• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4C
• /
• pp.358-363
• /
• 2010

In IEEE 802.15.4a IR-UWB (Impulse Radio Ultra Wideband) systems, it is crucial to acquire initial carrier/timing synchronization and estimate channel response by exploiting the SYNC symbols embedded in each packet. On the other hand, it is also crucial to detect the SFD pattern followed by the header and data symbols to reliably extract the information contained in the packet. In this paper, we propose a reliable SFD detection scheme utilizing some surplus SYNC symbols in addition to SFD symbols to improve the SFD detection performance.

• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.155-159
• /
• 2015

In this paper, we propose a method for pedestrian detection in real time video and reducing the calculation time of the HOG features for pedestrian detection. When the pedestrian is detected in real-time image, the next frame is detected by using a previously detected region information. In addition, we used a PSO to detect a pedestrian may appear in a region other than a pedestrian is detected quickly. the performance was measured for MIT, INRIA dataset, showed a performance increase of about 82% than the conventional method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.12
• /
• pp.5856-5864
• /
• 2011

In this paper, we propose a moving object detection method in road video sequences acquired from a stationary camera. Our proposed method is based on the background subtraction method using Gaussian pyramids in both the background images and input video frames. It is more effective than pixel based subtraction approaches to reduce false detections which come from the mis-registration between current frames and the background image. And to determine a threshold value automatically in subtracted images, we calculate the threshold value using Otsu's method in each frame and then apply a scalar Kalman filtering to the threshold value. Experimental results show that the proposed method effectively detects moving objects in road video images.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.357-362
• /
• 2019

This paper proposes a model and train method that can real-time detect objects and distances estimation based on a monocular camera by applying deep learning. It used YOLOv2 model which is applied to autonomous or robot due to the fast image processing speed. We have changed and learned the loss function so that the YOLOv2 model can detect objects and distances at the same time. The YOLOv2 loss function added a term for learning bounding box values x, y, w, h, and distance values z as 클래스ification losses. In addition, the learning was carried out by multiplying the distance term with parameters for the balance of learning. we trained the model location, recognition by camera and distance data measured by lidar so that we enable the model to estimate distance and objects from a monocular camera, even when the vehicle is going up or down hill. To evaluate the performance of object detection and distance estimation, MAP (Mean Average Precision) and Adjust R square were used and performance was compared with previous research papers. In addition, we compared the original YOLOv2 model FPS (Frame Per Second) for speed measurement with FPS of our model.

• Computers and Concrete
• /
• v.27 no.1
• /
• pp.29-39
• /
• 2021

This study aimed to develop a method for the determination of the damaged story in reinforced concrete (RC) structure with ambient vibrations, based on modified jerk energy methodology. The damage was taken as a localized reduction in the stiffness of the structural member. For loading, random white noise excitation was used, and dynamic responses from the finite element model (FEM) of 4 story RC shear frame were extracted at nodal points. The data thus obtained from the structure was used in the damage detection and localization algorithm. In the structure, two damage configurations have been introduced. In the first configuration, damage to the structure was artificially caused by a local reduction in the modulus of elasticity. In the second configuration, the damage was caused, using the Elcentro1940 and Kashmir2005 earthquakes in real-time history. The damage was successfully detected if the frequency drop was greater than 5% and the mode shape correlation remained less than 0.8. The results of the damage were also compared to the performance criteria developed in the Seismostruct software. It is demonstrated that the proposed algorithm has effectively detected the existence of the damage and can locate the damaged story for multiple damage scenarios in the RC structure.

• The Journal of Korea Robotics Society
• /
• v.16 no.1
• /
• pp.49-55
• /
• 2021

Recently, a smart farm technology is drawing attention as an alternative to the decline of farm labor population problems due to the aging society. Especially, there is an increasing demand for automatic harvesting system that can be commercialized in the market. Pre-harvest crop detection is the most important issue for the harvesting robot system in a real-world environment. In this paper, we proposed a real-time tomato instance tracking algorithm by using deep learning and probability models. In general, It is hard to keep track of the same tomato instance between successive frames, because the tomato growing environment is disturbed by the change of lighting condition and a background clutter without a stochastic approach. Therefore, this work suggests that individual tomato object detection for each frame is conducted by YOLOv3 model, and the continuous instance tracking between frames is performed by Kalman filter and probability model. We have verified the performance of the proposed method, an experiment was shown a good result in real-world test data.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.437-444
• /
• 2022

This paper proposes a CRC error verification method for SPI and I2C buses of automotive semiconductors. In automotive semiconductors, when an error occurs in communication and an incorrect value is transmitted, fatal results may occur. Unlike LIN communication and CAN communication, in communication such as SPI and I2C, there is no frame for detecting an error, so some definitions of new standards are required. Therefore, in this paper, the CRC error detection mode is newly defined in the SPI and I2C communication protocols, and the verification is presented by designing it in hardware.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.671-682
• /
• 2024

Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.763-767
• /
• 2008

In a speech coding system using excitation source of voiced and unvoiced, it would be involved a distortion of speech qualify in case coexist with a voiced and an unvoiced consonants in a frame. So, We proposed TS(Transition Segment) including unvoiced consonant searching and extraction method in order to uncoexistent with a voiced and unvoiced consonants in a frame. This research present a new method of TS approximate-synthesis by using Least Mean Square and frequency band division. As a result, this method obtain a high quality approximation-synthesis waveforms within TS by using frequency information of 0.547kHz below and 2.813kHz above. The important thing is that the maximum error signal can be made with low distortion approximation-synthesis waveform within TS. This method has the capability of being applied to a new speech coding of Voiced/Silence/TS, speech analysis and speech synthesis.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.98-105
• /
• 2012

This paper describes a new method for a speech playback speed control with high quality. The proposed method provides an adaptive threshold filtering solution for detecting active regions of a speech signal that are followed by playback speed. For a given playback speed, threshold value is adaptively determined with the statistics(:mean and standard deviation) of each frame in speech, and is used to select only active blocks within the current frame. To minimize quality degradation(i.e., pitch degradation) caused due to high-speed playback, the threshold filtering priorly eliminates relatively low-activity blocks including voice and unvoice. Simulation results show that the proposed scheme provides a playback speed control solution with higher quality than SOLA(Synchonized OverLap Add) method using the pitch extraction of speech.