Human Detection Algorithm Research Articles

Haar-like 특징과 템플릿을 이용한 귀 검출

Ear detection in an image processing is the one of the important area in biometrics. In this paper we propose a human ear detection algorithm with side face images. First, we search a face candidate area in an input image by using skin-color model and try to find an ear area based on Haar-like feature. Then, to verity whether it is the ear area or not, we use the template which is excellent object classification compare to recognize the characters in the plate. In this experiment, the proposed method showed that the processing speed is improved by 60% than previous works and the detection success rate is 92%.

Activity Analysis, Summarization, and Visualization for Indoor Human Activity Monitoring

In this work, we study how continuous video monitoring and intelligent video processing can be used in eldercare to assist the independent living of elders and to improve the efficiency of eldercare practice. More specifically, we develop an automated activity analysis and summarization for eldercare video monitoring. At the object level, we construct an advanced silhouette extraction, human detection and tracking algorithm for indoor environments. At the feature level, we develop an adaptive learning method to estimate the physical location and moving speed of a person from a single camera view without calibration. At the action level, we explore hierarchical decision tree and dimension reduction methods for human action recognition. We extract important ADL (activities of daily living) statistics for automated functional assessment. To test and evaluate the proposed algorithms and methods, we deploy the camera system in a real living environment for about a month and have collected more than 200 hours (in excess of 600 G bytes) of activity monitoring videos. Our extensive tests over these massive video datasets demonstrate that the proposed automated activity analysis system is very efficient.

Human detection algorithm for seismic and ultrasonic detectors.

Range detection methodologies for human acoustic signals are discussed. Seismic, passive, and active Doppler ultrasonic sensors are used in the presented methods. The algorithm developed for recognition of human’s presence in the measured signals is based on detection of the specific acoustic signatures resulting from specific human motion characteristics. These signatures have two characteristic times, T1 (the footstep repetition time, which is equal to the time of the whole body periodic motion) and T2 (the footstep duration time). The footstep duration time is equal to the time interval for a single footstep from “heel strike” to “toe slap and weight transfer.” Taking advantage of these times in signal processing for optimization of the signal‐to‐noise ratio and applying a procedure of cadence frequency detection allow recognition of human presence in the analyzed signals. This algorithm was tested and it was experimentally demonstrated that cadence frequencies for walking human and their harmonics for seismic and ultrasonic signatures (passive and active Doppler signatures) were the same. Cadence frequencies were stable and had no detectable variation in time for a regular walking style. This stability feature potentially may be used for human tracking. [Work supported by the Department of the Army, Army Research Office, Contract No. W911NF‐04‐1‐0190.]

3축 가속도 센서를 이용한 보행 횟수 검출 알고리즘과 활동 모니터링

최근 핸드폰, PDA 등에서 가속도센서를 이용한 연구가 많이 증가하고 있다. 본 논문에서는 3축 가속도센서를 이용해 사람이 보행 시 발생하는 데이터를 취득하여 사람의 걸음 수를 계산해 내는 알고리즘과 활동량을 실시간으로 모니터링 할 수 있는 UI 시스템을 개발하였다. 걷기, 제자리 걷기, 뛰기, 천천히 걷기 등의 각 상황별 걸음 수를 정밀하게 측정하기 위해 적응적인 임계값을 사용하는 보행 횟수 검출 알고리즘을 제안하였다. 또 이러한 알고리즘에 의해 얻은 보행 횟수를 이용해서 활동량으로 환산하고 UI화면에 실시간으로 보임으로써 정량화된 활동량으로 실시간 모니터링이 가능하도록 하였다. 실험결과 제안한 보행 횟수 검출 알고리즘이 에너지 기반의 기존의 고정 임계값을 이용하는 알고리즘 보다 <TEX>$5{\sim}10%$</TEX> 정확도가 높은 결과 값을 얻을 수 있었으며 특히, 천천히 걷기에서 정확도가 높아진 것을 확인하였다. The research for a 3-axial accelerometer sensor has increased dramatically in the fields of cellular phone, PDA, etc. In this paper, we develop a human walking detection algorithm using 3-axial accelerometer sensor and a user interface system to show the activity expenditure in real-time. To measure a walking number more correctly in a variety of walking activities including walking, walking in place, running, slow walking, we propose a new walking number detection algorithm using adaptive threshold value. In addition, we calculate the activity expenditure base on counted walking number and display calculated activity expenditure on UI in real-time. From the experimental results, we could obtain that the detection rate of proposal algorithm is higher than that of existing algorithm using a fixed threshold value about <TEX>$5{\sim}10%$</TEX>. Especially, it could be found out high detection rate in walking in place.

An efficient algorithm for human face detection and facial feature extraction under different conditions

In this paper, an efficient algorithm for human face detection and facial feature extraction is devised. Firstly, the location of the face regions is detected using the genetic algorithm and the eigenface technique. The genetic algorithm is applied to search for possible face regions in an image, while the eigenface technique is used to determine the fitness of the regions. As the genetic algorithm is computationally intensive, the searching space is reduced and limited to the eye regions so that the required timing is greatly reduced. Possible face candidates are then further verified by measuring their symmetries and determining the existence of the different facial features. Furthermore, in order to improve the level of detection reliability in our approach, the lighting effect and orientation of the faces are considered and solved.