• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.289-292
• /
• 2010

Recently human activity recognition using accelerometer has become a prominent research area in proactive computing. In this paper, we present a real-time activity recognition system using a single tri-axial accelerometer. Our system recognizes four primary daily human activities: namely walking, going upstairs, going downstairs, and sitting. The system also computes extra information from the recognized activities such as number of steps, energy expenditure, activity duration, etc. Finally, all generated information is stored in a database as daily log.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.551-554
• /
• 2001

A necessity of remote control robots or various searching robots etc. that accomplish works given instead of human under long distance and extreme environment such as volcano, universe, deep-sea exploration and nuclear power plant etc. is increasing, and so the development and the research regarding these mobile robots are actively progressing. The wheel mobile robot or the track mobile robot have a sufficient energy efficiency under this en, but also have a lot of limits to accomplish works given which are caused from the restriction of mobile ability. Therefore, recently many researches for the walking robot with superior mobility and energy efficiency on the terrain, which is uneven or where obstacles, inclination and stairways exist, have been doing. The research for these walking robots is separated into fields of mechanism and control system, gait research, circumference environment and system condition recognition etc. greatly. It is a research field that the gait research among these is the centralist in actual implementation of walking robot unlike different mobile robots. A research field for gait of walking robot is classified into two parts according to the nature of the stability and the walking speed, static gait or dynamic gait. While the speed of a static gait is lower than that of a dynamic gait, a static gait which moves the robot to maintain a static stability guarantees a superior stability relatively. A dynamic gait, which make the robot walk controlling the instability caused by the gravity during the two leg supporting period and so maintaining the stability of the robot body spontaneously, is suitable for high speed walking but has a relatively low stability and a difficulty in implementation compared with a static gait. The quadruped walking robot has a strong point that can embody these gaits together. In this research, we will develope an autonomous quadruped robot with an asaptibility to the environment by selectry appropriate gait, element such as duty factor, stride, trajectory, etc.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.23-30
• /
• 2005

As a human identification technique, gait recognition has recently gained significant attention. Silhouette-based gait recognition is one of the most popular methods. This paper aims to investigate features that determine the style of walking in silhouette-based gait recognition. Gait can be represented using two cues: static(shape) cue and dynamic(motion) cue. Most recently, research results have been reported in the literature that the characteristics of gait are mainly determined by static cue but not affected by dynamic cue. Unlike this, experimental results in this paper verifies that dynamic cue is as important as and in many cases more important than static cue. For experiments, we use two well-blown gait databases: UBC DB and Southampton Small DB. The images of UBC DB correspond to the 'ordinary' style of walking. The images of Southampton Small DB correspond to the 'disguised' (not ordinary by wearing special clothes or bags) style of walking. As results of experiments, the recognition rate was 100% by static cue and $95.2\%$ by dynamic cue for the images of UBC DB. For the images of Southampton Small DB, the recognition rate was $50.0\%$ by static cue and $55.8\%$ by dynamic cue. The risk against correct recognition was 0.91 by static cue and 0.97 by dynamic cue for the images of UBC DB. For the images of Southampton Small DB, the risk was 0.98 by static cue and 0.98 by dynamic cue. Consequently, the characteristics of ordinary gait are mainly determined by static cue but that of disguised gait by dynamic cue.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.554-562
• /
• 2023

This research offers a sports video action recognition approach based on the fish swarm algorithm in light of the low accuracy of existing sports video action recognition methods. A modified fish swarm algorithm is proposed to construct invariant features and decrease the dimension of features. Based on this algorithm, local features and global features can be classified. The experimental findings on the typical sports action data set demonstrate that the key details of sports action can be successfully retained by the dimensionality-reduced fusion invariant characteristics. According to this research, the average recognition time of the proposed method for walking, running, squatting, sitting, and bending is less than 326 seconds, and the average recognition rate is higher than 94%. This proves that this method can significantly improve the performance and efficiency of online sports video motion recognition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2339-2345
• /
• 2011

Gait recognition is the method to identify the person who walks in front of camera using characteristics of individuals by a sequence of images of walking people. The accuracy of biometric such as fingerprint or iris is very high; however, to provide information needs downsides which allow users to direct contact or close-up, etc. There have been many studies in gait recognition because it could capture images and analysis characteristics far from a person. In order to recognize the gait of person needs a continuous sequence of walking which can be distinguished from the individuals should be extracted features rather than an single image. Therefore, this paper proposes a method of gait recognition that the motion of objects in sequence is described the characteristics of a shape sequence descriptor, and through a variety of experiments can show possibility as a recognition technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2148-2161
• /
• 2019

