• Journal of Ocean Engineering and Technology
• /
• v.35 no.1
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.

• Computers and Concrete
• /
• v.26 no.5
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.259-265
• /
• 2023

Pedestrian detection is used to effectively detect pedestrians in various situations based on deep learning. Pedestrian detection has difficulty detecting pedestrians due to problems such as camera performance, pedestrian description, height, and occlusion. Even in the same pedestrian, performance in detecting them can differ according to the height of the pedestrian. The height of general pedestrians encompasses various scales, such as those of infants, adolescents, and adults, so when the model is applied to one group, the extraction of data becomes inaccurate. Therefore, this study proposed a pedestrian detection method that fine-tunes the pedestrian area by Refining Layer and Feature Concatenation to consider various heights of pedestrians. Through this, the score and location value for the pedestrian area were finely adjusted. Experiments on four types of test data demonstrate that the proposed model achieves 2-5% higher average precision (AP) compared to Faster R-CNN and DRPN.

• Structural Engineering and Mechanics
• /
• v.69 no.4
• /
• pp.407-416
• /
• 2019

This paper develops a wireless sensor for online fatigue crack detection and failure warning based on crack-induced nonlinear ultrasonic modulation. The wireless sensor consists of packaged piezoelectric (PZT) module, an excitation/sensing module, a data acquisition/processing module, a wireless communication module, and a power supply module. The packaged PZT and the excitation/sensing module generate ultrasonic waves on a structure and capture the response. Based on nonlinear ultrasonic modulation created by a crack, the data acquisition/processing module periodically performs fatigue crack diagnosis and provides failure warning if a component failure is imminent. The outcomes are transmitted to a base through the wireless communication module where two-levels duty cycling media access control (MAC) is implemented. The uniqueness of the paper lies in that 1) the proposed wireless sensor is developed specifically for online fatigue crack detection and failure warning, 2) failure warning as well as crack diagnosis are provided based on crack-induced nonlinear ultrasonic modulation, 3) event-driven operation of the sensor, considering rare extreme events such as earthquakes, is made possible with a power minimization strategy, and 4) the applicability of the wireless sensor to steel welded members is examined through field and laboratory tests. A fatigue crack on a steel welded specimen was successfully detected when the overall width of the crack was around $30{\mu}m$, and a failure warnings were provided when about 97.6% of the remaining useful fatigue lives were reached. Four wireless sensors were deployed on Yeongjong Grand Bridge in Souht Korea. The wireless sensor consumed 282.95 J for 3 weeks, and the processed results on the sensor were transmitted up to 20 m with over 90% success rate.

• Journal of Sensor Science and Technology
• /
• v.31 no.2
• /
• pp.131-137
• /
• 2022

Crimes related to illegal cameras are steadily increasing and causing social problems. Owing to the development of camera technology, the miniaturization and high performance of illegal cameras have caused anxiety among many people. This study is for detecting hidden cameras effectively such that they could not be easily detected by human eyes. An image sensor-based module with 940 nm wavelength infrared detection technology was developed, and an image processing algorithm was developed to selectively detect illegal cameras. Based on the Android smartphone environment, image processing technology was applied to an image acquired from an infrared camera, and a detection sensor module that is less sensitive to ambient brightness noise was studied. Experiments and optimization studies were conducted according to the Gaussian blur size, adaptive threshold size, and detection distance. The performance of the infrared image-based illegal camera detection sensor module was excellent. This is expected to contribute to the prevention of crimes related to illegal cameras.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.8
• /
• pp.99-105
• /
• 2011

This paper is about the design of 3-axis magnetic sensor module which detects parking and moving vehicle. For the sensor module, MR Sensor from Honeywell of which maximum measurement range is ${\pm}2$[G] is used. It also consisted of amplifier and sensor filter and fabricated $30{\times}50$[mm] PCB. Fabricated sensor module produced helmholtz coil of which the length is 1.2[m] of 3-axis to know the performance. It installed sensor module at the center and measured the detected magnetic field. In result, 3-axis were detected as 0.2~0.3[mG] and the drift of the fluctuation of magnetic field was stabilized at 0.03[mG] unit. For the performance evaluation of the vehicle detection, after the entry and parking of the vehicle, variation of magnetic field was measured as 0.323~0.695[G] which the average 0.5[G] of the earth magnetic field was the center and the range of variation was confirmed as 0.37[G]. Therefore, the designed magnetic sensor can be used as the vehicle detection sensor module.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.793-810
• /
• 2022

Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.

• Journal of Korean Library and Information Science Society
• /
• v.46 no.1
• /
• pp.321-344
• /
• 2015

This paper presents a fusion approach to sentiment detection that combines multiple sources of evidence to retrieve blogs that contain opinions on a specific topic. Our approach to finding opinionated blogs on topic consists of first applying traditional information retrieval methods to retrieve blogs on a given topic and then boosting the ranks of opinionated blogs based on the opinion scores computed by multiple sentiment detection methods. Our sentiment detection strategy, whose central idea is to rely on a variety of complementary evidences rather than trying to optimize the utilization of a single source of evidence, includes High Frequency module, which identifies opinions based on the frequency of opinion terms (i.e., terms that occur frequently in opinionated documents), Low Frequency module, which makes use of uncommon/rare terms (e.g., "sooo good") that express strong sentiments, IU Module, which leverages n-grams with IU (I and you) anchor terms (e.g., I believe, You will love), Wilson's lexicon module, which uses a collection-independent opinion lexicon constructed from Wilson's subjectivity terms, and Opinion Acronym module, which utilizes a small set of opinion acronyms (e.g., imho). The results of our study show that combining multiple sources of opinion evidence is an effective method for improving opinion detection performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.1
• /
• pp.109-114
• /
• 2017

In this study, we have developed the active leakage current detection module based on a MSP430 processor, 16bit signal processor. This module can be operated in a desired trip threshold within 0.03 seconds as specified in KS C 4613. This developed module is expected to be applicable as a module for prevention of electric shock in smart distribution panel of smart grid.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.2
• /
• pp.171-181
• /
• 1988

In this study, a packet voice/data terminal(PVDT) that services both voice and data in the packet-switched network is implemented. The software structure of the PVDT is designed according to the OSI 7 layer architecture. The discrimination of voice and data is made in the link layer. Voice packets have priority over data packets in order to minimize the transmission delay, and are serviced by a simple protocol so that the overhead arising form the retransmission of packets may be minimized. The hardware structure of the PVDT is divided into five modules; a master control module, a speech proessing module, a speech activity detection module, a telephone interface module, and an input/output interface module. In addition to the hardware implementation, the optimal reconstruction delay of voice packets to reduce the influence of delay variance is analyzed.