• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.456-463
• /
• 2021

In this paper, Ultra Wide-Band(UWB) radar sensor is employed to detect flying drones and avoid collision in dense clutter environments. UWB signal is preferred when high resolution range measurement is required for moving targets. However, the time varying motion of flying drones may increase clutter noises in return signals and deteriorates the target detection performance, which lead to the performance degradation of anti-collision radars. We adopt a dynamic clutter suppression algorithm to estimate the time-varying distances to the moving drones with enhanced accuracy. A modified Constant False Alarm Rate(CFAR) is developed using an adaptive filter algorithm to suppress clutter while the false detection performance is well maintained. For this purpose, a velocity dependent CFAR algorithm is implemented to eliminate the clutter noise against dynamic target motions. Experiments are performed against flying drones having arbitrary trajectories to verify the performance improvement.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.485-492
• /
• 2021

Vision-based autonomous precision landing technology for UAVs requires precise position estimation and landing guidance technology. Also, for safe landing, it must be designed to determine the safety of the landing point against ground obstacles and to guide the landing only when the safety is ensured. In this paper, we proposes vision-based navigation, and algorithms for determining the safety of landing point to perform autonomous precision landings. To perform vision-based navigation, CNN technology is used to detect landing pad and the detection information is used to derive an integrated navigation solution. In addition, design and apply Kalman filters to improve position estimation performance. In order to determine the safety of the landing point, we perform the obstacle detection and position estimation in the same manner, and estimate the speed of the obstacle using LSM. The collision or not with the obstacle is determined based on the CPA calculated by using the estimated state of the obstacle. Finally, we perform flight test to verify the proposed algorithm.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.2
• /
• pp.205-214
• /
• 2004

This paper presents design concepts, specifications and performances of a newly developed Black Box, the reconstruction analysis tool with the records, and results of validation tests. The Black Box can detect crash accidents automatically, and record the vehicle's motion and driver's maneuvers during a pre-defined time period before and after the accident. The items of the Black Box included the acceleration, yaw-rate, vehicle speed, engine RPM, braking application, steering and several digital inputs for recording driver's maneuvers. To detect the accident-related-crash, it is important to understand characteristics of the crash signal, which are much different from those of normal driving. Therefore, analytical considerations should be taken in designing pre-filtering circuits and selecting appropriate parameters for identifying crash accidents. And, it is necessary to select proper combination of motion sensors and design proper pre-filtering circuits in order to describe the vehicle's motion. The analysis algorithms were developed and implemented which can perform accurate detection of crash accidents, simulating pre-crash trajectories, and calculating parameters for reconstruction analysis of crash accidents. The developed Black Box was installed on passenger cars and several types of validation tests were conducted. Through the tests, the accuracy of the recorded data and usefulness of the analysis tool for reconstruction have been validated.

• IE interfaces
• /
• v.19 no.1
• /
• pp.43-52
• /
• 2006

In order to make best use of NC machine tools with minimal labor costs, they need to be in operation 24 hours a day without being attended by human operators except for setup and tool changes. Thus, unattended machining is becoming a dream of every modern machine shop. However, without a proper mechanism for real-time monitoring of the machining processes, unattended machine could lead to a disaster. Investigated in this paper are ways to using PC camera as a real-time monitoring system for unattended NC milling operations. This study defined five machining states READY, NORMAL MACHINING, ABNORMAL MACHINING, COLLISION and END-OF-MACHINING and modeled them with DEVS (discrete event system) formalism. An image change detection algorithm has been developed to detect the table movements and a flame and smoke detection algorithm to detect unstable cutting process. Spindle on/off and cutting status could be successfully detected from the sound signals. Initial experimentation shows that the PC camera could be used as a reliable monitoring system for unattended NC machining.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.76-80
• /
• 2018

In recent years, with the development of automobile technology, smart system technology that assists safe driving has been developed. A camera is installed on the front and rear of the vehicle as well as on the left and right sides to detect and warn of collision risks and hazards. Beyond the technology of simple black-box recording via cameras, we are developing intelligent systems that combine various computer vision technologies. However, most related studies have been developed to optimize performance in laboratory-like environments that do not take environmental factors such as weather into account. In this paper, we propose a method to detect object by restoring visibility in image with degraded image due to weather factors such as fog. First, the image quality degradation such as fog is detected in a single image, and the image quality is improved by restoring using an intermediate value filter. Then, we used an adaptive feature extraction method that removes unnecessary elements such as noise from the improved image and uses it to recognize objects with only the necessary features. In the proposed method, it is shown that more feature points are extracted than the feature points of the region of interest in the improved image.

