Visual Motion Segmentation in Crowd Videos Based on Spatial-Angular Stacked Sparse Autoencoders

Visual motion segmentation(VMS)is an important and key part of many intelligent crowd systems.It can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd stampedes and crashes,which pose a serious risk to public safety and have resulted in numerous fatalities over the past few decades.Trajectory clustering has become one of the most popular methods in VMS.However,complex data,such as a large number of samples and parameters,makes it difficult for trajectory clustering to work well with accurate motion segmentation results.This study introduces a spatial-angular stacked sparse autoencoder model(SA-SSAE)with l2-regularization and softmax,a powerful deep learning method for visual motion segmentation to cluster similar motion patterns that belong to the same cluster.The proposed model can extract meaningful high-level features using only spatial-angular features obtained from refined tracklets(a.k.a‘trajectories’).We adopt l2-regularization and sparsity regularization,which can learn sparse representations of features,to guarantee the sparsity of the autoencoders.We employ the softmax layer to map the data points into accurate cluster representations.One of the best advantages of the SA-SSAE framework is it can manage VMS even when individuals move around randomly.This framework helps cluster the motion patterns effectively with higher accuracy.We put forward a new dataset with itsmanual ground truth,including 21 crowd videos.Experiments conducted on two crowd benchmarks demonstrate that the proposed model can more accurately group trajectories than the traditional clustering approaches used in previous studies.The proposed SA-SSAE framework achieved a 0.11 improvement in accuracy and a 0.13 improvement in the F-measure compared with the best current method using the CUHK dataset.

Research on dynamics patterns and parameter characters of crustal deformation field before and after strong earthquake

Based on the dynamic monitoring data of crustal deformation, the parameter evolution for the dynamics pattern and fractal dimension of crustal deformation field and the integral activity level of many faults etc. before and after the Tangshan (1976) and Lijiang (1996) strong earthquakes and others are studied by using the method of pattern dynamics. It is exposed that two time space characters, the ordered dimension drop of the deformation field and the accelerated motion of multi fault before an earthquake, are probably caused by the deformation localization and fault softening after the seismogenic process enters the nonlinear stage. They could be an important seismic precursor if they occurred repeatedly before strong earthquakes.

Adaptive Walking of a Quadrupedal Robot Based on Layered Biological Reflexes

A multiple-legged robot is traditionally controlled by using its dynamic model.But the dynamic-model-based approach fails to acquire satisfactory performances when the robot faces rough terrains and unknown environments.Referring animals＇ neural control mechanisms,a control model is built for a quadruped robot walking adaptively.The basic rhythmic motion of the robot is controlled by a well-designed rhythmic motion controller（RMC） comprising a central pattern generator（CPG） for hip joints and a rhythmic coupler（RC） for knee joints.CPG and RC have relationships of motion-mapping and rhythmic couple.Multiple sensory-motor models,abstracted from the neural reflexes of a cat,are employed.These reflex models are organized and thus interact with the CPG in three layers,to meet different requirements of complexity and response time to the tasks.On the basis of the RMC and layered biological reflexes,a quadruped robot is constructed,which can clear obstacles and walk uphill and downhill autonomously,and make a turn voluntarily in uncertain environments,interacting with the environment in a way similar to that of an animal.The paper provides a biologically inspired architecture,with which a robot can walk adaptively in uncertain environments in a simple and effective way,and achieve better performances.

Review of biomechanical deviations among nonpregnant,pregnant,and postpartum cohorts

During pregnancy,women experience substantial changes in physiology,morphology,and hormonal systems.These changes have profound effects on the biomechanics of the human body,particularly the musculoskeletal system,resulting in discomfort,pain,and decreased body stability.Sufficient biomechanical knowledge is critical for understanding the etiology and precautions of musculoskeletal disorders.With awareness of health problems in the pregnant cohort,identification,intervention,and precaution of problems have garnered attention.Researchers have conducted studies to determine the biomechanics of pregnancy.There have been review studies on summarization.However,to the best of our knowledge,few studies have comprehensively described biomechanical changes throughout pre-,in-,and postpartum periods.This review analyzed available studies on biomechanical changes during these three periods in the electronic databases of PubMed,Scopus,and Cochrane from inception until June 2,2021.Synthesized the general information,age of the studied subjects,investigated periods,sample size,objectives,measurement tools,and outcomes of reviewed studies.And Using National Institutes of Health quality assessment tool for observational cohort and cross-sectional studies to assessment the quality of the reviewed articles.These studies revealed biomechanical deviations in body stability,motion patterns,and gait modes during these three periods.Regarding research content,there are insufficient studies on certain critical biomechanical aspects,such as the kinetic parameters of the inner body,which are the most direct factors related to musculoskeletal problems.According to the National Institutes of Health quality assessment tool for observational cohort and cross-sectional studies,a more comprehensive and explicit understanding of pregnancy biomechanics can be expected.

Design,analysis,and neural control of a bionic parallel mechanism

Although the torso plays an important role in the movement coordination and versatile locomotion of mammals,the structural design and neuromechanical control of a bionic torso have not been fully addressed.In this paper,a parallel mechanism is designed as a bionic torso to improve the agility,coordination,and diversity of robot locomotion.The mechanism consists of 6-degree of freedom actuated parallel joints and can perfectly simulate the bending and stretching of an animal’s torso during walking and running.The overall spatial motion performance of the parallel mechanism is improved by optimizing the structural parameters.Based on this structure,the rhythmic motion of the parallel mechanism is obtained by supporting state analysis.The neural control of the parallel mechanism is realized by constructing a neuromechanical network,which merges the rhythmic signals of the legs and generates the locomotion of the bionic parallel mechanism for different motion patterns.Experimental results show that the complete integrated system can be controlled in real time to achieve proper limb-torso coordination.This coordination enables several different motions with effectiveness and good performance.