• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.6
• /
• pp.366-371
• /
• 2005

For an autonomous mobile robot localization, it is very important for the robot to be able to recognize indoor environment and match a detected object to an object defined within a map developed either online or of offline. Given the map defining the locations of geometric beacons like wall and corner existing in the robot operation environment, this paper presents a stereo ultrasonic sensor based method practically applicable in recognizing the geometric beacons in real-time. The stereo ultrasonic sensor used in the experiment consists of an ultrasonic transmitter and two ultrasonic receivers placed symmetrically about the transmitter Experimental results are provided to demonstrate that the proposed method is more efficient in recognizing wall and coner than the conventional method of using multiple number of transmitter-receiver pairs.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.716-717
• /
• 2023

최근 자율주행 기술이 큰 주목을 받고 있지만 고가의 센서를 필요로 하기 때문에 연구 및 상용화에 큰 어려움을 겪고 있다. 따라서 본 논문은 쉽게 사용 가능한 딥러닝 2D 객체 인식 모델과 범용 태블릿에 탑재된 저비용 LiDAR 센서를 이용하여 실시간 3D 객체 탐지가 가능한 시스템을 개발한다. 개발된 시스템을 실제 1/10 크기의 차량 모델에 적용하여 테스트해본 결과 개발 용이성과 정확도 측면에서 자율주행을 위한 저비용 센서로 충분히 활용될 가능성이 있음을 확인하였다.

• International Journal of High-Rise Buildings
• /
• v.9 no.4
• /
• pp.335-342
• /
• 2020

This article comes up with a new method which is based on the visual characteristic of the objects and machine learning technology to achieve semi-automated recognition of the personnel, machine & materials of the construction sites. Balancing the real-time performance and accuracy, using Faster RCNN (Faster Region-based Convolutional Neural Networks) with transfer learning method appears to be a rational choice. After fine-tuning an ImageNet pre-trained Faster RCNN and testing with it, the result shows that the precision ratio (mAP) has so far reached 67.62%, while the recall ratio (AR) has reached 56.23%. In other word, this recognizing method has achieved rational performance. Further inference with the video of the construction of Huoshenshan Hospital also indicates preliminary success.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.203-208
• /
• 2021

At the manufacturing site, workers have been operating by inputting materials into the manufacturing process and leaving input records according to the work instructions, but product LOT tracking has been not possible due to many omissions. Recently, it is being carried out as a system to automatically input materials using RFID-Tag. In particular, the initial automatic recognition rate was good at 97 percent by automatically generating input information through RACK (TAG) ID and RACK input time analysis, but the automatic recognition rate continues to decrease due to multi-material RACK, TAG loss, and new product input issues. It is expected that it will contribute to increasing speed and yield (normal product ratio) in the overall production process by improving automatic recognition rate and real-time monitoring through the establishment of artificial intelligent smart factory datasets.

• Plant Journal
• /
• v.17 no.3
• /
• pp.37-41
• /
• 2021

P&ID((Piping and Instrument Diagram) is a key drawing in the engineering industry because it contains information about the units and instrumentation of the plant. Until now, simple repetitive tasks like listing symbols in P&ID drawings have been done manually, consuming lots of time and manpower. Currently, a deep learning model based on CNN(Convolutional Neural Network) is studied for drawing object detection, but the detection time is about 30 minutes and the accuracy is about 90%, indicating performance that is not sufficient to be implemented in the real word. In this study, the detection of symbols in a drawing is performed using 1-stage object detection algorithms that process both region proposal and detection. Specifically, build the training data using the image labeling tool, and show the results of recognizing the symbol in the drawing which are trained in the deep learning model.

• Journal of the Korean Society for Railway
• /
• v.4 no.3
• /
• pp.102-109
• /
• 2001

In this paper, it has a proposal of the RFID reader antenna design that expand the dedicated short-range communication distance between a static object on the ground and a mobile object attached on the moving article. The static reader equipped with micro-processor makes it possible to have a serial communication with a main system, so that much data can be transfer to the main system. An antenna is adjusted in order to a communication, the scale is designed by results values of simulation using matlab. It is achieved to systematically manage logistics, person resource and security system by grasping the information and location of mobile object on the basis that this system receives the information between a static reader and a mobile object tag at 134.2kHz band on real time, also to make it possible the main system to process. Therefore, the reader antenna scale is controlled on the foundation of a magnetic field theory in order to expand a recognition distance of reader and tag, so that can be optimistically recognized with minimizing the direction influence of reader and tag.

• Journal of Digital Convergence
• /
• v.10 no.2
• /
• pp.211-216
• /
• 2012

There are two kinks of processes could detect the laser pointer. One is the process which detects the location of the pointer. the other one is a possibility of dividing with the process which converts the coordinate of the laser pointer which is input in coordinate of the monitor. The previous Mean-Shift algorithm is not appropriately for real-time video image to calculate many quantity. In this paper, we proposed the context driven real-time laser pointer detection and tracking. The proposed method is a possibility of getting the result which is fixed from the situation which the background and the background which are complicated dynamically move. In the actual environment, we can get to give constant results when the object come in, when going out at forecast boundary. Ultimately, this paper suggests empirical application to verify the adequacy and the validity with the proposed method. Accordingly, the accuracy and the quality of image recognition will be improved the surveillance system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.145-152
• /
• 2010

With the recent development of the ubiquitous computing technology, there are increasing interest and research in technologies such as sensors and RFID related to information recognition and location positioning in various ubiquitous fields. Especially, RTLS(Real-Time Locating Services) dealing with spatio-temporal data is emerging as a promising technology. For these reasons, the ISO/IEC published the RTLS standard specification for compatibility and interoperability in RTLS. Therefore, in this paper, we designed and implemented Spatio-temporal Query Processing Systems for efficiently managing and searching the incoming Spatio-temporal data stream of moving objects. Spatio-temporal Query Processing Systems's spatio-temporal middleware maintains interoperability among heterogeneous devices and guarantees data integrity in query processing through real time processing of unceasing spatio-temporal data streams and two way synchronization of spatio-temporal DBMSs. Web Server uses the SOAP(Simple Object Access Protocol) message between client and server for interoperability and translates client's SOAP message into CQL(Continuous Query Language) of the spatio-temporal middleware. Finally, this thesis proved the utility of the system by applying the spatio-temporal Query Processing Systems to a real-time Locating Services.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.89-100
• /
• 2024

In the field of computer vision, models such as You Look Only Once (YOLO) and ResNet are widely used due to their real-time performance and high accuracy. However, to apply these models in real-world environments, factors such as runtime compatibility, memory usage, computing resources, and real-time conditions must be considered. This study compares the characteristics of three deep model runtimes: ONNX Runtime, TensorRT, and OpenCV DNN, and analyzes their performance on two models. The aim of this paper is to provide criteria for runtime selection for practical applications. The experiments compare runtimes based on the evaluation metrics of time, memory usage, and accuracy for vehicle license plate recognition and classification tasks. The experimental results show that ONNX Runtime excels in complex object detection performance, OpenCV DNN is suitable for environments with limited memory, and TensorRT offers superior execution speed for complex models.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.135-136
• /
• 2017

When driving at night time environment, the whole body of transports does not visible to us. Due to lack of light conditions, there are only two options, which is clearly visible their taillights and break lights. To improve the recognition correctness of vehicle detection, we present an approach to vehicle detection and tracking using finding contour of the object on binary image at night time. Bilateral filtering is used to make more clearly on threshold part. To remove unexpected small noises used morphological opening. In verification stage, paired tail lights are tracked during their existence in the ROI. The accuracy of the test results for vehicle detection is about 93%.