scholarly journals Gait Recognition Using GEI and AFDEI

2015 ◽  
Vol 2015 ◽  
pp. 1-5 ◽  
Author(s):  
Jing Luo ◽  
Jianliang Zhang ◽  
Chunyuan Zi ◽  
Ying Niu ◽  
Huixin Tian ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
Gait Recognition ◽  
Dynamic Information ◽  
Static Information ◽  
Gait Feature ◽  
Time Requirements ◽  
The Common ◽  
The Moment ◽  
Neighbor Classifier ◽  
Better Than

Gait energy image (GEI) preserves the dynamic and static information of a gait sequence. The common static information includes the appearance and shape of the human body and the dynamic information includes the variation of frequency and phase. However, there is no consideration of the time that normalizes each silhouette within the GEI. As regards this problem, this paper proposed the accumulated frame difference energy image (AFDEI), which can reflect the time characteristics. The fusion of the moment invariants extracted from GEI and AFDEI was selected as the gait feature. Then, gait recognition was accomplished using the nearest neighbor classifier based on the Euclidean distance. Finally, to verify the performance, the proposed algorithm was compared with the GEI + 2D-PCA and SFDEI + HMM on the CASIA-B gait database. The experimental results have shown that the proposed algorithm performs better than GEI + 2D-PCA and SFDEI + HMM and meets the real-time requirements.

Gait Recognition Based on Locality Preserving Projections

2015 ◽  
Vol 738-739 ◽  
pp. 625-630
Author(s):  
Chao Li ◽  
Jin Ye Peng ◽  
Jing Guo ◽  
Xian Feng Wang ◽  
Xu Qi Wang
Keyword(s):  
Nearest Neighbor ◽  
Wavelet Packet ◽  
Gait Recognition ◽  
Recognition Method ◽  
The Public ◽  
Nearest Neighbor Classifier ◽  
Locality Preserving Projections ◽  
Locality Preserving ◽  
Neighbor Classifier

A gait recognition method based on wavelet packet decomposition (WPD) and Locality preserving projections (LPP) is proposed in this paper. The method includes the following steps, pretreatment, feature extraction by WPD and dimensionality reduction by LPP and classification of the test samples to a corresponding class according to the nearest neighbor classifier. The experiment results on the public gait database show the effectiveness of the proposed method.

scholarly journals Deep Large Margin Nearest Neighbor for Gait Recognition

2021 ◽  
Vol 30 (1) ◽  
pp. 604-619
Author(s):  
Wanjiang Xu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Video Surveillance ◽  
Computational Efficiency ◽  
Nearest Neighbor ◽  
Gait Recognition ◽  
Large Margin ◽  
Extensive Evaluation ◽  
Gait Features ◽  
Gait Feature

Abstract Gait recognition in video surveillance is still challenging because the employed gait features are usually affected by many variations. To overcome this difficulty, this paper presents a novel Deep Large Margin Nearest Neighbor (DLMNN) method for gait recognition. The proposed DLMNN trains a convolutional neural network to project gait feature onto a metric subspace, under which intra-class gait samples are pulled together as small as possible while inter-class samples are pushed apart by a large margin. We provide an extensive evaluation in terms of various scenarios, namely, normal, carrying, clothing, and cross-view condition on two widely used gait datasets. Experimental results demonstrate that the proposed DLMNN achieves competitive gait recognition performances and promising computational efficiency.

Scanning Secondary Electron Microscopy of Myofibrils Using Transmission Techniques

1975 ◽  
Vol 33 ◽  
pp. 556-557
Author(s):  
M. K. Lamvik
Keyword(s):  
Electron Microscopy ◽  
Electron Microscope ◽  
Carbon Films ◽  
Photographic Recording ◽  
Transmission Electron ◽  
Thin Carbon ◽  
The Common ◽  
Scanning Electron ◽  
Better Than ◽  
Cellular Organelles

When observing small objects such as cellular organelles by scanning electron microscopy, it is often valuable to use the techniques of transmission electron microscopy. The common practice of mounting and coating for SEM may not always be necessary. These possibilities are illustrated using vertebrate skeletal muscle myofibrils.Micrographs for this study were made using a Hitachi HFS-2 scanning electron microscope, with photographic recording usually done at 60 seconds per frame. The instrument was operated at 25 kV, with a specimen chamber vacuum usually better than 10-7 torr. Myofibrils were obtained from rabbit back muscle using the method of Zak et al. To show the component filaments of this contractile organelle, the myofibrils were partially disrupted by agitation in a relaxing medium. A brief centrifugation was done to clear the solution of most of the undisrupted myofibrils before a drop was placed on the grid. Standard 3 mm transmission electron microscope grids covered with thin carbon films were used in this study.

