• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.1
• /
• pp.92-102
• /
• 2017

For an automotive surveillance radar system, fast-chirp train based FMCW (Frequency Modulated Continuous Wave) radar is a very effective method, because clutter and moving targets are easily separated in a 2D range-velocity map. However, pedestrians with low echo signals may be masked by strong clutter in actual field. To address this problem, we proposed in the previous work a clutter cancellation and moving target indication algorithm using the coherent phase method. In the present paper, we initially composed the test set-up using a 24 GHz FMCW transceiver and a real-time data logging board in order to verify this algorithm. Next, we created two indoor test environments consisting of moving human and stationary targets. It was found that pedestrians and strong clutter could be effectively separated when the proposed method is used. We also designed and implemented these algorithms in FPGA (Field Programmable Gate Array) in order to analyze the hardware and time complexities. The results demonstrated that the complexity overhead was nearly zero compared to when the typical method was used.

• PNF and Movement
• /
• v.22 no.1
• /
• pp.43-54
• /
• 2024

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.550-560
• /
• 2018

Many countries have provided support for research and development and implemented policies for Advanced Driver Assistance Systems (ADAS) for enhancing the safety of vehicles. With such efforts, the toll of casualties due to traffic accidents has decreased gradually. Korea has exhibited the lowest toll of casualties due to traffic accidents and is ranked 32nd in mortality among the 35 OECD members. Traffic accidents typically fall into three categories depending on the cause of the accident: vehicle to vehicle (V2V), vehicle to pedestrian (V2P), and vehicle independent. Most accidents are caused by drivers' mistakes in recognition, judgment, or operation. ADAS has been proposed to prevent and reduce accidents from such human errors. Moreover, the global automobile industry has recently been developing various safety measures, but on-road tests are still limited and contain various risks. Therefore, this study investigated the international standards for evaluation tests with regard to the assessment techniques in braking capability to cope with the limitations of on-road tests. A theoretical formula for braking force and a control algorithm are proposed, which were validated by comparing the results with those from an on-road test. These results verified the braking force depending on the functions of ADAS. The risks of on-road tests can be reduced because the proposed theoretical formula allows a prediction of the tendencies.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.1
• /
• pp.33-42
• /
• 2020

In Integration Approach (IA)-based Pedestrian Dead Reckoning (PDR), it is important to detect the exact zero-velocity of the foot with an Inertial Measurement Unit (IMU). By detecting zero-velocity during the stance phase of the foot touching the ground and executing Zero-velocity UPdaTe (ZUPT) at the exact time, stable navigation information can be provided by the PDR. When the pace is fast, however, it is not easy to accurately detect the zero-velocity because of the small stance phase interval and the large signal variance of the corresponding interval. Incorrect zero-velcity detection greatly causes navigation errors of IA-based PDR. In this paper, we propose a method to detect the zero-velocity stably even at high speed by novel buffering of IMU's output data and signal processing of the buffer. And we design a PDR based on this. By analyzing the performance of the proposed Zero-Velocity Detection (ZVD) algorithm and ZVD-based PDR through experiemnts, we confirm that the proposed method can provide accurate navigation information of pedestrians such as firefighters in the indoor space.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.12
• /
• pp.2220-2227
• /
• 2008

The safety equipments of railway level crossing which are installed at intersections between roads and railway lines prevent level crossing accidents by informing all of the vehicles and pedestrians of approaching trains. The intelligent safety system for level crossing which employs information and communication technology has been developed in USA and Japan, etc. But, in Korea, the relevant research has not been performed. In this paper, we analyze the cause of railway level crossing accidents and the inherent problem of the existing safety equipments. Based on analyzed results, we design the intelligent safety system which prevent collision between a train and a vehicle. This system displays train approaching information in real-time at roadside warning devices, informs approaching train of the detected obstacle in crossing areas, and is interconnected with traffic signal to empty the crossing area before train comes. Especially, we present the video based obstacle detection algorithm and verify its performance with prototype H/W since the abrupt obstacles in crossing areas are the main cause of level crossing accidents. We identify that the presented scheme detects both pedestrian and vehicle with good performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.2
• /
• pp.155-162
• /
• 2009

In walking guide robot, a guide vehicle detects an obstacle distribution in the walking space using range sensors, and generates a 3D grid map to map the obstacle information and the tactile display. And the obstacle information is transferred to a blind pedestrian using tactile feedback. Based on the obstacle information a user plans a walking route and controls the guide vehicle. The algorithm for 3D detection of an obstacle distribution and the method of mapping the generated obstacle map and the tactile display device are proposed in this paper. The experiment for the 3D detection of an obstacle distribution using ultrasonic sensors is performed and estimated. The experimental system consisted of ultrasonic sensors and control system. In the experiment, the detection of fixed obstacles on the ground, the moving obstacle, and the detection of down-step are performed. The performance for the 3D detection of an obstacle distribution and space mapping is verified through the experiment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.