International Conference on Information and Automation 

About: International Conference on Information and Automation is an academic conference. The conference publishes majorly in the area(s): Control theory & Robot. Over the lifetime, 4405 publications have been published by the conference receiving 21200 citations.

A multiple object tracking method using Kalman filter

Abstract: It is important to maintain the identity of multiple targets while tracking them in some applications such as behavior understanding. However, unsatisfying tracking results may be produced due to different real-time conditions. These conditions include: inter-object occlusion, occlusion of the ocjects by background obstacles, splits and merges, which are observed when objects are being tracked in real-time. In this paper, an algorithm of feature-based using Kalman filter motion to handle multiple objects tracking is proposed. The system is fully automatic and requires no manual input of any kind for initialization of tracking. Through establishing Kalman filter motion model with the features centroid and area of moving objects in a single fixed camera monitoring scene, using information obtained by detection to judge whether merge or split occurred, the calculation of the cost function can be used to solve the problems of correspondence after split happened. The algorithm proposed is validated on human and vehicle image sequence. The results shows that the algorithm proposed achieves efficient tracking of multiple moving objects under the confusing situations.

Algorithms for Node Clustering in Wireless Sensor Networks: A Survey

Abstract: The self-organizational ability of ad-hoc Wireless Sensor Networks (WSNs) have led them to be the most popular choice in ubiquitous computing. Clustering sensor nodes and organizing them hierarchically have proven to be an effective method to provide better data aggregation and scalability for the sensor network while conserving limited energy. In this paper we provide a comprehensive analysis of clustering algorithms available for WSN and classify them based on the cluster formation parameters and cluster head (CH) election criteria. We further study the key design challenges and discuss the performance issues related clustering algorithms.

Bluetooth Low Energy (BLE) based mobile electrocardiogram monitoring system

Abstract: A wireless electrocardiogram (ECG) monitoring system is developed which integrates Bluetooth Low Energy (BLE) technology. This BLE-based system is comprised of a single-chip ECG signal acquisition module, a Bluetooth module and a smart-phone. Apple's iPhone 4S is selected as the mobile device platform, which embedded with Bluetooth v4.0, Wi-Fi and iOS. In this paper, the monitoring system is able to acquire ECG signals through 2-lead electrocardiogram (ECG) sensor, transmit the ECG data via the Bluetooth wireless link, process and display the ECG waveform in a smart-phone. The results show that implementation of Bluetooth Low Energy (BLE) technology in the existing ECG monitoring system not only eliminates the physical constraints imposed by hard-wired link but also highly reduces the power consumption of the long-term monitoring system.

Convolutional neural network-based image representation for visual loop closure detection

Abstract: Deep convolutional neural networks (CNN) have recently been shown in many computer vision and pattern recognition applications to outperform by a significant margin state-of-the-art solutions that use traditional hand-crafted features. However, this impressive performance is yet to be fully exploited in robotics. In this paper, we focus one specific problem that can benefit from the recent development of the CNN technology, i.e., we focus on using a pre-trained CNN model as a method of generating an image representation appropriate for visual loop closure detection in SLAM (simultaneous localization and mapping). We perform a comprehensive evaluation of the outputs at the intermediate layers of a CNN as image descriptors, in comparison with state-of-the-art image descriptors, in terms of their ability to match images for detecting loop closures. The main conclusions of our study include: (a) CNN-based image representations perform comparably to state-of-the-art hand-crafted competitors in environments without significant lighting change, (b) they outperform state-of-the-art competitors when lighting changes significantly, and (c) they are also significantly faster to extract than the state-of-the-art hand-crafted features even on a conventional CPU and are two orders of magnitude faster on an entry-level GPU.

Sahana: Overview of a Disaster Management System

Abstract: Large scale disasters bring together a diversity of organizations and produce massive amounts of heterogeneous data that must be managed by these organizations. The lack of effective ICT solutions can lead to a lack of coordination and chaos among these organizations, as they track victims' needs and respond to the disaster. The result can be delayed or ineffective response, the potential wastage of pledged support, imbalances in aid distribution, and a lack of transparency. ICT solutions to manage disasters can potentially improve efficiency and effectiveness. Sahana is a free and open source software (FOSS) application that aims to be a comprehensive solution for information management in relief operations, recovery and rehabilitation. This paper addresses the alignment between FOSS development and humanitarian applications, it then describes the anatomy of the Sahana system. We follow up with a case study of Sahana deployment and lessons learned.