Increase in the number of sport lovers in games like football, cricket, etc. has created a need for digging, analyzing and presenting more and more multidimensional information to them. Different classes of people require different kinds of information and this expands the space and scale of the required information. Tracking of ball movement is of utmost importance for extracting any information from the ball based sports video sequences. Based on the literature survey, we have initially proposed a block diagram depicting different steps and flow of a general tracking process. The paper further follows the same flow throughout. Detection is the first step of tracking. Dynamic and unpredictable nature of ball appearance, movement and continuously changing background make the detection and tracking processes challenging. Due to these challenges, many researchers have been attracted to this problem and have produced good results under specific conditions. However, generalization of the published work and algorithms to different sports is a distant dream. This paper is an effort to present an exhaustive survey of all the published research works on ball tracking in a categorical manner. The work also reviews the used techniques, their performance, advantages, limitations and their suitability for a particular sport. Finally, we present discussions on the published work so far and our views and opinions followed by a modified block diagram of the tracking process. The paper concludes with the final observations and suggestions on scope of future work.

Ball tracking in sports: a survey

This paper attempts to study the potential of lime on strength and bearing capacity improvement of subgrade soil. The effect of soil type, different lime percentages (3, 5, 7 and 9%) and curing duration (0, 7, 14 and 28 days) on the engineering properties of soil is evaluated by conducting series of laboratory tests such as linear shrinkage, unconfined compressive strength (UCS), split-tensile strength (STS) and California bearing ratio (CBR) test. The result indicates that soil with large clay fractions needs a relatively higher percentage of lime to alter their physicochemical characteristics. Addition of lime reduced the linear shrinkage strains and increased the UCS, STS and CBR value of soil. But beyond an optimum lime content opposite trend is observed. The strength improvement of lime stabilized soil is further enhanced with curing time. Moreover, the micro-structural analyses are performed to understand the mechanisms involved in the lime stabilization process. Change in soil morphology fr...

The strength and microstructural behavior of lime stabilized subgrade soil in road construction

This paper presents a novel framework for predicting shot location and type in tennis. Inspired by recent neuroscience discoveries, we incorporate neural memory modules to model the episodic and semantic memory components of a tennis player. We propose a Semi-Supervised Generative Adversarial Network architecture that couples these memory models with the automatic feature learning power of deep neural networks, and demonstrate methodologies for learning player level behavioral patterns with the proposed framework. We evaluate the effectiveness of the proposed model on tennis tracking data from the 2012 Australian Tennis Open and exhibit applications of the proposed method in discovering how players adapt their style depending on the match context.

Memory Augmented Deep Generative Models for Forecasting the Next Shot Location in Tennis

Soil improvement by incorporating different reinforcement materials has been one of the most popular fields of study in geotechnical engineering since it can provide the engineers with a practical and relatively easy solution when dealing with various construction projects. Despite numerous studies carried out on the static behavior of reinforced soils, the dynamic characteristics of these mixtures have not been fully understood. Therefore, this paper aims to shed light upon this issue by conducting repeated loading triaxial tests on a sandy soil reinforced by different Waste Tire Textile Fiber (WTTF) contents. Various parameters such as permanent strain, resilient modulus, energy dissipation capacity, and damping ratio were investigated. The results of this study show that permanent strain is increased as a result of fiber addition. Nevertheless, rutting is not expected to occur since all soil-fiber mixtures are categorized in groups A (plastic shakedown) and B (plastic creep) of shakedown theory. Resilient modulus is increased up to 744% with an optimum WTTF content of 2%. Dissipated energy and damping ratio are also found to increase as a result of fiber inclusion. Furthermore, a new model is proposed to accurately predict the resilient modulus in terms of the number of cycles and fiber content.

Long-term dynamic behavior of a sandy subgrade reinforced by Waste Tire Textile Fibers (WTTFs)

Prediction of the resilient modulus of two tropical subgrade soils considering unsaturated conditions

The design of highway subgrades necessitates the estimation of strength and stiffness characteristics to a reasonably accurate extent. The present study provides details on investigations on the modulus of resilience of lateritic soils in the region of Dakshina Kannada in Southern India, using the cyclic tri-axial test equipment. The discussions also provide comparisons on similar studies performed using the portable falling weight deflectometer (PFWD), and the California bearing ratio (CBR) test. As part of this study, regression equations were developed in order to correlate the observations made using the PFWD and the CBR with the results obtained using the cyclic tri-axial test. It is felt that the regressions developed for estimating the modulus of resilience based on simpler experimental approaches such as the CBR, and the PFWD, will be of special advantage to pavement engineers in developing nations.

