Gram-positive bacterium that possesses a distinctive outer membrane structure.In this study,we first demonstrated that theβ-barrel domains of BamA are not interchangeable between D.radiodurans and E.coli.The structure of D.radiodurans BamA was subsequently determined at 3.8Åresolution using cryo-electron microscopy,revealing obviously distinct arrangements of extracellular loop 4(ECL4)and ECL6 after structural comparison with their counterparts in gracilicutes.Despite the overall similarity in the topology of theβ-barrel domain,our results indicate that certain ECLs have evolved into distinct structures between the Terrabacteria and Gracilicutes clades.While BamA and its function are generally conserved across diderm bacterial species,our findings underscore the evolutionary diversity of this core OMP folder among bacteria,offering new insights into bacterial physiology and evolutionary biology.