• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.481-483
• /
• 2023

본 논문에서는 다중 카메라환경에서의 안면인식 기반 영유아 활동 사진 자동 생성 시스템을 개발했다. 개발한 시스템은 어린이집에서 알림장 작성을 위한 촬영하는 동안 보육에 부주의하여 안전사고가 발생하는 것을 방지 할 수 있다. 시스템은 이동식 수집기와 분류 서버로 나뉘어 작동하게 된다. 이동식 수집기는 Raspberry Pi를 이용하였고 초당 1장 내외의 사진을 촬영하여 SAMBA를 사용 공유폴더에 저장한다. 분류 서버에서는 YOLOv5를 사용해 안면을 인식해 분류한다. OpenCV와 TensorFlow-Keras를 통해 분류된 사진에서의 표정을 파악하여 부모에게 전송할 웃는사진만을 분류하여 남겨둔다. 이외의 사진은 /dev/null로 이동하여 삭제된다.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2381-2398
• /
• 2024

The construction of virtual indoor spaces is crucial for the development of metaverses, virtual production, and other 3D content domains. Traditional methods for creating these spaces are often cost-prohibitive and labor-intensive. To address these challenges, we present a pipeline for generating digital twins of real indoor environments from RGB-D camera-scanned data. Our pipeline synergizes space structure estimation, 3D object detection, and the inpainting of missing areas, utilizing deep learning technologies to automate the creation process. Specifically, we apply deep learning models for object recognition and area inpainting, significantly enhancing the accuracy and efficiency of virtual space construction. Our approach minimizes manual labor and reduces costs, paving the way for the creation of metaverse spaces that closely mimic real-world environments. Experimental results demonstrate the effectiveness of our deep learning applications in overcoming traditional obstacles in digital twin creation, offering high-fidelity digital replicas of indoor spaces. This advancement opens for immersive and realistic virtual content creation, showcasing the potential of deep learning in the field of virtual space construction.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.67-78
• /
• 1996

The purpose of this paper is object recognition even in the presence of occlusion by using generalized Hough transform(GHT). The GHT can be considered as a kind of model based object recognition algorithm and is executed in the following two stages. The first stage is to store the information of the model in the form of R-table (Reference table). The next stage is to identify the existence of the objects in the image by using the R-table. The improved GHT method is proposed for the practical vision system. First, in constructing the R-table, we extracted the partial arc from the portion of the whole object boundary, and this partial arc can be used for constructing the R-table. Also, clustering algorithm is employed for compensating an error arised by digitizing an object image. Second, an efficient method is introduced to avoid Ballard's use of 4-D array which is necessary for estimating position, orientation and scale change of an object. Only 2-D array is enough for recognizing an object. Especially, scale token method is introduced for calculating the scale change which is easily affected by camera zoom. The results of our test show that the improved hierarchical GHT method operates stably in the realistic vision situation, even in the case of object occlusion.

• Journal of the HCI Society of Korea
• /
• v.10 no.2
• /
• pp.21-26
• /
• 2015

NUI (Natural User Interface) system interprets the user's natural movement or the signals from human body to the machine. sEMG (surface electromyogram) can be observed when there is any effort in muscle even without actual movement, which is impossible with camera and accelerometer based NUI system. In sEMG based movement recognition system, the minimal number of electrodes is preferred to minimize the inconvenience. We analyzed the decrease in recognition accuracy as decreasing the number of electrodes. For the four kinds of movement intention without movement, extension (up), flexion (down), abduction (right), and adduction (left), the multilayer perceptron classifier was used with the features of RMS (Root Mean Square) from sEMG. The classification accuracy was 91.9% in four channels, 87.0% in three channels, and 78.9% in two channels. To increase the accuracy in two channels of sEMG, RMSs from previous time epoch (50-200 ms) were used in addition. With the RMSs from 150 ms, the accuracy was increased from 78.9% to 83.6%. The decrease in accuracy with minimal number of electrodes could be compensated partly by utilizing more features in previous RMSs.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.426-432
• /
• 2021

