• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.5
• /
• pp.409-421
• /
• 2017

Recently Unmanned Aerial Vehicle (UAV) technology offers new opportunities for assessing crop growth condition using UAV imagery. The objective of this study was to select optimal vegetation indices and regression model for estimating of rice growth using UAV images. This study was conducted using a fixed-wing UAV (Model : Ebee) with Cannon S110 and Cannon IXUS camera during farming season in 2016 on the experiment field of National Institute of Crop Science. Before heading stage of rice, there were strong relationships between rice growth parameters (plant height, dry weight and LAI (Leaf Area Index)) and NDVI (Normalized Difference Vegetation Index) using natural exponential function ($R{\geq}0.97$). After heading stage, there were strong relationships between rice dry weight and NDVI, gNDVI (green NDVI), RVI (Ratio Vegetation Index), CI-G (Chlorophyll Index-Green) using quadratic function ($R{\leq}-0.98$). There were no apparent relationships between rice growth parameters and vegetation indices using only Red-Green-Blue band images.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.4
• /
• pp.97-104
• /
• 2005

Vision-based lane sensing systems require accurate and robust sensing performance in lane detection. Besides, there exists trade-off between the computational burden and processor cost, which should be considered for implementing the systems in passenger cars. In this paper, a stereo vision-based lane detection system is developed with considering sensor configuration aspects. An inverse perspective mapping method is formulated based on the relative correspondence between the left and right cameras so that the 3-dimensional road geometry can be reconstructed in a robust manner. A new monitoring model for estimating the road geometry parameters is constructed to reduce the number of the measured signals. The selection of the sensor configuration and specifications is investigated by utilizing the characteristics of standard highways. Based on the sensor configurations, it is shown that appropriate sensing region on the camera image coordinate can be determined. The proposed system is implemented on a passenger car and verified experimentally.

• Tunnel and Underground Space
• /
• v.20 no.6
• /
• pp.421-433
• /
• 2010

The digital images to be used for digital vision measurement like digital face mapping and photogrammetric monitoring in construction could be influenced by various conditions such as a kind of light, the intensity of radiation, camera set-up and so on. Because it is very difficult to assess the rock mass from the digital images acquired under different circumstances, some tests and analysis are carried out to modify the images to be suitable and consistent for the digital image optimization. As a result, the recommended conditions for the acquisition of optimized digital images are suggested.

• Journal of Mechanical Science and Technology
• /
• v.19 no.6
• /
• pp.1290-1303
• /
• 2005

In this research, a remote control system has been developed and implemented, which combines autonomous obstacle avoidance in real-time with force-reflective tele-operation. A tele-operated mobile robot is controlled by a local two-degrees-of-freedom force-reflective joystick that a human operator holds while he is monitoring the screen. In the system, the force-reflective joystick transforms the relation between a mobile robot and the environment to the operator as a virtual force which is generated in the form of a new collision vector and reflected to the operator. This reflected force makes the tele-operation of a mobile robot safe from collision in an uncertain and obstacle-cluttered remote environment. A mobile robot controlled by a local operator usually takes pictures of remote environments and sends the images back to the operator over the Internet. Because of limitations of communication bandwidth and the narrow view-angles of the camera, the operator cannot observe shadow regions and curved spaces frequently. To overcome this problem, a new form of virtual force is generated along the collision vector according to both distance and approaching velocity between an obstacle and the mobile robot, which is obtained from ultrasonic sensors. This virtual force is transferred back to the two-degrees-of-freedom master joystick over the Internet to enable a human operator to feel the geometrical relation between the mobile robot and the obstacle. It is demonstrated by experiments that this haptic reflection improves the performance of a tele-operated mobile robot significantly.

