A Combination of Off-line and On-line Learning to Classifier Grids for Object Detection
Journal Title: EAI Endorsed Transactions on Context-aware Systems and Applications - Year 2016, Vol 3, Issue 9
Abstract
We propose a new method for object detection by combining off-line and on-line boosting learning to classifier grids based on visual information without human intervention concerned to intelligent surveillance system. It allows for combine information labeled and unlabeled use different contexts to update the system, which is not available at off-line training time. The main goal is to develop an adaptive but robust system and to combine prior knowledge with new information in an unsupervised learning framework that is learning 24 hours a day and 7 days a week. We use co-training strategy by combining off-line and on-line learning to the classifier grids. The proposed method is practically favorable as it meets the requirements of real-time performance, accuracy and robustness. It works well with reasonable amount of training samples and is computational efficiency. Experiments on detection of objects in challenging data sets show the outperforming of our approach.
Authors and Affiliations
Nguyen Dang Binh
Keywords
Related Articles
- EP ID EP45778
- DOI http://dx.doi.org/10.4108/eai.2-5-2016.151208
- Views 256
- Downloads 0
Highlighted Activities of ICTCC 2016
The Second International Conference on Nature of Computation and Communication (ICTCC 2016) is jointly organized by EAI, Nguyen Tat Thanh University (NTTU), and Kien Giang University (KGU) and endorsed by the European Al...
Modified Virtual Air Guitar: A Concept Realized using Image Processing Techniques
Even amidst the hustle and bustle of busy lives, numerous people dream of playing a musical instrument. Unfortunately, many may never get a chance to touch one. But this doesn’t stop them from ‘air drumming’ or playing ‘...
Design guidelines for rapid and simple context-aware mobile application development – an android case study
Presenting a context-aware service and information is a key aspect of ubiquitous computing, but development of such applications is quite complicated. Context-aware applications should be able to obtain raw data fromsens...
Book Titled Nature-Inspired Networking: Theory and Applications: An Introduction
Nature-Inspired Networking: Theory and Applications contains nine original, peer-reviewed chapters reporting on new developments of interest to the nature-inspired networking/computing communities. All chapters contain r...
Fourier Volume Registration based Dense 3D Mapping
In image processing phase correlation has been shown to outperform feature matching in several contexts. In this paper, a novel volume registration technique is proposed for solving the simultaneous localization and mapp...