Sanjay Sahani

Followers

Following

Public Views

Uploads

Papers by Sanjay Sahani

Multi-Routing in Wireless Sensor Networks Using an Ant Colony Optimization (Aco)

Wireless Sensor Networks consisting of nodes with limited power are deployed to gather useful inf... more Wireless Sensor Networks consisting of nodes with limited power are deployed to gather useful information from the field. In WSNs it is critical to collect the information in an energy efficient manner. Ant Colony Optimization, a swarm intelligence based optimization technique, is widely used in network routing. A novel routing approach using an Ant Colony Optimization algorithm is proposed for Wireless Sensor Networks consisting of stable nodes. Illustrative examples, detailed descriptions and comparative performance test results of the proposed approach are included. The approach is also implemented to a small sized hardware component as a router chip. Simulation results show that proposed algorithm provides promising solutions allowing node designers to efficiently operate routing tasks.

Download

Fast real time object tracking based on normalized cross correlation and importance of thresholding segmentation

2016 International Conference on Recent Trends in Information Technology (ICRTIT), 2016

Real Time object tracking based on template matching is one of the key technologies in image proc... more Real Time object tracking based on template matching is one of the key technologies in image processing. This paper describes a fast template matching algorithm based on Normalized Cross Correlation (NCC) for object tracking in a real time video sequence. It proposes an upper bound criteria, which states that the calculated optimum correlation score at current position is lower than the maximum correlation score obtained in previous position. This condition accelerates the matching process. At the same time, a sufficient termination condition based on an adaptive lower bound threshold function is also applied. It has been proved that, if these conditions are verified simultaneously, then the template can proceed with next reference position without executing the rest of operations in current position. Hence, the redundancy in NCC based object tracking can efficiently be reduced by the proposed conditions. Image segmentation plays an important role for object tracking. In this paper two segmentation techniques have been considered specifically suitable for real time scenario. The performance of the proposed template matching with the two segmentation techniques are proved by real time tracking of various objects captured from large set of video sequences.

Fast template matching based on multilevel successive elimination algorithm

2012 International Conference on Signal Processing and Communications (SPCOM), 2012

This paper proposes a fast template matching method based on multilevel successive elimination al... more This paper proposes a fast template matching method based on multilevel successive elimination algorithm (MSEA) and yields exactly the same result as the exhaustive search algorithm. The algorithm uses two stage searching method to effectively determine the peak point of correlation accurately and robustly. In the first stage, the pixel positions are sampled to form a rectangular or hexagonal grid structure of pixels. The SEA or MSEA is performed on the sampled grid positions. The output of the first stage method is the coordinate at which we get the minimum SAD value. In the second stage, centering on this position, we perform the normalized cross correlation (NCC) with box filtering operation on each pixel position in a window size of 16×16 pixels. The best matching point is obtained at the peak point of NCC value. The method has broad applications in the fields of real time moving object tracking, pattern recognition, machine vision etc. Experimental results are presented here to verify substantial computational savings of the proposed algorithm in comparison with the SEA/MSEA.

Fast normalized cross correlation with early elimination condition

2012 International Conference on Recent Trends in Information Technology, 2012

Real Time target tracking based on template matching has become one of the key technologies in im... more Real Time target tracking based on template matching has become one of the key technologies in image processing technique. This paper describes a fast algorithm based on Normalized Cross Correlation for real time target tracking in a video sequence. The Normalized Cross Correlation is efficiently implemented in practice with the concept of Box Filtering and Integral Image to eliminate redundant computations. But NCC-BF and NCC-II still have lot of redundancies in exhaustive template matching process. This paper proposes an upper bound criteria called as Early Elimination Condition, which states that the calculated optimum correlation score at current position is lower than the maximum correlation score obtained in previous position. This condition accelerates the matching process. In this paper, it has been proved that if this condition is verified, then the template can proceed with next reference position without executing the rest of operations in current position. Hence, the redundancy in NCC based object tracking can be efficiently reduced by our proposed elimination condition described in this paper. The performance of the upper bound criteria is established by tracking various objects captured from large set of video clips.

A fast template matching algorithm for aerial object tracking

2011 International Conference on Image Information Processing, 2011

In this paper, a fast template matching method has been proposed based on coarse fine template ma... more In this paper, a fast template matching method has been proposed based on coarse fine template matching approach. The method is aimed at aerial object tracking. In the process of coarse stage, number of sub image blocks of search area is formed adaptively based on the template size. If the object covers more than seventy percent of search region, then

Online time numeral recognition from monochrome video sequence

2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES, 2013

This paper presents a online multi-font numeral recognition method, whose main aim is to recogniz... more This paper presents a online multi-font numeral recognition method, whose main aim is to recognize overlaid time numeral from video. The portion of the video frame containing the time text is binarized and segmented. Minimum rectangular bounding box is inserted over the isolated numeral images. Euler number of numeral images is found out to initially differentiate into three groups. Then, the numerals are recognised by considering the individual distinct features of each numeral within the group. This recognition process is carried out for all numeral positions. Sometimes it is seen that either due to noise in video sequence or because of poor quality of recorded! online video, some of the numerals are not recognized. Therefore, image correlation is performed as the last step, only for the unrecognized numeral images. Experiments were conducted on various infrared and CCD camera video sequences as well as on commercially available CCTV CCD videos, by taking different sizes and types of fonts. The method provides accuracy of 98.67% and the per-frame computation time is 15.413 ms which is fast as per interlaced video.

Sanjay Sahani

Uploads

Papers by Sanjay Sahani

Log In