• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1227-1232
• /
• 2015

Several works help make sliding window object detection fast, nevertheless, computational demands remain prohibitive for numerous applications. This paper proposes a fast object detection method based on three strategies: cascade classifier, selective window search and fast feature extraction. Experimental results show that the proposed method outperforms the compared methods and achieves both high detection precision and low computation cost. Our approach runs at 17ms per frame on 640×480 images while attaining state-of-the-art accuracy.

• Journal of Magnetics
• /
• 제21권2호
• /
• pp.204-208
• /
• 2016

This paper demonstrates the key parameter detection for smelting of submerged arc furnace (SAF) based on magnetic field radiation. A magnetic field radiation model for the inner structure of SAF is established based on relative theory of electromagnetic field. A simple equipment of 3D magnetic field detection system is developed by theoretical derivation and simulation. The experiments are carried out under the environment of industrial field and AC magnetic field generated by electrode currents and molten currents in the furnace is reflected outside of the furnace. The experimental results show that the key parameters of smelting including the position of electrode tip, the length of electric arc, and the liquid level of molten bath can be achieved. The computed tomography for SAF can be realized by the detection for smelting.

• International Journal of Advanced Culture Technology
• /
• 제8권4호
• /
• pp.119-128
• /
• 2020

Object detection is an important field of computer vision and is applied to applications such as security, autonomous driving, and face recognition. Recently, as the application of artificial intelligence technology including deep learning has been applied in various fields, it has become a more powerful tool that can learn meaningful high-level, deeper features, solving difficult problems that have not been solved. Therefore, deep learning techniques are also being studied in the field of object detection, and algorithms with excellent performance are being introduced. In this paper, a deep learning-based object detection algorithm used to detect multiple objects in an image is investigated, and future development directions are presented.

• Journal of the Semiconductor & Display Technology
• /
• 제20권2호
• /
• pp.109-114
• /
• 2021

When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.

• Current Optics and Photonics
• /
• 제6권5호
• /
• pp.463-472
• /
• 2022

At certain wavelengths, single-pixel imaging is considered to be a solution that can achieve high quality imaging and also reduce costs. However, achieving imaging of complex scenes is an overhead-intensive process for single-pixel imaging systems, so low efficiency and high consumption are the biggest obstacles to their practical application. Improving efficiency to reduce overhead is the solution to this problem. Salient object detection is usually used as a pre-processing step in computer vision tasks, mimicking human functions in complex natural scenes, to reduce overhead and improve efficiency by focusing on regions with a large amount of information. Therefore, in this paper, we explore the implementation of salient object detection based on single-pixel imaging after a single pixel, and propose a scheme to reconstruct images based on Fourier bases and use U²Net models for salient object detection.

• Structural Monitoring and Maintenance
• /
• 제10권1호
• /
• pp.63-86
• /
• 2023

Structural health monitoring and damage detection are essential for assessing, maintaining, and rehabilitating structures. Most of the existing damage detection approaches compare the current state structural response with the undamaged vibrational structural response, which is unsuitable for old and existing structures where undamaged vibrational responses are absent. One of the approaches for existing structures, numerical model updating/inverse modelling, available in the literature, is limited to numerical studies with high-end software. In this study, an attempt is made to study the effectiveness of the model updating technique, simplify modelling complexity, and economize its usability. The optimization-based detection problem is addressed by using programmable open-sourced code, OpenSees^® and a derivative-free optimization code, NOMAD^®. Modal analysis is used for damage identification of beam-like structures with several damage scenarios. The performance of the proposed methodology is validated both numerically and experimentally. The proposed method performs satisfactorily in identifying both locations and intensity of damage in structures.

• ETRI Journal
• /
• 제39권4호
• /
• pp.592-604
• /
• 2017

Intrusion detection is very important for network situation awareness. While a few methods have been proposed to detect network intrusion, they cannot directly and effectively utilize semi-quantitative information consisting of expert knowledge and quantitative data. Hence, this paper proposes a new detection model based on a directed acyclic graph (DAG) and a belief rule base (BRB). In the proposed model, called DAG-BRB, the DAG is employed to construct a multi-layered BRB model that can avoid explosion of combinations of rule number because of a large number of types of intrusion. To obtain the optimal parameters of the DAG-BRB model, an improved constraint covariance matrix adaption evolution strategy (CMA-ES) is developed that can effectively solve the constraint problem in the BRB. A case study was used to test the efficiency of the proposed DAG-BRB. The results showed that compared with other detection models, the DAG-BRB model has a higher detection rate and can be used in real networks.

• Korean Journal of Remote Sensing
• /
• 제32권4호
• /
• pp.339-351
• /
• 2016

For the safety of sea, it is important to monitor sea fog, one of the dangerous meteorological phenomena which cause marine accidents. To detect and monitor sea fog, Moderate Resolution Imaging Spectroradiometer (MODIS) data which is capable to provide spatial distribution of sea fog has been used. The previous automatic sea fog detection algorithms were focused on detecting sea fog using Terra/MODIS only. The improved algorithm is based on the sea fog detection algorithm by Wu and Li (2014) and it is applicable to both Terra and Aqua MODIS data. We have focused on detecting spring season sea fog events in the Yellow Sea. The algorithm includes application of cloud mask product, the Normalized Difference Snow Index (NDSI), the STandard Deviation test using infrared channel ($STD_{IR}$) with various window size, Temperature Difference Index(TDI) in the algorithm (BTCT - SST) and Normalized Water Vapor Index (NWVI). Through the calculation of the Hanssen-Kuiper Skill Score (KSS) using sea fog manual detection result, we derived more suitable threshold for each index. The adjusted threshold is expected to bring higher accuracy of sea fog detection for spring season daytime sea fog detection using MODIS in the Yellow Sea.

• ETRI Journal
• /
• 제37권6호
• /
• pp.1199-1210
• /
• 2015

Automatic emotion recognition based on facial cues, such as facial action units (AUs), has received huge attention in the last decade due to its wide variety of applications. Current computer-based automated two-phase facial emotion recognition procedures first detect AUs from input images and then infer target emotions from the detected AUs. However, more robust AU detection and AU-to-emotion mapping methods are required to deal with the error accumulation problem inherent in the multiphase scheme. Motivated by our key observation that a single AU detector does not perform equally well for all AUs, we propose a novel two-phase facial emotion recognition framework, where the presence of AUs is detected by group decisions of multiple AU detectors and a target emotion is inferred from the combined AU detection decisions. Our emotion recognition framework consists of three major components - multiple AU detection, AU detection fusion, and AU-to-emotion mapping. The experimental results on two real-world face databases demonstrate an improved performance over the previous two-phase method using a single AU detector in terms of both AU detection accuracy and correct emotion recognition rate.

• ETRI Journal
• /
• 제44권2호
• /
• pp.300-312
• /
• 2022

Recently, public safety services have attracted significant attention for their ability to protect people from crimes. Rapid detection of dangerous situations (that is, abnormal situations where someone may be harmed or killed) is required in public safety services to reduce the time required to respond to such situations. This study proposes a novel danger detection technology based on multimodal data, which includes data from multiple sensors (for example, accelerometer, gyroscope, heart rate, air pressure, and global positioning system sensors), and multilog data, which includes contextual logs of humans and places (for example, contextual logs of human activities and crime-ridden districts) over time. To recognize human activity (for example, walk, sit, and punch), the proposed technology uses multimodal data analysis with an attitude heading reference system and long short-term memory. The proposed technology also includes multilog data analysis for detecting whether recognized activities of humans are dangerous. The proposed danger detection technology will benefit public safety services by improving danger detection capabilities.