• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• Journal of Korea Multimedia Society
• /
• v.11 no.4
• /
• pp.454-461
• /
• 2008

This paper is regarding a new input interface based on displacement of mobile devices having a camera. The mobile device can capture consecutive images by the camera, the displacement of the device is estimated by computing the displacement between consecutive images in real-time. The proposed system extracts feature points based on SUSAN comer detector which has low computational complexity. We generate Voronoi domain by using the two-pass algorithm to match extracted features. Finally, the displacement of a mobile device is estimated by calculating SAD values between two consecutive images. We evaluated the performance of the proposed algorithm with 1500 images. True matching accuracy of the proposed algorithm is 90% and the computation for each image is conducted in 5m sec.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.182-182
• /
• 2016

표면영상유속계는 영상분석을 이용하여 홍수시 하천 수표면 유속을 측정하는 비접촉식 유속측정장치이다. 때문에 안전하고 편하게 홍수시 유속을 측정할 수 있으나, 실제 적용상 몇 가지 문제가 있다. 하나는 야간과 악천후에는 영상 촬영이 어렵다는 점이고, 다른 하나는 영상과 실세계와의 좌표변환을 위한 참조점 측량이 반드시 필요하다는 점이다. 본 연구에서는 열영상 카메라를 이용하여 첫 번째 문제를 해결하고, 방향센서(경사계)를 이용하여 두 번째 문제를 해결하여, 언제든지 유속측정이 가능한 실시간 표면영상유속계를 개발하였다. 열영상카메라는 별도의 조명장치없이도 주야간 영상 촬영이 가능하다. 또한 안개의 영향을 받지 않으며, 저유속시 생기는 수면파의 움직임도 잡아낼 수 있는 장점이 있다. 또한, 방향센서를 이용하여 참조점을 이용하지 않고, 좌표변환 관계를 구성할 수 있도록 카메라 모형(camera model)을 구성하였다. 이 카메라 모형에 필요한 외부 변수는 하천수표면과 카메라와의 높이 및 카메라의 두 가지 경사각뿐이다. 여기에 일반적인 카메라 보정에 이용하는 방법으로 구한 카메라 내부 변수를 결합하면 된다. 이렇게 개발한 열영상 표면영상유속계는 실험 수로와 하천 현장에 적용한 결과, 종전보다 훨씬 적용이 간편하며, 매우 높은 정확도로 유속을 측정할 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.189-192
• /
• 2009

This paper presents comparison and analysis of various CFA patterns which are used in single sensor digital camera. There are several patterns which are already used, however, images are sometimes darker or brighter than what human see in real life. Also, images show some noise and blurring. To overcome this problems, many studies on the patterns have been discussed. We carry out experiment with seven patterns including the Bayer pattern. The bilinear method is selected for a interpolation method. The experimental result indicates that image quality is not affected by individual patterns and each pattern requires its own interpolation method.

• Journal of the Optical Society of Korea
• /
• v.17 no.1
• /
• pp.50-56
• /
• 2013

Optical-fiber electronic speckle pattern interferometry (ESPI) is a non-contact, non-destructive examination technique with the advantages of rapid measurement, high accuracy, and full-field measurement. The optical-fiber ESPI system used in this study was compact and portable with the advantages of easy set-up and signal acquisition. By suitably configuring the optical-fiber ESPI system, producing an image signal in a charge-coupled device camera, and periodically modulating beam phases, we obtained phase information from the speckle pattern using a four-step phase shifting algorithm. Moreover, we compared the actual defect size with that of interference fringes which appeared on a screen after calculating the pixel value according to the distance between the object and the CCD camera. Conventional methods of measuring defects are time-consuming and resource-intensive because the estimated values are relative. However, our simple method could quantitatively estimate the defect length by carrying out numerical analysis for obtaining values on the X-axis in a line profile. The results showed reliable values for average error rates and a decrease in the error rate with increasing defect length or pressure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.3025-3047
• /
• 2021

This paper presents the latest Ethernet standardization of in-vehicle network and the future trends of automotive Ethernet technology. The proposed system provides design and optimization algorithms for automotive networking technology related to AVB (Audio Video Bridge) technology. We present a design of in-vehicle network system as well as the optimization of AVB for automotive. A proposal of Reduced Latency of Machine to Machine (RLMM) plays an outstanding role in reducing the latency among devices. RLMM's approach to real-world experimental cases indicates a reduction in latency of around 41.2%. The setup optimized for the automotive network environment is expected to significantly reduce the time in the development and design process. The results obtained in the study of image transmission latency are trustworthy because average values were collected over a long period of time. It is necessary to analyze a latency between multimedia devices within limited time which will be of considerable benefit to the industry. Furthermore, the proposed reliable camera and video streaming through optimized AVB device settings would provide a high level of support in the real-time comprehension and analysis of images with AI (Artificial Intelligence) algorithms in autonomous driving.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.61-68
• /
• 2019

Only the power is converted from AC to DC, in accordance with IEC 60587 based test method, in order to develop the LSR(Liquid Silicone Rubber) insulator material for HVDC, the experiment of Inclined Plate Tracking and Erosion Resistance was conducted. A contaminant (2.5 mS/cm: ammonium chloride) was applied at a rate of 0.3 ml/min and a voltage of ${\pm}3.5kV$, and was evaluated on the basis of 60 mA/2s. The samples were prepared by dispersing LSR/Nano silica_25wt% Composites in LSR. The erosion phenomena of surface discharge and tracking due to DC polarity and negative polarity were measured by image, leakage current maximum and thermal camera. The thermal imaging camera measured the surface temperature generated by the joule heat of the leakage current due to the drying discharge and the conductive current. After the measurement, the tracking and erosion mechanisms were evaluated for erosion weight, erosion depth and erosion length. Positive and negative polarity of LSR/Nano Silica_25wt% composite Tracking and erosion results show that positive polarity is more severe than negative polarity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4160-4173
• /
• 2019

Borescopes facilitate the inspection of areas inside machines and systems that are not directly accessible for visual inspection. They offer real-time, up-close access to confined and hard-to-access spaces without having to dismantle or destructure the object under inspection. Borescopes are ideal instruments for routine maintenance, quality inspection and monitoring of systems and structures. The main application being fault or defect detection, it is useful to have measuring capability to quantify object dimensions in a target area. High-end borescopes use multi-optic solutions to provide measurement information of viewed objects. Multi-optic solutions can provide accurate measurements at the expense of structural complexity and cost increase. Measuring functionality is often unavailable in low-end, single camera borescopes. In this paper, a single camera measurement solution that enables the size estimation of viewed objects is proposed. The proposed solution computes and overlays a scaled grid of known spacing value over the screen view, enabling the human inspector to estimate the size of the objects in view. The proposed method provides a simple means of measurement that is applicable to low-end borescopes with no built-in measurement capability.