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 275
- Downloads 0
Some Improvements on Active Queue Management Mechanism Based on Adaptive Fuzzy Control
Active queue management operates at network nodes to control the number of packets in the queue of nodes, by actively receiving packets when the queue is not full, removing packets when the queue is full or notifying bot...
A Variable Neighborhood Search Algorithm for Solving the Steiner Minimal Tree Problem in Sparse Graphs
Steiner Minimal Tree (SMT) is a complex optimization problem that has many important applications in science and technology; This is a NP-hard problem. Much research has been carried out to solve the SMT problem using ap...
A 802.22b protocol for inter/intra WRAN communication
In this paper we focus on cognitive 802.22b Wireless Regional Area Networks (WRANs). In particular a protocol, named inter intra-resource sharing algorithm (2I-RSA), is presented to address the problem of self coexistenc...
Implementation of NoC on FPGA with Area and Power Optimization
On-chip bus-based communication has many shortcomings to it, including resource sharing, delay, latency and cost (power and area). Network on Chip (NoC) is an innovation that is planned to eliminate the shortcomings to b...
Design and optimization of the Automatic Brown PlantHopper (BPH) light trap surveillance network
Communicating coverage of automatic BPH light trap surveillance network characterizes how well an area is monitored or tracked by automatic light traps. Connectivity is an important required that shows how nodes in a aut...