Characterization of friction at three contact pairs by photoelastic Isotropic point (IP)

Friction coefficient between a circular-disk periphery and V-block surface was determined by introducing the concept of isotropic point (IP) in isochromatic field of the disk under three-point symmetric loading. IP position on the symmetry axis depends on active coefficient of friction during experiment. We extend this work to asymmetric loading of circular disk in which case two frictional contact pairs out of three loading contacts, independently control the unconstrained IP location. Photoelastic experiment is conducted on particular case of asymmetric three-point loading of circular disk. Basics of digital image processing are used to extract few essential parameters from experimental image, particularly IP location. Analytical solution by Flamant for half plane with a concentrated load, is utilized to derive stress components for required loading configurations of the disk. IP is observed, in analytical simulations of three-point asymmetric normal loading, to move from vertical axis to the boundary along an ellipse-like curve. When friction is included in the analysis, IP approaches the center with increase in loading friction and it goes away with increase in support friction. With all these insights, using experimental IP information, friction angles at three contact pairs of circular disk under asymmetric loading, are determined.

Human Action Recognition in Compressed Domain using PBL-McRBFN Approach

Large variations in human actions lead to major challenges in computer vision research. Several algorithms are designed to solve the challenges. Algorithms that stand apart, help in solving the challenge in addition to performing faster and efficient manner. In this paper, we propose a human cognition inspired projection based learning for person-independent human action recognition in the H.264/AVC compressed domain and demonstrate a PBL-McRBEN based approach to help take the machine learning algorithms to the next level. Here, we use gradient image based feature extraction process where the motion vectors and quantization parameters are extracted and these are studied temporally to form several Group of Pictures (GoP). The GoP is then considered individually for two different bench mark data sets and the results are classified using person independent human action recognition. The functional relationship is studied using Projection Based Learning algorithm of the Meta-cognitive Radial Basis Function Network (PBL-McRBFN) which has a cognitive and meta-cognitive component. The cognitive component is a radial basis function network while the Meta-Cognitive Component(MCC) employs self regulation. The McC emulates human cognition like learning to achieve better performance. Performance of the proposed approach can handle sparse information in compressed video domain and provides more accuracy than other pixel domain counterparts. Performance of the feature extraction process achieved more than 90% accuracy using the PTIL-McRBFN which catalyzes the speed of the proposed high speed action recognition algorithm. We have conducted twenty random trials to find the performance in GoP. The results are also compared with other well known classifiers in machine learning literature.

Database Independent Human Emotion Recognition with Meta-Cognitive Neuro-Fuzzy Inference System

Facial emotions are the most expressive way to display emotions. Many algorithms have been proposed which employ a particular set of people (usually a database) to both train and test their model. This paper focuses on the challenging task of database independent emotion recognition, which is a generalized case of subject-independent emotion recognition. The emotion recognition system employed in this work is a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS). McFIS has two components, a neuro-fuzzy inference system, which is the cognitive component and a self-regulatory learning mechanism, which is the meta-cognitive component. The meta-cognitive component, monitors the knowledge in the neuro-fuzzy inference system and decides on what-to-learn, when-to-learn and how-to-learn the training samples, efficiently. For each sample, the McFIS decides whether to delete the sample without being learnt, use it to add/prune or update the network parameter or reserve it for future use. This helps the network avoid over-training and as a result improve its generalization performance over untrained databases. In this study, we extract pixel based emotion features from well-known (Japanese Female Facial Expression) JAFFE and (Taiwanese Female Expression Image) TFEID database. Two sets of experiment are conducted. First, we study the individual performance of both databases on McFIS based on 5-fold cross validation study. Next, in order to study the generalization performance, McFIS trained on JAFFE database is tested on TFEID and vice-versa. The performance The performance comparison in both experiments against SVNI classifier gives promising results.

Action Recognition from Motion Capture Data using Meta-cognitive RBF Network Classifier

Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 31) angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).