scholarly journals Improving the Detection of the Contact Point in Active Sensing Antennae by Processing Combined Static and Dynamic Information

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1808
Author(s):  
Luis Mérida-Calvo ◽  
Daniel Feliu-Talegón ◽  
Vicente Feliu-Batlle
Keyword(s):  
Contact Point ◽  
Load Cell ◽  
Robotic Systems ◽  
Accurate Estimation ◽  
Flexible Beam ◽  
Dynamic Information ◽  
New Developments ◽  
Static Information ◽  
Insect Antennae ◽  
Flexible Antenna

The design and application of sensing antenna devices that mimic insect antennae or mammal whiskers is an active field of research. However, these devices still require new developments if they are to become efficient and reliable components of robotic systems. We, therefore, develop and build a prototype composed of a flexible beam, two servomotors that drive the beam and a load cell sensor that measures the forces and torques at the base of the flexible beam. This work reports new results in the area of the signal processing of these devices. These results will make it possible to estimate the point at which the flexible antenna comes into contact with an object (or obstacle) more accurately than has occurred with previous algorithms. Previous research reported that the estimation of the fundamental natural frequency of vibration of the antenna using dynamic information is not sufficient as regards determining the contact point and that the estimation of the contact point using static information provided by the forces and torques measured by the load cell sensor is not very accurate. We consequently propose an algorithm based on the fusion of the information provided by the two aforementioned strategies that enhances the separate benefits of each one. We demonstrate that the adequate combination of these two pieces of information yields an accurate estimation of the contacted point of the antenna link. This will enhance the precision of the estimation of points on the surface of the object that is being recognized by the antenna. Thorough experimentation is carried out in order to show the features of the proposed algorithm and establish its range of application.

scholarly journals Fuzzy Covering-Based Three-Way Clustering

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Dandan Yang
Keyword(s):  
Nearest Neighbor ◽  
Structural Information ◽  
Boundary Region ◽  
Global Perspective ◽  
Semantic Interpretation ◽  
Entropy Theory ◽  
Fuzzy Similarity ◽  
Fuzzy Similarity Relation ◽  
The Universe ◽  
Better Than

This paper investigates the three-way clustering involving fuzzy covering, thresholds acquisition, and boundary region processing. First of all, a valid fuzzy covering of the universe is constructed on the basis of an appropriate fuzzy similarity relation, which helps capture the structural information and the internal connections of the dataset from the global perspective. Due to the advantages of valid fuzzy covering, we explore the valid fuzzy covering instead of the raw dataset for RFCM algorithm-based three-way clustering. Subsequently, from the perspective of semantic interpretation of balancing the uncertainty changes in fuzzy sets, a method of partition thresholds acquisition combining linear and nonlinear fuzzy entropy theory is proposed. Furthermore, boundary regions in three-way clustering correspond to the abstaining decisions and generate uncertain rules. In order to improve the classification accuracy, the k-nearest neighbor (kNN) algorithm is utilized to reduce the objects in the boundary regions. The experimental results show that the performance of the proposed three-way clustering based on fuzzy covering and kNN-FRFCM algorithm is better than the compared algorithms in most cases.

Evaluation of Gas-Liquid Chromatography in Assays for Blood Volatiles

1965 ◽  
Vol 11 (11) ◽  
pp. 1023-1035 ◽  
Author(s):  
Alan Mather ◽  
Angel Assimos
Keyword(s):  
Liquid Chromatography ◽  
Alcohol Concentration ◽  
Quantitative Assay ◽  
Gas Liquid Chromatography ◽  
Internal Reference ◽  
Detection And Identification ◽  
Large Populations ◽  
The Common ◽  
Low Levels ◽  
Better Than

Abstract A simple screening by gas-liquid chromatography (GLC) can provide definitive answers in the detection and identification of a number of volatile substances, including acetone and the common alcohols. After identification, quantitative assay by an internal-reference technic yields highly specific values for ethyl alcohol concentration with a precision at least equal to (and for low levels, better than) that of conventional assays. The unique advantage of GLC is in its simultaneous quantitative assay of mixtures, some of which cannot be satisfactorily assayed or even recognized in any other way. The combination of speed and negligible sample volumes render the technic valuable for sequential studies on capillary blood samples and, potentially, for mass screening of large populations.

Sign in / Sign up

Export Citation Format

Share Document