• Ocean Systems Engineering
• /
• v.10 no.4
• /
• pp.415-434
• /
• 2020

Detecting objects is important for the safe operation of ships, and enables collision avoidance, risk detection, and autonomous sailing. This study proposes a ship detection method from images and videos taken at sea using one of the state-of-the-art deep neural network-based object detection algorithms. A deep learning model is trained using a public maritime dataset, and results show it can detect all types of floating objects and classify them into ten specific classes that include a ship, speedboat, and buoy. The proposed deep learning model is compared to a universal trained model that detects and classifies objects into general classes, such as a person, dog, car, and boat, and results show that the proposed model outperforms the other in the detection of maritime objects. Different deep neural network structures are then compared to obtain the best detection performance. The proposed model also shows a real-time detection speed of approximately 30 frames per second. Hence, it is expected that the proposed model can be used to detect maritime objects and reduce risks while at sea.

• Journal of the Korean Society of Safety
• /
• v.28 no.4
• /
• pp.1-7
• /
• 2013

Train accidents can be directly connected to fatal accidents-collision, derailment, Fire, railway crossing accidents-resulting in tremendous human casualties. First of all, the railway derailment is not only related to most of railway accidents but also it can lead to much more catastrophic accompanying train overtured than other factors. Therefore, it is most important factor to ensure railway safety. some foreign countries have applied to the detector machines(e.g., ultrasonic detector car, sleep mode, current detector, optical sensing, optical fiber). Since it was developed in order to prevent train from being derailed. In korea, the existing track method has been used to monitor rail condition using track circuit. However, we found out it impossible for Communication Based Train Control system(CBTC), recent technology to detect rail condition using balise(data transmission devices) without no track circuit. For this reason, it is needed instantly to develop real-time monitoring system used to detect broken rails. Firstly, this paper presents domestic and international statues analysis of rail breaks technology. Secondly, the composition and the characteristics of the real-time monitoring system. Finally, the evidence that this system could assumed the location and type of broken rails was proved by the experiment of prototype and operation line tests. We concluded that this system can detect rail break section in which error span exist within${\pm}1m$.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.111-116
• /
• 2014

Using only laser range finder to detect the obstacles in an environment that contains transparent obstacles can not guarantee autonomous mobile robot from collision problem. To solve this problem, a mobile robot using laser range finder must be used additional sensor device such as sonar sensor that can detect the transparent obstacle. In this paper, a method is addressed to deal with the problem to detect the transparent obstacles within environment only by using laser range finder for mobile robot. In case the recognized transparent obstacle, the proposed algorithm is to localize the transparent obstacle to extract and process the reflected noise. This algorithm ensures autonomous of mobile robot only using laser range finder. The effectiveness of the proposed algorithm is evaluated by the real mobile robot and real laser range finder experiments with three case studies.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.5
• /
• pp.96-108
• /
• 2017

The current collision warning and avoidance system(CWAS) is one of the representative Advanced Driver Assistance Systems (ADAS) that significantly contributes to improve the safety performance of a vehicle and mitigate the severity of an accident. However, current CWAS mainly have focused on preventing a forward collision in an uninterrupted flow, and the prevention performance near intersections and other various types of accident scenarios are not extensively studied. In this paper, the safety performance of Vision-Sensor (VS) and Radar-Sensor(RS) - based collision warning systems are evaluated near an intersection area with the data from Naturalistic Driving Study(NDS) of Second Strategic Highway Research Program(SHRP2). Based on the VS and RS data, we newly derived sixteen vehicle-to-vehicle accident scenarios near an intersection. Then, we evaluated the detection performance of VS and RS within the derived scenarios. The results showed that VS and RS can prevent an accident in limited situations due to their restrained field-of-view. With an accident prevention rate of 0.7, VS and RS can prevent an accident in five and four scenarios, respectively. For an efficient accident prevention, a different system that can detect vehicles'movement with longer range than VS and RS is required as well as an algorithm that can predict the future movement of other vehicles. In order to further improve the safety performance of CWAS near intersection areas, a communication-based collision warning system such as integration algorithm of data from infrastructure and in-vehicle sensor shall be developed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.141-144
• /
• 1996

This study deals with the problem of the recognition of the preceding vehicles by image processing. The purpose of this study is the development of the equipment to prevent a collision with preceding vehicles during driving the vehicle. In order to decrease the processing time and increase reliability, at first, the traffic lane is extracted. It is determined by detecting road edges and calculating their tangent. After the traffic lane is gotten, the position of the vehicle is searched inside the lane. The features used to detect the vehicles in the algorithm are shadow of the vehicle, vertical edges, horizontal edges, and symmetrical segment. The preceding vehicles are extracted successfully by this method.