• Structural Monitoring and Maintenance
• /
• v.2 no.3
• /
• pp.181-197
• /
• 2015

Assessing the condition of paint on civil structures is an important but challenging and costly task, in particular when it comes to large and complex structures. Current practices of visual inspection are labour-intensive and time-consuming to perform. In addition, this task usually relies on the experience and subjective judgment of individual inspectors. In this study, hyperspectral imaging and classification techniques are proposed as a method to objectively assess the state of the paint on a civil or other structure. The ultimate objective of the work is to develop a technology that can provide precise and automatic grading of paint condition and assessment of degradation due to age or environmental factors. Towards this goal, we acquired hyperspectral images of steel surfaces located at long (mid-range) and short distances on the Sydney Harbour Bridge with an Acousto-Optics Tunable filter (AOTF) hyperspectral camera (consisting of 21 bands in the visible spectrum). We trained a multi-class Support Vector Machines (SVM) classifier to automatically assess the grading of the paint from hyperspectral signatures. Our results demonstrate that the classifier generates highly accurate assessment of the paint condition in comparison to the judgement of human experts.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.159-166
• /
• 2021

COVID-19 has dramatically changed people's daily life. Wearing masks is considered as a simple but effective way to defend the spread of the epidemic. Hence, a real-time and accurate mask wearing detection system is important. In this paper, a deep learning-based mask wearing detection system is developed to help people defend against the terrible epidemic. The system consists of three important functions, which are image detection, video detection and real-time detection. To keep a high detection rate, a deep learning-based method is adopted to detect masks. Unfortunately, according to the suddenness of the epidemic, the mask wearing dataset is scarce, so a mask wearing dataset is collected in this paper. Besides, to reduce the computational cost and runtime, a simple online and real-time tracking method is adopted to achieve video detection and monitoring. Furthermore, a function is implemented to call the camera to real-time achieve mask wearing detection. The sufficient results have shown that the developed system can perform well in the mask wearing detection task. The precision, recall, mAP and F1 can achieve 86.6%, 96.7%, 96.2% and 91.4%, respectively.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• ETRI Journal
• /
• v.41 no.4
• /
• pp.494-505
• /
• 2019

In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real-world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real-world scenarios because they are mainly focused on well-refined datasets. Because the dumping actions in the real-world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person-held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person-held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting-based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real-world videos containing various dumping actions. In addition, the proposed framework is implemented in a real-time monitoring system through a fast online algorithm.

• Current Optics and Photonics
• /
• v.6 no.4
• /
• pp.420-429
• /
• 2022

In this paper, the details and design process of an optical system for space target detection cameras are introduced. The whole system is divided into three structures. The first structure is a short-focus visible light system for rough detection in a large field of view. The field of view is 2°, the effective focal length is 1,125 mm, and the F-number is 3.83. The second structure is a telephoto visible light system for precise detection in a small field of view. The field of view is 1°, the effective focal length is 2,300 mm, and the F-number is 7.67. The third structure is an infrared light detection system. The field of view is 2°, the effective focal length is 390 mm, and the F-number is 1.3. The visible long-focus narrow field of view and visible short-focus wide field of view are switched through a turning mirror. Design results show that the modulation transfer functions of the three structures of the system are close to the diffraction limit. It can further be seen that the short-focus wide-field-of-view distortion is controlled within 0.1%, the long-focus narrow-field-of-view distortion within 0.5%, and the infrared subsystem distortion within 0.2%. The imaging effect is good and the purpose of the design is achieved.

• Journal of the Korean Society of Safety
• /
• v.37 no.5
• /
• pp.7-13
• /
• 2022

Digital image correlation (DIC) is a method used to measure the displacement and strain of structures. It involves transforming and analyzing images before and after deformation using correlation coefficients from irregular light and shade on the surface of structures. In the present study, a microspeckle pattern was applied to the surface of a specimen to identify initial cracking. The test specimen constituted CFRP composites laminated on a curved Al liner The specimen was manufactured by stacking 100 ply of CFRP prepregs in the 0° and 90° directions in a three-point bending test. The equivalent strain was evaluated through DIC analysis after monitoring deformation using a CCD camera. Fracture shape was observed using a microscope. The equivalent strain contour distribution was checked until the maximum load fracture occurred at the center of the test specimen. Variations in the strain indicated the initial occurrence and progression of microcracks. These results can be used to improve the accuracy of detecting micro crack initiation and to achieve structural stability.