Automatic object searching system based on Real Time SIFT Algorithm

2010 ◽  
Author(s):  
G. Kishore Kumar ◽  
G.V. Raghavendra Prasad ◽  
G. Mamatha
Keyword(s):  
Real Time ◽  
Sift Algorithm ◽  
Object Searching

Improved SIFT Algorithm Based on Mixed Programming

2014 ◽  
Vol 926-930 ◽  
pp. 3058-3062
Author(s):  
Dong Guang Zuo ◽  
Tao Wen ◽  
Zhong Ke Li ◽  
Zhan Liang Li
Keyword(s):  
Real Time ◽  
Image Matching ◽  
Sift Algorithm ◽  
Mixed Programming ◽  
Matching Procedure ◽  
Real Time Applications

In order to improve the generality and real-time of image matching procedure, Visual Studio 2010 and MATLAB R2009a have been used as the platform to research mixed programming and improved SIFT algorithm. In this method, the advantages of C # and Matlab have been combined to reduce the difficulty of programming and to improve programming efficiency. The results show that, improved SIFT algorithm can greatly improve real-time of matching program while guaranteeing good matching rate, its suitable in real-time applications.

An Algorithm Based on SURF for Surveillance Video Mosaicing

2011 ◽  
Vol 267 ◽  
pp. 746-751 ◽  
Author(s):  
Ke You Guo ◽  
Song Ye ◽  
Hu Ming Jiang ◽  
Chun Yu Zhang ◽  
Kai Han
Keyword(s):  
Real Time ◽  
Least Square Method ◽  
Least Square ◽  
Surveillance Video ◽  
Sift Algorithm ◽  
Related Function ◽  
Accuracy Requirement ◽  
Video Mosaicing ◽  
Wide Range ◽  
The Ideal

Using the SIFT algorithm for image mosaicing is the study hotspot in recent years, which is in a wide range of applications. SIFT algorithm of large amount of data and the time-consuming calculation method is not applicable in higher real-time video mosaicing. Firstly using SURF extracts feature points, secondly using the nearest matching method, RANSAC and least-square method solve the homography matrix between images, and finally using normalized covariance related function for obtaining the best effect of the homography matrix. The algorithm not only meets the accuracy requirement of parameter estimation, but also has smaller computation and faster speed than SIFT. It has proved that the algorithm used in this paper has good real-time performance, high accuracy and the ideal effect, which can satisfy the requirement of real-time mosaicking.

scholarly journals Real Time Object Detection using CNN

2018 ◽  
Vol 7 (2.24) ◽  
pp. 33
Author(s):  
Akash Tripathi ◽  
T V. Ajay Kumar ◽  
Tarun Kanth Dhansetty ◽  
J Selva Kumar
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Image Classification ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Small Sample ◽  
Small Data ◽  
Processing Unit ◽  
Sift Algorithm ◽  
Central Processing

Achieving new heights in object detection and image classification was made possible because of Convolution Neural Network(CNN). However, compared to image classification the object detection tasks are more difficult to analyze, more energy consuming and computation intensive. To overcome these challenges, a novel approach is developed for real time object detection applications to improve the accuracy and energy efficiency of the detection process. This is achieved by integrating the Convolutional Neural Networks (CNN) with the Scale Invariant Feature Transform (SIFT) algorithm. Here, we obtain high accuracy output with small sample data to train the model by integrating the CNN and SIFT features. The proposed detection model is a cluster of multiple deep convolutional neural networks and hybrid CNN-SIFT algorithm. The reason to use the SIFT featureis to amplify the model‟s capacity to detect small data or features as the SIFT requires small datasets to detect objects. Our simulation results show better performance in accuracy when compared with the conventional CNN method. As the resources like RAM, graphic card, ROM, etc. are limited we propose a pipelined implementation on an aggregate Central Processing Unit(CPU) and Graphical Processing Unit(GPU) platform.  

Sign in / Sign up

Export Citation Format

Share Document