Photosensitivity study of GeS2 chalcogenide glass under femtosecond laser pulses irradiation

The present study discusses the photosensitivity of GeS2 chalcogenide glass in response to irradiation with femtosecond pulses at 1047 nm. Bulk GeS2 glasses are prepared by conventional melt quenching technique and the amorphous nature of the glass is confirmed using X-ray diffraction. Ultrafast laser inscription technique is used to fabricate the straight channel waveguides in the glass. Single scan and multi scan waveguides are inscribed in GeS2 glasses of length 0.65 cm using a master oscillator power amplifier Yb doped fiber laser (IMRA mu jewel D400) with different pulse energy and translation speed. Diameters of the inscribed waveguides are measured and its dependence on the inscription parameters such as translation speed and pulse energy is studied. Butt coupling method is used to characterize the loss measurement of the inscribed optical waveguides. The mode field image of the waveguides is captured using CCD camera and compared with the mode field image of a standard SMF-28 fibers.

A novel interferometric technique to estimate thermal diffusivity of `optically transparent solid' using `Isothermal surface velocimetry'

One-dimensional transient heat flow is interpreted as a procession of `macro-scale translatory motion of indexed isothermal surfaces'. A new analytical model is proposed by introducing velocity of isothermal surface in Fourier heat diffusion equation. The velocity dependent function is extracted by revisiting `the concept of thermal layer of heat conduction in solid' and `exact solution' to estimate thermal diffusivity. The experimental approach involves establishment of 1 D unsteady heat flow inside the sample through Step-temperature excitation. A novel self-reference interferometer is utilized to separate a `unique isothermal surface' in time-varying temperature field. The translatory motion of the said isothermal surface is recorded using digital camera to estimate its velocity. From the knowledge of thermo-optic coefficient, temperature of the said isothermal surface is predicted. The performance of proposed method is evaluated for Quartz sample and compared with literature.

Non-invasive pressure monitoring by hoop strain using Fiber Bragg Grating sensor

Non-invasive, real-time dynamic monitoring of pressure inside a column with the aid of Fiber Bragg Grating (FBG) sensor is presented in the present work. A bare FBG sensor is adhered on the circumference of a pressure column normal to its axis, which has the ability to acquire the hoop strain induced by the pressure variation inside the column. Pressure induced hoop strain response obtained using FBG sensor is validated against the pressure measurements obtained from conventional pressure gauge. Further, a protrusion setup on the outer surface of the column has been proposed over which a secondary FBG sensor is bonded normal to its axis, in order to increase the gauge length of this FBG sensor. This is carried out in order to validate the variation in sensitivity of the protrusion bonded FBG sensor compared to the bare FBG sensor bonded over the surface. A comparative study is done between the two FBG sensors and a conventional pressure gauge in order to establish the capacity of FBG sensor obtained hoop strain response for pressure monitoring inside the column.

Divide and Conquer: Efficient Large-Scale Structure from Motion Using Graph Partitioning

Despite significant advances in recent years, structure-from-motion (SfM) pipelines suffer from two important drawbacks. Apart from requiring significant computational power to solve the large-scale computations involved, such pipelines sometimes fail to correctly reconstruct when the accumulated error in incremental reconstruction is large or when the number of 3D to 2D correspondences are insufficient. In this paper we present a novel approach to mitigate the above-mentioned drawbacks. Using an image match graph based on matching features we partition the image data set into smaller sets or components which are reconstructed independently. Following such reconstructions we utilise the available epipolar relationships that connect images across components to correctly align the individual reconstructions in a global frame of reference. This results in both a significant speed up of at least one order of magnitude and also mitigates the problems of reconstruction failures with a marginal loss in accuracy. The effectiveness of our approach is demonstrated on some large-scale real world data sets.

Activity Recognition in Egocentric Life-Logging Videos

With the increasing availability of wearable cameras, research on first-person view videos (egocentric videos) has received much attention recently. While some effort has been devoted to collecting various egocentric video datasets, there has not been a focused effort in assembling one that could capture the diversity and complexity of activities related to life-logging, which is expected to be an important application for egocentric videos. In this work, we first conduct a comprehensive survey of existing egocentric video datasets. We observe that existing datasets do not emphasize activities relevant to the life-logging scenario. We build an egocentric video dataset dubbed LENA (Life-logging EgoceNtric Activities) (http://people.sutd.edu.sg/similar to 1000892/dataset) which includes egocentric videos of 13 fine-grained activity categories, recorded under diverse situations and environments using the Google Glass. Activities in LENA can also be grouped into 5 top-level categories to meet various needs and multiple demands for activities analysis research. We evaluate state-of-the-art activity recognition using LENA in detail and also analyze the performance of popular descriptors in egocentric activity recognition.