This study presents a human action recognition system from multi‐view image sequences. The authors’ approach to human action recognition is based on an estimation of local motion from multiple camera views. The authors propose a new motion descriptor, called histogram of motion intensity and direction, to capture local motion characteristics of human activity. After image normalisation, they estimate motion flow using dense optical flow. Using regular grids, they extract local flow motion and estimate the dominant angle and the intensity of optical flow. The histogram of the dominant angle and its intensity are used as a descriptor for each sequence. After the identification of head direction, they concatenate descriptors in each view as a single feature vector from multiple‐view sequences. Classification based on the proposed feature vector using support vector machine shows better performance than three‐dimensional optical flow‐based approaches, but with lower computational requirements. The authors evaluated action recognition on the publicly available i3DPost and the Institut de Recherche en Informatique et en Automatique (INRIA) Xmas Motion Acquisition Sequences database. Experimental results show promising state‐of‐the‐art results and validate the advanced performance of the authors’ approach.

This paper presents a smart lighting control system based on human motion tracking. Proper illumination and color temperature depend on human activities. A smart lighting system that provides automatic control of lighting illumination and color temperature needs to track human motion and understand human activities. Infrared and thermal spectrum provides useful information robust to the lighting condition. Depth information can be acquired independently of the lighting condition and it is relatively easy to detect humans independent of their clothing, and skin color. Commercial depth cameras or thermal cameras were used for accurate tracking and for estimating human behavior. The activity modes can be estimated using the human motion tracking results from depth cameras and from thermal cameras. Multiple depth cameras were used to detect human subject motion in a large area. The activity modes such as study mode and watching TV mode were estimated and the illumination and color temperature of the LED lighting system were controlled in real time according to the estimated activity.

No abstract

Purpose-The purpose of this paper is to investigate different effects of three network externality factors, i.e. local network size, network strength, and total network size, on online messenger, online community, chat room and e-mail services. Design/methodology/approach-In the paper hypotheses are tested with a regression model using a survey data collected from 107 MBA students at a business school in South Korea. Findings-The paper finds that the three network externality factors have different effects on the users' future usage intention for the four Internet services. Local network size is significant for online messenger services, local network size and network strength are significant for online community services, and total network size is significant for chat room services. For email services, none of the network externality factors are significant. Research limitations/implications-The paper shows that a total network size is an important network externality factor affecting the success of a network. However, users' satisfaction with network services and two additional network externality factors, local network size and network strength, are also important determinants. To generalize the finding, investigations into other network services in other environments and into some offline networks are necessary. Originality/value-The paper shows that depending on types of networks, managers can focus on different important network externality factors in managing their networks.

No abstract