• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.309-312
• /
• 2004

본 논문에서는 인간과 로봇의 상호작용을 위해 감정에 기반한 감정 처리 모델을 설계하였다. 감정 재현 기술은 사용자에게 친근감을 주기 위해 로봇 시스템이 제스처, 표정을 통하여 사람이나 동물의 감성과 동작을 표현하는 분야이다. 로봇이 감정을 표현하는 문제에는 많은 심리학적, 해부학적, 공학적 문제가 관련된다. 여러가지 애매모호한 상황임에 불구하고 심리학자인 Ekman과 Friesen에 의해 사람의 여섯 가지 기본 표정이 놀람, 공포, 혐오, 행복감, 두려움, 슬픔은 문화에 영향을 받지 않고 공통적으로 인식되는 보편성을 가지고 있는 것으로 연구됐다. 사람의 행동에 대한 로봇의 반응이 학습되어 감정모델이 결정되고, 그 결과가 행동결정에 영향을 주어 로봇의 행동에 반영되도록 하였다. 본 논문에서는 인간과 로봇과의 상호작용을 통해 정보를 축적하고 인간의 반응에 적응해나 갈 수 있는 감정 처리 모델을 제안한다.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1630-1642
• /
• 2010

Recently, there is an increasing need for developing the technique of Hand Gesture Recognition (HGR), for vision based interface. Since hand gesture is defined as consecutive change of hand posture, developing the algorithm of Hand Posture Recognition (HPR) is required. Among the factors that decrease the performance of HPR, we focus on rotation factor. To achieve rotation invariant HPR, we propose a method that uses the property of video that adjacent frames in video have high correlation, considering the environment of HGR. The proposed method introduces template update of object tracking using the above mentioned property, which is different from previous works based on still images. To compare our proposed method with previous methods such as template matching, PCA and LBP, we performed experiments with video that has hand rotation. The accuracy rate of the proposed method is 22.7%, 14.5%, 10.7% and 4.3% higher than ordinary template matching, template matching using KL-Transform, PCA and LBP, respectively.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.981-996
• /
• 2007

In this paper, we describe a method that can recognize gestures by obtaining motion features information with principal factor analysis from sequential gesture images. In the algorithm, firstly, a two dimensional silhouette region including human gesture is segmented and then geometric features are extracted from it. Here, global features information which is selected as some meaningful key feature effectively expressing gestures with principal factor analysis is used. Obtained motion history information representing time variation of gestures from extracted feature construct one gesture subspace. Finally, projected model feature value into the gesture space is transformed as specific state symbols by grouping algorithm to be use as input symbols of HMM and input gesture is recognized as one of the model gesture with high probability. Proposed method has achieved higher recognition rate than others using only shape information of human body as in an appearance-based method or extracting features intuitively from complicated gestures, because this algorithm constructs gesture models with feature factors that have high contribution rate using principal factor analysis.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.51-56
• /
• 2023

Hand gesture recognition is an essential technology for the people who have difficulties using spoken language to communicate. Electromyogram (EMG), which is often utilized for hand gesture recognition, is expected to have difficulties in hand gesture recognition because its people's movements varies depending on prior postures, but the study on this subject is rare. In this study, we conducted tests to confirm if the prior postures affect on the accuracy of gesture recognition. Data were recorded from 20 subjects with different prior postures. We achieved average accuracies of 89.6% and 52.65% when the prior states between the training and test data were unique and different, respectively. The accuracy was increased when both prior states were considered, which confirmed the need to consider a variety of prior states in hand gesture recognition with EMG.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.619-628
• /
• 2011

Normally vision-based 3D human pose recognition technology is used to method for convey human gesture in HCI(Human-Computer Interaction). 2D pose model based recognition method recognizes simple 2D human pose in particular environment. On the other hand, 3D pose model which describes 3D human body skeletal structure can recognize more complex 3D pose than 2D pose model in because it can use joint angle and shape information of body part. In this paper, we describe a development of interactive game contents using pose recognition interface that using 3D human body joint information. Our system was proposed for the purpose that users can control the game contents with body motion without any additional equipment. Poses are recognized comparing current input pose and predefined pose template which is consist of 14 human body joint 3D information. We implement the game contents with the our pose recognition system and make sure about the efficiency of our proposed system. In the future, we will improve the system that can be recognized poses in various environments robustly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.135-138
• /
• 2006

지능형 홈 네트워크 기술에 대한 도입으로 인해 인간뿐만 아니라 사물들도 컴퓨팅 및 커뮤니케이션 능력을 가지고 주변 상황을 인식하고 판단하여 인간에게 유용한 서비스를 제공하게 될 것이다. 그러나 현 실정에 있어 홈 네트워크 서비스는 단순한 가전기기 제어 관련 서비스만을 제공하고 있다. 다양하게 변화하는 상황에 맞는 상황 적응적 서비스를 제공해야 하는 본 취지에 맞는 서비스를 제공하지 못하고 있다. 따라서 본 논문에서는 사용자의 행위에 규칙성에 기반을 두며, 사용자 행위를 예측하여 지능적으로 동작할 수 있는 근거를 마련할 수 있는 능동적인 서비스를 제공할 수 있는 지능형 제어 모델을 제안하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.360-363
• /
• 2018

Human activity is influenced by various factors, from individual physical features such as vertebral flexion and pelvic distortion to feelings such as joy, anger, and sadness. However, the nature of these behaviors changes over time, and behavioral characteristics do not change much in the short term. The activity data of a person has a time series characteristic that changes with time and a certain regularity for each action. In this study, we applied LSTM, a kind of cyclic neural network to deal with time - series characteristics, to the technique of recognizing activity type and improved recognition rate of activity type by measuring time and parameter optimization of components of LSTM model.