Sowmyanarayanan Krishnakumar

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
In all computer vision system, the important step is to separate moving object from background and thus detecting all the objects from video images. The main aim of this paper is to design a bounding box concept for the human detection and tracking system in the presence of crowd. The images are captured by using monocular cameras. The bounding box around(More)
— The main objective of object tracking is to detect and track target objects in the current frame in the video sequence under various environmental conditions. The tracking of objects is difficult due to the impact of various factors like appearance change, occlusion, change in illumination, fast movement of object, etc. These problems can be overcome by(More)
First order optimization methods, while being powerful and rapidly convergent, suffer from the fact that as the descriptive geometric parameters change from iteration to iteration, corresponding to these new geometries, new meshes need to be implemented. Correspondingly the new topologies of the meshes introduce non-physical jumps in the object function.(More)
—Optimization models related with routing, bandwidth utilization and power consumption are developed in the wireless mesh computing environment using the operations research techniques such as maximal flow model, transshipment model and minimax optimizing algorithm. The Path creation algorithm is used to find the multiple paths from source to destination.A(More)
Hexagonal geometry has some advantageous like higher sampling efficiency, consistent connectivity and higher angular resolution. In addition to these advantages, the layout of photo-receptors in the human retina is more closely resembles to the hexagonal structure. It is due to these reasons many researchers have studied the possibility of using a hexagonal(More)
In this work, we introduce a novel method for recognizing multiple objects in an image at a very high speed. The system is based on self learning high speed parallel processing devices. The system processes video streams at speed of 1000 frames per second or more. For high speed object recognition using sequential computing from an image of a video having(More)
  • 1