• 한국항행학회논문지
• /
• 제25권4호
• /
• pp.299-304
• /
• 2021

기존의 사람 행동 인식 시스템은 웨어러블 센서, 카메라와 같은 장치를 통해 행동을 탐지하였다. 그러나, 이와 같은 방법들은 추가적인 장치와 비용이 요구되고, 특히 카메라 장치의 경우 사생활 침해 문제가 발생한다. 이미 설치되어 있는 WiFi 신호를 사용한다면 해당 문제를 해결할 수 있다는 장점이 있다. 본 논문에서는 WiFi 신호의 채널 상태 정보를 활용한 CNN 기반 사람 행동 인식 시스템을 제안하고, 가속 하드웨어 구조 설계 및 구현 결과를 제시한다. 해당 시스템은 실내 공간에서 학습 중 나타날 수 있는 네 가지 행동에 대해 정의하였고, 그에 대한 WiFi의 채널 상태 정보를 CNN으로 분류하여 평균 정확도는 91.86%를 보였다. 또한, 가속화를 위해 CNN 분류기에서 연산량이 가장 많은 완전 연결 계층에 대한 가속 하드웨어 구조 설계 결과를 제시하였다. FPGA 디바이스 상에서 성능 평가 결과, 기존 software 기반 시스템 대비 4.28배 빠른 연산 시간을 보임을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 한국음향학회지
• /
• 제26권1호
• /
• pp.25-31
• /
• 2007

본 논문은 음성인식을 위한 음성구간 검출과정에서, 음향에너지 이외에도 화자의 입술움직임 영상신호까지 확인하도록 함으로써, 외부의 음향잡음이 음성인식 대상으로 오인식되는 것을 방지하기 위하여 시도한 것이다. 먼저, PC용 화상카메라를 통하여 영상을 획득하고, 입술움직임 여부가 식별된다. 그리고 입술움직임 영상신호 데이터는 공유메모리에 저장되어 음성인식 프로세스와 공유한다. 한편, 음성인식의 전처리 단계인 음성구간 검출과정에서는 공유메모리에 저장되어 있는 데이터를 확인함으로써 사람의 발성에 의한 음향에너지인지의 여부를 확인하게 된다. 음성인식기와 영상처리기를 연동시켜 실험한 결과, 화상카메라에 대면해서 발성하면 음성인식 결과의 출력까지 정상적으로 진행됨을 확인하였고, 화상카메라에 대면하지 않고 발성하면 음성인식 결과를 출력하지 않는 것을 확인하였다. 이는 음향에너지가 입력되더라도 입술움직임 영상이 확인되지 않으면 음향잡음으로 간주하도록 한 것에 따른 것이다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(C)
• /
• pp.429-432
• /
• 2011

Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from a single view and ignores the issue of view invariance. In this paper, we present an independent Gabor features (IGFs) method comes from the derivation of independent Gabor features in the feature extraction stage. The Gabor transformed human image exhibit strong characteristics of spatial locality, scale and orientation selectivity.

• 한국식품조리과학회지
• /
• 제17권6호
• /
• pp.639-647
• /
• 2001

The purpose of this study was to examine the recognition about food preparation and cooking ability of college students majoring in food & nutrition and others. Data were collected from 729 students residing in Chonbuk area by using a self-administered questionnaire. Food and nutrition major students got significantly higher scores than non-major. ones in the recognition of significance and interest in cooking activity. Both food and nutrition major and non-major female students recognized the necessity of cooking ability than non-major male students. Sixty eight percent of the subjects answered that they have aided often his or her family to cook at home. The students majoring in food and nutrition were interested in various fields such as Korean, western style and fusion food. Most of the respondents teamed how to cook from family at home; however major students have learned cooking not only from family but also from various channels such as culinary school, TV and books. The practical use of knowledge about food science was very low in most respondents. The cooking methods used frequently were sauteing, broiling and deep-fat-frying. This study showed that both food and nutrition major and non-major students recognized the necessity of cooking ability and had interests in cooking activity, but cooking ability of non-major ones was significantly lower than that of major students, and the traditional consciousness that women have to take charge of cooking at home tends to be decreasing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2839-2852
• /
• 2013

Context-awareness is an essential part of ubiquitous computing, and over the past decade video based activity recognition (VAR) has emerged as an important component to identify user's context for automatic service delivery in context-aware applications. The accuracy of VAR significantly depends on the performance of the employed human body segmentation algorithm. Previous human body segmentation algorithms often engage modeling of the human body that normally requires bulky amount of training data and cannot competently handle changes over time. Recently, active contours have emerged as a successful segmentation technique in still images. In this paper, an active contour model with the integration of Chan Vese (CV) energy and Bhattacharya distance functions are adapted for automatic human body segmentation using depth cameras for VAR. The proposed technique not only outperforms existing segmentation methods in normal scenarios but it is also more robust to noise. Moreover, it is unsupervised, i.e., no prior human body model is needed. The performance of the proposed segmentation technique is compared against conventional CV Active Contour (AC) model using a depth-camera and obtained much better performance over it.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.982-990
• /
• 2018

In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.

• 대한지역사회영양학회지
• /
• 제15권5호
• /
• pp.670-678
• /
• 2010

Recognition thresholds for NaCl, sucrose, citric acid, and caffeine, as well as the pleasant concentration of NaCl were assessed in 176 males and 312 females aged 50-88 years. Furthermore, relationships among taste sensitivities, taste preferences, and lifestyles were examined. The taste solutions were presented one after the other in ascending order using the sip-and-spit method. For the recognition thresholds of the 4 basic tastes, women perceived significantly lower concentrations than the men. However, the pleasant concentration of NaCl did not show a gender difference. Sensitivities for the 4 basic tastes did not decrease with age in the men, but they did significantly decrease with age for the women, especially for those above 70 years. For men, regular exercise was positively correlated with sensitivities for sour taste and bitter taste, and physical activity was negatively correlated with the pleasant concentrations of NaCl. For women, who had more physical activity, sensitivities for sweet taste and sour taste were lower compared to the others. This study indicates that the sensitivities for 4 basic tastes in water diminished with age, but pleasant salt concentration did not change with age. Further research on pleasant NaCl concentration is required to determine factors affecting salt preference, in order to decrease salt intake in the elderly.

• ETRI Journal
• /
• 제44권3호
• /
• pp.426-437
• /
• 2022

To understand the multilateral characteristics of human behavior and physiological markers related to physical, emotional, and environmental states, extensive lifelog data collection in a real-world environment is essential. Here, we propose a data collection method using multimodal mobile sensing and present a long-term dataset from 22 subjects and 616 days of experimental sessions. The dataset contains over 10 000 hours of data, including physiological, data such as photoplethysmography, electrodermal activity, and skin temperature in addition to the multivariate behavioral data. Furthermore, it consists of 10 372 user labels with emotional states and 590 days of sleep quality data. To demonstrate feasibility, human activity recognition was applied on the sensor data using a convolutional neural network-based deep learning model with 92.78% recognition accuracy. From the activity recognition result, we extracted the daily behavior pattern and discovered five representative models by applying spectral clustering. This demonstrates that the dataset contributed toward understanding human behavior using multimodal data accumulated throughout daily lives under natural conditions.