Sirindhorn International Institute of Technology

About: Sirindhorn International Institute of Technology is a based out in . It is known for research contribution in the topics: Supply chain & Combustion. The organization has 1048 authors who have published 1678 publications receiving 30067 citations.

Robust hand tracking in low-resolution video sequences

Abstract: Automatic detection and tracking of human hands in video imagery has many applications. While some success has been achieved in human-computer interaction applications, hand tracking would also be extremely useful in security systems, where it could help the system to understand and predict human actions, intentions, and goals. We have designed and implemented a prototype hand tracking system, which is able to track the hands of moving humans in low resolution video sequences. Our system uses grayscale appearance and skin color information to classify image sub-windows as either containing or not containing a human hand. The prototype's performance is quite promising, detecting nearly all visible hands in a test sequence with a relatively low error rate. In future work we plan to improve the prototype and explore methods for interpreting human gestures in surveillance video.

A memetic algorithm for communication network design taking into consideration an existing network

Abstract: This paper applies a memetic algorithm (MA) to solve a communication network design problem taking into consideration existing network facilities The link capacity assignment problem in packet-switched networks (CA problem) is studied as an example of the network design problem In the CA problem, we focus on the case in which link cost functions are piecewise linear concave, where the unit cost of the newly-installed link capacity is smaller than that of the existing link capacity The MA in this paper is constructed by combining a genetic algorithm (CA) with a local search operator, which is a heuristic design algorithm previously developed for the CA problem Experimental results show that MA solves the CA problem very efficiently, and the solutions obtained by MA are better than those by CA

Retinal vessel segmentation using ensemble classifier of bagged decision trees

Abstract: This paper presents a new supervised method for segmentation of blood vessels in retinal images. This method uses an ensemble system of boot strapped decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological linear transformation, line strength measures and Gabor filter responses. The feature vector encodes information to handle the healthy as well as the pathological retinal image. The method is evaluated on the publicly available DRIVE and STARE databases. Method performance on both sets of test images is better than the 2 nd human observer and other existing methodologies available in the literature. The incurred accuracy, speed, robustness and simplicity make the algorithm a suitable tool for automated retinal image analysis.

Modeling route choice behavior of evacuees in highly urbanized area: A case study of Bagong Silangan, Quezon City, Philippines

Abstract: The need for better evacuation management is becoming inevitably important as a preparedness measure to minimize negative impacts of disasters. One of the essential aspects necessary for evacuation modeling and management is taking into account the travel behavior of evacuees. This study was conducted to understand the evacuation route choice behavior of households affected by the flood that happened during Mid-August of 2013 at Bagong Silangan, Quezon City, Philippines. Three binary logit route choice models with hazard-related and socio-demographic information, as well as evacuation-related decisions as exogenous factors, were estimated and validated. Significant explanatory variables in each model vary. Generally, Models 2 and 3 indicate some level of usefulness in predicting evacuation route choice behavior. Results also provide implications for evacuation planning and management. These models could be incorporated in an evacuation simulation model that is used to analyze and evaluate evacuation plans. The routes taken by evacuees according to their timing can then be the basis of traffic loaded on such routes and assessed whether number of evacuees can be accommodated accordingly. Based on the results, planners can analyze and evaluate appropriate actions such as the evacuation timing, routes and destinations to advise households at risk in case of future floods.