Studies on modulus of resilience using cyclic tri-axial test and correlations to PFWD, DCP, and CBR

The use of portable falling weight deflectometers (PFWDs) has gained prominence among pavement engineers in the characterisation of soil sub-grade based on modulus of stiffness. The values of modulus of resilience and the corresponding values of the rebound deflection measured using the PFWD are largely influenced by the soil stiffness. The focus of the present investigation is on the study of the effect of soil parameters such as grain size distribution, maximum dry density (MDD) and optimum moisture content (OMC) on the values of modulus of stiffness (EPFWD) obtained using the PFWD for tests performed on lateritic soil blends. Tests were conducted on various blends of lateritic soil samples compacted to MDD at moulding water contents set to the optimum moisture content (OMC), dry-side of optimum at OMC−3% and wet-side of optimum at OMC+3%. The regressions developed between the values of EPFWD and the percentage of fines and the percentage of sand for lateritic and lithomargic soils indicate a st...

Effect of soil parameters on modulus of resilience based on portable falling weight deflectometer tests on lateritic sub-grade soils

Resilient modulus (Mr) of a soil is used as a basic input in the analysis of sub-grade and sub-base in the mechanistic empirical design approaches. The present work focuses on evolving a cost effective approach for the determination of resilient modulus in the laboratory based on tests performed using the CBR method, and the DCP. Lateritic sub-grades in India exhibit wide-ranging variations in strength and stiffness due to varying fines content, and other characteristics. Additionally, soils of lateritic origin with a higher proportion of fines, also called as lithomargic soils, pose difficulties to pavement engineers due to the poor supporting strength. In order to investigate the strength and stiffness of a wide variety of lateritic soils, it was proposed to perform tests on lateritic soils blended with lithomargic fines in this study. The study focuses on correlating the effect of grain-size, maximum dry-density (MDD), and optimum moisture content (OMC) on the resilient modulus (Mr) measured using the cyclic tri-axial test for various blends of lateritic soils. Tests were performed on soil samples compacted to MDD for molding water contents set to the OMC, dry-side of OMC, and the wet-side of OMC. The results indicated that an increase in the fines-content resulted in an increase in the OMC, and a decrease in the MDD and Mr values. Regressions were developed correlating the fines content to the resilient modulus. This study is expected to provide the necessary basis for estimating the strength of a wide variety of lateritic sub-grades based on the fines content.

Effect of Soil Parameters on Resilient Modulus Using Cyclic Tri-Axial Tests on Lateritic Subgrade Soils from Dakshina Kannada, India

In this work, we develop image processing and computer vision techniques for visually tracking a tennis ball, in 3D, on a court instrumented with multiple low-cost IP cameras The technique first obtains 2D ball tracking data from each camera view using 2D object tracking methods Next, an automatic feature-based video synchronization method is applied This technique uses the extracted 2D ball information from two or more camera views, plus camera calibration information In order to find 3D trajectory, the temporal 3D locations of the ball is estimated using triangulation of correspondent 2D locations obtained from automatically synchronized videos Furthermore, in order to improve the continuity of the tracked 3D ball during times when no two cameras have overlapping views of the ball location, we incorporate a physics-based trajectory model into the system The resultant 3D ball tracks are then visualized in a virtual 3D graphical environment Finally, we quantify the accuracy of our system in terms of reprojection error

/pdf/3d-estimation-and-visualization-of-motion-in-a-multicamera-j7227zneh7.pdf

3D Estimation and Visualization of Motion in a Multicamera Network for Sports

Chip Multiprocessors(CMPs) and Multiprocessor System-on-Chips(MPSoCs) are meeting the ever increasing demand for high performance in processing large scale data and applications. There is a corresponding increase in the volume and frequency of traffic in the Network-on-Chip(NoC) architectures like CMPs and SoCs. NoC performance parameters like network latency, flit latency and hop count are critical measures which directly influence the overall performance of the architecture and execution time of the application. Unfortunately, cycle-accurate software simulators become slow for interactive use with an increase in architectural size of NoC. In order to provide the chip designer with an efficient framework for accurate measurements of NoC performance parameters, we propose a Machine Learning(ML) framework. Which is designed using different ML regression algorithms like Support Vector Regression(SVR) with different kernels and Artificial Neural Networks(ANN) with different activation functions. The proposed learning framework can be used to analyze the performance parameters of Mesh and Torus based NoC architectures. Results obtained are compared against the widely used cycle-accurate Booksim simulator. Experiments were conducted by variables like topology size from $2\times 2$ to $30\times 30$ with different virtual channels, traffic patterns and injection rates. The framework showed an approximate prediction error of 5% to 8% and overall minimum speedup of $1500\times$ to $2000\times$ .

Anil Kumar

Papers

Studies on modulus of resilience using cyclic tri-axial test and correlations to PFWD, DCP, and CBR

Effect of soil parameters on modulus of resilience based on portable falling weight deflectometer tests on lateritic sub-grade soils

Effect of Soil Parameters on Resilient Modulus Using Cyclic Tri-Axial Tests on Lateritic Subgrade Soils from Dakshina Kannada, India

3D Estimation and Visualization of Motion in a Multicamera Network for Sports

Machine Learning Based Framework to Predict Performance Evaluation of On-Chip Networks