scholarly journals A Comparative Analysis of Kernel-Based Target Tracking Methods using Different Colour Feature Based Target Models

2012 ◽  
pp. 106-111
Author(s):  
Nirja Magoch Thakur ◽  
MM Kuber
Keyword(s):  
Comparative Analysis ◽  
Target Tracking ◽  
Tracking System ◽  
Texture Features ◽  
Feature Space ◽  
Color Feature ◽  
Feature Based ◽  
Real Time Tracking ◽  
Colour Feature ◽  
Effective Use

An effective target modeling is the root of a robust and efficient tracking system. Color feature is widely used feature space for target modeling in real time tracking applications because of its computational efficiency and invariance towards change in shape, scale and rotation. The effective use of this feature with kernel-based target tracking can lead to a robust tracking system. This paper provides a comparative analysis of the performance of three variants of kernel-based tracking system using color feature. The simulation results show that the target modeling using transformed background weighted target model will perform efficiently when initialized target has similar color feature with background while the combination of color-texture will be more accurate and robust when texture features are prominently present.

Desease Identification In Plant Leaf Image of Chili (Capsicum Annum (L)) Using Image Processing and Automated Colour Equalization (ACE) Algorithm

2018 ◽  
Vol 1 (2) ◽  
pp. 99
Author(s):  
Basiroh Basiroh
Keyword(s):  
Image Processing ◽  
Agricultural Sector ◽  
Texture Features ◽  
Support Vector ◽  
Color Feature ◽  
Colour Feature ◽  
Agricultural Yield ◽  
Accuracy Of Results ◽  
Ace Algorithm ◽  
Leaf Image

The world of agriculture becomes one of the vital objects and one of the promising business prospects. To obtain optimal agricultural yield, the process of plant care and the way of planting should be really - maximal, because the main key in seeking maximum results in terms of quality and quantity. Harvest failures are the least desirable to farmers and crop failures are the number one scariest specter for cultivating farmers. Today's informatics technology has been developed in an effort to support increased yields in the agricultural sector. This study measured the level of accuracy of results ekstraksi texture and colour feature. This research method using SVM classification ( Support Vector Machine ) seeks image processing through analyzing with Automated Color Equalization (ACE). With this method the accuracy of the extraction results a combination of 80% texture features, color feature extraction, and a combination of 80% color feature texture

A Method of Moving Object Tracking Based on Background Subtraction and Color Feature

2013 ◽  
Vol 710 ◽  
pp. 747-750
Author(s):  
Chun Yang Liu ◽  
Dao Zheng Hou ◽  
Chang An Liu
Keyword(s):  
Target Tracking ◽  
Background Subtraction ◽  
Feature Matching ◽  
Search Algorithm ◽  
Color Difference ◽  
Subtraction Method ◽  
Color Feature ◽  
Multi Target Tracking ◽  
Weak Points ◽  
Feature Based

Background subtraction method is a tracking method only based on motion information. It cannot make a distinction between the foreground objects detected. The feature-based tracking methods need to select the appropriate prediction and search algorithm. But the algorithm complexity and amount of computation is large for the multi-target tracking. Therefore, this paper presents the method based on the combination of background subtraction and color feature. For improving the weak points of the traditional background subtraction method based on grayscale image, it is proposed to use the background subtraction based on RGB color difference. It improves the integrity of the foreground regions that makes better effect of the color feature matching. The experimental results show that in the multi-target tracking applications, the proposed method is simple and easy to implement. It can be used to track the targets with specific color feature and has high robustness.

An Adaptive Clustering and Inter-Cluster Negotiation Protocol for Multi-Target Tracking Based on WSN

2012 ◽  
Vol 457-458 ◽  
pp. 1083-1088
Author(s):  
Zhen Hua Luo ◽  
Jing Zhi Ye ◽  
Wen Feng Luo
Keyword(s):  
Target Tracking ◽  
Real Time ◽  
Tracking System ◽  
Base Station ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Data Synchronization ◽  
Adaptive Clustering ◽  
Multi Target Tracking ◽  
Real Time Tracking

In many wireless sensor networks (WSNs), target tracking is an essential application. This paper studies the real-time target tracking algorithm and the implementation for a multi-target real-time tracking system. The system consists of a wireless sensor network which includes several distributed ultrasonic sensor nodes and a monitoring base station, and two robots as moving targets. To avoid the conflicts in the network, a sensor node task scheduling scheme, and an adaptive clustering and inter-cluster negotiation network protocol (ACICN) are proposed for the system. To cope with distributed and asynchronous measurements, data synchronization and Extended Kalman Filter (EKF) location algorithm are studied for the system. The experiments show that the system can effectively track multi targets simultaneously.

FINANCIAL CONTROLLING IN THE SYSTEM OF FINANCIAL MANAGEMENT

2018 ◽  
Vol 28 (1) ◽  
pp. 137-141
Author(s):  
Petya Yordanova – Dinova
Keyword(s):  
Comparative Analysis ◽  
Financial Management ◽  
Financial Stability ◽  
Business Environment ◽  
Innovative Approach ◽  
Financial Sustainability ◽  
The Common ◽  
The Difference ◽  
Effective Use ◽  
And Control

This paper explores the comparative analysis of the financial controlling, who is a result from the common controlling concept and the financial management. In the specialized literature, financial controlling is seen as an innovative approach to financial management. It is often presented as the most promising instrument of financial diagnostics. Generally speaking, financial controlling is seen as a process of managing the company`s assets which are valued in monetary measures. The difference between the financial management and the financial controlling is that the second covers all functions of management, analysis and control of finances, aiming at maximizing their effective use and increasing the value of the enterprise. Financial controlling is often seen as a function of the common practice of financial management. Its objective is to preserve the financial stability and financial sustainability of enterprises operating in a highly aggressive business environment.

scholarly journals Performance Verification of a Target Tracking System With a Laser Rangefinder

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 30993-31009
Author(s):  
Jihoon Lee ◽  
Suwon Lee ◽  
Youngjun Lee ◽  
Youdan Kim ◽  
Yongjun Heo ◽  
...  
Keyword(s):  
Target Tracking ◽  
Tracking System ◽  
Laser Rangefinder ◽  
Performance Verification

scholarly journals Two Ensemble-CNN Approaches for Colorectal Cancer Tissue Type Classification

2021 ◽  
Vol 7 (3) ◽  
pp. 51
Author(s):  
Emanuela Paladini ◽  
Edoardo Vantaggiato ◽  
Fares Bougourzi ◽  
Cosimo Distante ◽  
Abdenour Hadid ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Digital Pathology ◽  
Texture Features ◽  
Tissue Type ◽  
Cancer Tissue ◽  
Learning Methods ◽  
Feature Based ◽  
Type Classification ◽  
Whole Slide Images

In recent years, automatic tissue phenotyping has attracted increasing interest in the Digital Pathology (DP) field. For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. The development of Whole Slide Images (WSIs) has provided the required data for creating automatic tissue phenotyping systems. In this paper, we study different hand-crafted feature-based and deep learning methods using two popular multi-classes CRC-tissue-type databases: Kather-CRC-2016 and CRC-TP. For the hand-crafted features, we use two texture descriptors (LPQ and BSIF) and their combination. In addition, two classifiers are used (SVM and NN) to classify the texture features into distinct CRC tissue types. For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). Moreover, we propose two Ensemble CNN approaches: Mean-Ensemble-CNN and NN-Ensemble-CNN. The experimental results show that the proposed approaches outperformed the hand-crafted feature-based methods, CNN architectures and the state-of-the-art methods in both databases.

Sign in / Sign up

Export Citation Format

Share Document