Continuous wave (CW) Doppler radar has the advantage of being able to solve the privacy problem unlike camera and obtains signals in a non-contact manner. Therefore, this paper proposes a human activity recognition (HAR) system using CW Doppler radar, and presents the hardware design and implementation results for acceleration. CW Doppler radar measures signals for continuous operation of human. In order to obtain a single motion spectrogram from continuous signals, an algorithm for counting the number of movements is proposed. In addition, in order to minimize the computational complexity and memory usage, binarized neural network (BNN) was used to classify human motions, and the accuracy of 94% was shown. To accelerate the complex operations of BNN, the FPGA-based BNN accelerator was designed and implemented. The proposed HAR system was implemented using 7,673 logics, 12,105 registers, 10,211 combinational ALUTs, and 18.7 Kb of block memory. As a result of performance evaluation, the operation speed was improved by 99.97% compared to the software implementation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.175-182
• /
• 2021

The purpose of this paper is to develop a machine learning-based marine drone to prevent the farming from harmful birds such as ducks. Existing drones have been developed as marine drones to solve the problem of being lost if they collide with birds in the air or are in the sea. We designed a CNN-based learning algorithm to judge harmful birds that appear on the sea by maritime drones operating by autonomous driving. It is designed to transmit video to the control PC by connecting the Raspberry Pi to the camera for location recognition and tracking of harmful birds. After creating a map linked with the location GPS coordinates in advance at the mobile-based control center, the GPS location value for the location of the harmful bird is received and provided, so that a marine drone is dispatched to combat the harmful bird. A bird fighting drone system was designed and implemented.

• Korean Security Journal
• /
• no.50
• /
• pp.61-87
• /
• 2017

National Assembly is a constitutional institution that is required to first consult the will of the people and it should do its effort continuously so that security of citizens using parking lot would be enhanced at the same time while improving parking service in order to increase customer satisfaction of the people. Under this recognition, in this study, Doonchi parking lot of National Assembly under consigned management was first reviewed in a perspective of criminal prevention through environmental design(CPTED) and particularly, fence installation and reinforcement work for securing 'territoriality' and operation of all round shooting camera and installation of No-trespassing warning board at entrance were suggested. Second, it was recommended to change independent control system in which CCTV security system of National Assembly Doonchi parking lot is operated separately from National Assembly safety situation room and integrate it with National Assembly safety situation room(revised to double safety system) and performance of CCTV camera was made to be increased to over 2m. In addition, video recording mode was converted to NVR mode for application to IP camera in the future and in order to avoid dead zone of security monitoring area and based on site inspection result, addition 3 places of newly installing CCTV were indicated. Third, it was recommended to introduce parking fare billing and management system through unmanned equipment in parking lot management and operation.(specialized management of professional parking service provider was reviewed). By doing so, risk of cash handling by charging personnel was removed by reducing current 7 working personnel to 3 and particularly, by converting parking lot management mode being operated temporarily from 9 A.M. to 9 P.M. at present to 24 hours operation mode and providing more specialized parking service, citizens visiting National Assembly were provided with convenience and image of National Assembly was also enhanced. This study was carried out in parallel with various literature and case studies, including data from the Office of the Defense Protection in the National Assembly.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.4
• /
• pp.333-351
• /
• 2023

This study investigates user behavior in library spaces through the lens of AI camera analytics. By leveraging the face recognition and tracking capabilities of AI cameras, we accurately identified the gender and age of visitors and meticulously collected video data to track their movements. Our findings revealed that female users slightly outnumbered male users and the dominant age group was individuals in their 30s. User visits peaked between Tuesday to Friday, with the highest footfall recorded between 14:00 and 15:00 pm, while visits decreased over the weekend. Most visitors utilized one or two specific spaces, frequently consulting the information desk for inquiries, checking out/returning items, or using the rest area for relaxation. The library stacks were used approximately twice as much as they were avoided. The most frequented subject areas were Philosophy(100), Religion(200), Social Sciences(300), Science(400), Technology(500), and Literature(800), with Literature(800) and Religion(200) displaying the most intersections with other areas. By categorizing users into five clusters based on space utilization patterns, we discerned varying objectives and subject interests, providing insights for future library service enhancements. Moreover, the study underscores the need to address the associated costs and privacy concerns when considering the broader application of AI camera analytics in library settings.