Parminder Singh Reel

Analysis of contemporary robotics simulators

Designing a robot physically and validating it at every step is an arduous task. Contemporary robotics simulators can help to achieve laborious physics simulations, 3D visualizations, virtual robot modeling and novel research work that save time and money. Simulators are written in numerous programming languages like C, C++, Java, C# and other OOP languages that decide their platform compatibility. Some robot simulators use physics engines like ODE, Karma Engine for better simulation that include responses like collision detection, scene representation and rigid body simulations. Some use sophisticated 3D graphic aids like OpenGL and Graphic cards (NVidia, ATI) rather than traditional Direct3D, considering various facets like cost, portability and extensions. Codes can be transferred to the real robots from some simulators after proper verification for their operation. Unlimited features like multiplayer, controllers transference over networks, ‘special effects’ and so forth, keep on pouring. This paper proffers some of the widespread commercial/ open-source simulators for robots and UAVs used in market. Further, I conclude that any kind of robot including legged, wheeled or UAVs can be simulated using simulators available in market with continuous endeavors to upgrade these simulators.

Effects of threshold of hard cut based technique for advertisement detection in TV video streams

Advertisement detection in a TV video recording/archiving system is a challenging task. In this paper, shot change (hard cut) detection that is based on “inter-frame difference”, “normalized difference energy” and the “normalized sum of absolute differences” and its comparison with a threshold are discussed. The effects of changing video threshold on hard cut detection have been summarized. A threshold value is evaluated for the efficient extraction of complete advertisement. Effects of various thresholds are extensively tested on more than 20 hrs of TV video streams. The frequency of shot breaks along with blank frames is considered as a key component in advertisement detection. Results of these MATLAB and LabVIEW based computer simulations have been reported.

Energy efficient wireless sensing framework to enhance mobile learning

Wireless sensor network (WSN) technology has got the various potential applications for mobile learning. It facilitates the proper monitoring of environmental conditions which can be combined with the convectional mobile learning devices to enhance and extend the features of mobile learning. However sensor nodes have energy constraints for mobile learning applications. In this paper, a novel approach to implement energy efficient wireless sensing framework for mobile learning is presented using an Unmanned Aerial Vehicle as a Mobile Agent. This approach has unique features of wireless power delivery and data collection options from the required sensor nodes on the mobile learning device. UAV provides unrestricted accessibility and wirelessly triggering the sensor node, thus reducing energy consumption. It carries Beagle Board payload for on the spot calculations of data collected. The onboard video camera provides captures video of the area of interest and helps in enhancing the learning experience. This paper is intended to give sufficient details of the implementation of our approach.

Real Time Low Level Parallel Image Processing For Active Vision Systems

This paper presents an overview of low level parallel image processing algorithms and their implementationfor active vision systems. Authors have demonstrated novel low level image processing algorithms for point operators, local operators, dithering, smoothing, edge detection, morphological operators, image segmentation and image compression. The algorithms have been prepared & described as pseudo codes. These algorithms have been simulated Using Parallel Computing ToolboxTM (PCT) of MATLAB. The PCT provides parallel constructs in the MATLAB language, such as parallel for loops, distributed arrays and message passing & enables rapid prototyping ofparallel code through an interactive parallel MATLAB session

Morphology based feature extraction and recognition for enhanced wheat quality evaluation

Wheat grain quality assessment is important in meeting market requirements. The quality of the wheat can be judge byits length, thickness, width, area, etc. In this paper on the basis of simple mathematical calculations different parameters of a number of wheat grains are calculated. The present paper focused on the classification of wheat grains using morphological. The grain types used in this study were Hard Wheat, Tender Wheat. In this paper the application of neural network is used for assessment of wheat grain. The contours of whole and broken grains have been extracted, precisely normalised and then used as input data for the neural network. The network optimisation has been carried out and then the results have been analysed in the context of response values worked –out by the output neurons.

Segregation of Colored Objects Using Industrial Robotic Arm

There is a great need of reducing human effort in each and every span of industrial engineering. The paper deals in a robotic arm that fetches objects from a conveyor belt and does some dedicated work say packing the objects in the same color of packaging as that of object or segregating the objects on the basis of color or geometry. An overhead camera is mounted perpendicular to the belt at some specified height which would be sending recorded images to the processing unit and processing unit would be instructing the robotic arm to pick up some objects. The processing unit uses image processing to instruct the arm.

Social networking: a new vision of e-learning

The paper aims at promoting e-learning through most popular websites of the era, better known as Social Networks. The focus of the research is to build a common platform where every individual be it be a technician or an industrialist or may be a student can share their ideas and resources with an ease of troubleshooting and problem handling. In addition to it, the help fetched from the server can facilitate video call support to enhance the overall scenario.

Aerial Vehicle Based Sensing Framework for Structural Health Monitoring

A novel approach to implement wireless active sensing framework for Structural Health Monitoring is presented using an Unmanned Aerial Vehicle as a Mobile Agent. This approach has unique features of critical activity detection, wireless power delivery and measurement and data collection options from the sensor nodes through Zigbee. The active sensing is initiated by wirelessly triggering the sensor node from UAV. UAV provides unrestricted accessibility in various applications for SHM. It carries Beagle Board payload for real-time calculations to check the health of structures. The onboard video camera provides improved analysis of Critical activities like abnormal vibration and structure tilt. It captures video of the area of interest and data measured by any sensor node network. This paper is intended to give sufficient details of the implementation of our approach.