Kajal Sharma

Work place: University of Delhi, Delhi, 110007, India

E-mail: kajal175@gmail.com

Website: https://scholar.google.com/citations?hl=en&user=f4rQH7EAAAAJ

Research Interests: Computer Networks, Robotics, Neural Networks, Computer Vision


Kajal Sharma received the B.E. degree in Computer Engineering from University of Rajasthan, India, in 2005, M.Tech. and Ph.D. degrees in Computer Science from Banasthali University, Rajasthan, India, in 2007 and 2010, respectively. From October 2010 to September 2011, she worked as a postdoctoral researcher at Kongju National University, Korea. From October 2011, she worked as a postdoctoral researcher at the School of Computer Engineering, Chosun University, Gwangju, Korea. Her research interest areas are image and video processing, neural networks, computer vision, robotics, etc.

Author Articles
Optimization and Tracking of Vehicle Stable Features Using Vision Sensor in Outdoor Scenario

By Kajal Sharma

DOI: https://doi.org/10.5815/ijmecs.2016.08.05, Pub. Date: 8 Aug. 2016

Detection and tracking of stable features in moving real time video sequences is one of the challenging task in vision science. Vision sensors are gaining importance due to its advantage of providing much information as compared to recent sensors such as laser, infrared, etc. for the design of real–time applications. In this paper, a novel method is proposed to obtain the features in the moving vehicles in outdoor scenes and the proposed method can track the moving vehicles with improved matched features which are stable during the span of time. Various experiments are conducted and the results show that features classification rates are higher and the proposed technique is compared with recent methods which show better detection performance.

[...] Read more.
GPU Optimized Stereo Image Matching Technique for Computer Vision Applications

By Kajal Sharma

DOI: https://doi.org/10.5815/ijmecs.2015.05.05, Pub. Date: 8 May 2015

In this paper, we propose a graphics processing unit (GPU) based matching technique to perform fast feature matching between different images. Lowe proposed a scale invariant feature transform algorithm that has been successfully used in various feature matching applications such as stereo vision, object recognition, and many others, but this algorithm is computationally intensive. In order to solve this problem, we propose a matching technique optimized for graphics processing units to perform computation with less time. We have applied GPU optimization for the fast computation of keypoints to make our system fast and efficient. The proposed method used self-organizing map feature matching technique to perform efficient matching between different images. The experiments are performed on various images to examine the performance of the system in diverse conditions such as image rotation, scaling, and blurring conditions. The experimental results reveal that the proposed algorithm outperforms the existing feature matching methods resulting into fast feature matching with the optimization of graphics processing unit.

[...] Read more.
Other Articles