In this paper, we present a real-time cattle action recognition algorithm to detect the estrus phase of cattle from a live video stream. In order to classify cattle movement, specifically, to detect the mounting action, the most observable sign of the estrus phase, a simple yet effective feature description exploiting motion history images (MHI) is designed. By learning the proposed features using the support vector machine framework, various representative cattle actions, such as mounting, walking, tail wagging, and foot stamping, can be recognized robustly in complex scenes. Thanks to low complexity of the proposed action recognition algorithm, multiple cattle in three enclosures can be monitored simultaneously using a single fisheye camera. Through extensive experiments with real video streams, we confirmed that the proposed algorithm outperforms a conventional human action recognition algorithm by 18% in terms of recognition accuracy even with much smaller dimensional feature description.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.5
• /
• pp.481-485
• /
• 2014

In service robots, a number of human movements are analyzed using a variety of sensors. Vibration signals from walking movements of a human provide useful information about the distance and the movement direction of the human. In this paper, we measure the intensity of vibrations and detect both human walking pace and direction. In our experiments, vibration signals detected by microphone sensors provide good estimation of the distance and direction of a human movement. This can be applied to HRI (Human-Robot Interaction) technology.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1046-1050
• /
• 2003

In general, conventional user identification systems require users to carry a TAG or badge or to remember ID and password. Though biometric identification systems may relieve these problems, they are susceptible to environmental noise to some degree. We propose a natural user identification system, ubiFloor, exploiting user's walking pattern to identify the user. The system identifies a user, while tracking the user's location, with a set of simple ON/OFF switch sensors or equipments. Experimental results show that the proposed system can recognize the registered users at the rate of 92%. Future improvement in recognition rate may be achieved by combining other sensors such as camera, microphone, etc.

• Knowledge Management Research
• /
• v.19 no.1
• /
• pp.59-77
• /
• 2018

The tourism industry is now changing to smart tourism, which maximizes tourists' overall tourism experience with the use of advanced mobile technologies and emphasizes the utilization of tourism information. Despite the quantitative expansion of the tourism industry, there is a lack of academic and practical discussion on tourism safety. Especially, in the context of walking tourism, tourists are more likely to be exposed to natural or social disasters and emergencies. Therefore, it is necessary to build a system that can provide walking tourists with safety information not only on dangerous factors which are anticipated to be confronted during a walking trip in advance but also on specific dangers in real time. Under the circumstances, this study seeks to identify the types of tourism safety information that can be offered by using publicly available open data, drawing on the safety information framework on the walking tourism that is presented in Choi et al. (2017)'s study. More specifically, this study focuses on the use of open data which is provided by the Korean government. Furthermore, this study verifies the types of safety information that are most urgently needed in walking travel situations. Specifically, this study aims to derive the importance and priority of each type of safety information for a walking trip by applying the analytic hierarchy process (AHP) analysis. For this, we collected 35 questionnaires from walking tour operators (practitioners) and walking tourists. The main results are as follows. First, natural disaster information is the most important factor in the top-level factor of safety information for walking tourists, followed by social disaster, life safety, and exhibition (security crisis) information. Second, information on natural disasters, environmental pollution, and weather is considered to be important at the sub-level factor. Lastly, the noteworthy result of this study is that the importance of each type of safety information varies depending on the walking tour operators (practitioners) and the walking tourists. That is, there is a recognition difference between the operator (practitioner) and the user in the importance and priority of the safety information of the walking trip. Therefore, it is necessary to develop policies and services reflecting the opinions of potential users when providing safety information so that the most importantly recognized information can be provided first.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1883-1886
• /
• 2003

Gait is defined as "a manor of walking". It can used as a biometric measure to recognize known persons. Gait is an idiosyncratic feature determined by an individual's weight, stride length, and posture combined with characteristic motion. but its feature extracted from images varies with the viewpoint. In this paper, we propose a gait recognition method using a planer homography, which is robust for viewpoint variation. We represent an individual as key-silhouettes. And we endow key-silhouettes with weight calculated using the characteristic of PCA. Experimental result shows that proposed method is robust for viewpoint variation as images synthesised same viewpoint.