• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.28.4-28
• /
• 2001

This paper proposes an IR camera system that performs the task of removing mines for humanitarian purposes. Because of the high risks involved, it is necessary to conduct mine detection from the most remote endeavoring. By mating use of infrared ray (IR) cameras, scattered mines can be detected from remote locations. In the case of mines buried in the ground, detection is possible if the peripheral temperature difference is large enough between the ground and mine weapon. As one of the world´s advanced nations in sensor technology, Japan should promote surveys and studies for detecting mines safely by using its advanced remote sensing technologies.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.3
• /
• pp.257-269
• /
• 2023

This paper presents a method for detecting faults in data obtained from the Automatic Identification System (AIS) of surface vessels. The data include latitude, longitude, Speed Over Ground (SOG), and Course Over Ground (COG). We derive two methods that utilize two models: a constant state model and a derivative augmented model. The constant state model incorporates noise variables to account for state changes, while the derivative augmented model employs explicit variables such as first or second derivatives, to model dynamic changes in state. Generally, the derivative augmented model detects faults more promptly than the constant state model, although it is vulnerable to potentially overlooking faults. The effectiveness of this method is validated using AIS data collected at a harbor. The results demonstrate that the proposed approach can automatically detect faults in AIS data, thus offering partial assistance for enhancing navigation safety.

• Journal of the Korean association of regional geographers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2008

The first pine wilt damage in Korea, which called AIDS of pine, was found out at Mt. Geumjeong of Pusan province in 1988. The damage area spread 53's city, Gun, Gu throughout the Gyeongsangnamdo in December 2005 since then find out. The best treatment for these damaged forests is well known as fumigation method after early detection. But early detection by an observer is very difficult because of the damaged forest areas are spread over huge range. Also the access of observer is difficult in condition of Korea topographical characteristic. In this study, an attempt was done to investigation about early detection of pine wilt damage using near infrared CCD camera.

• Smart Structures and Systems
• /
• v.9 no.3
• /
• pp.253-271
• /
• 2012

Finite element (FE) model updating is a useful tool for global damage detection technique, which identifies the damage of the structure using measured vibration data. This paper presents the application of a finite element model updating method to detect the damage of a small-scale reinforced concrete building structure using measured acceleration data from shaking table tests. An iterative FE model updating strategy using the least-squares solution based on sensitivity of frequency response functions and natural frequencies was provided. In addition, a side constraint to mitigate numerical difficulties associated with ill-conditioning was described. The test structure was subjected to six El Centro 1942 ground motion histories with different Peak Ground Accelerations (PGA) ranging from 0.06 g to 0.5 g, and analytical models corresponding to each stage of the shaking were obtained using the model updating method. Flexural stiffness values of the structural members were chosen as the updating parameters. In model updating at each stage of shaking, the initial values of the parameter were set to those obtained from the previous stage. Severity of damage at each stage of shaking was determined from the change of the updated stiffness values. Results indicated that larger reductions in stiffness values occurred at the slab members than at the wall members, and this was consistent with the observed damage pattern of the test structure.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.3
• /
• pp.57-67
• /
• 2015

In this paper, we proposed the geolocation method using target detection information in infrared images. Our method was applied to geolocation system of hostile targets in ground-to-ground field. The major distortion that has bad effect of geolocation was composed of optic, topography, GPS(Global Positioning System) and IMU(Inertial Measurement Unit) of reconnaissance unit. We proposed enhanced geolocation method to cope with optic and topography distortion using polynomial fitting and slant-range calculation model to overcome earth curvature problem, and the result showed that the performance of our method was good for system requirements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1264-1286
• /
• 2018

In this paper, a novel background prior-based salient object detection framework is proposed to deal with images those are more complicated. We take the superpixels located in four borders into consideration and exploit a mechanism based on image boundary information to remove the foreground noises, which are used to form the background prior. Afterward, an initial foreground prior is obtained by selecting superpixels that are the most dissimilar to the background prior. To determine the regions of foreground and background based on the prior of them, a threshold is needed in this process. According to a fixed threshold, the remaining superpixels are iteratively assigned based on their proximity to the foreground or background prior. As the threshold changes, different foreground priors generate multiple different partitions that are assigned a likelihood of being foreground. Last, all segments are combined into a saliency map based on the idea of similarity voting. Experiments on five benchmark databases demonstrate the proposed method performs well when it compares with the state-of-the-art methods in terms of accuracy and robustness.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.203-209
• /
• 2023

One major advantage of ground penetrating radar (GPR) over other field test methods is its ability to obtain subsurface images of roads in an efficient and non-intrusive manner. Not only can the strata of pavement structure be retrieved from the GPR scan images, but also various irregularities, such as cracks and internal cavities. This article introduces a deep learning-based approach, focusing on detecting subsurface cracks by recognizing their distinctive hyperbolic signatures in the GPR scan images. Given the limited road sections that contain target features, two data augmentation methods, i.e., feature insertion and generation, are implemented, resulting in 9,174 GPR scan images. One of the most popular real-time object detection models, You Only Learn One Representation (YOLOR), is trained for detecting the target features for two types of subsurface cracks: bottom cracks and full cracks from the GPR scan images. The former represents partial cracks initiated from the bottom of the asphalt layer or base layers, while the latter includes extended cracks that penetrate these layers. Our experiments show the test average precisions of 0.769, 0.803 and 0.735 for all cracks, bottom cracks, and full cracks, respectively. This demonstrates the practicality of deep learning-based methods in detecting subsurface cracks from GPR scan images.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.7
• /
• pp.739-745
• /
• 2014

In this paper, an evaluation of intelligent CCTV system is proposed with recording and implementation video and video DB. Videos for evaluation are recorded by dividing far, mid and near zone. Video DB has video recording information, detection area, and ground truth in XML format. A video annotation tool is proposed to make ground truth effectively in this paper. A video annotation tool writes ground truths of videos and includes evaluation comparing system alarms with ground truths.