• Smart Structures and Systems
• /
• v.23 no.4
• /
• pp.359-371
• /
• 2019

As part of a structural health monitoring system, the relative geometric relationship between a ship and bridge has been recognized as important for bridge authorities and ship owners to avoid ship-bridge collision. This study proposes a novel computer vision method for the real-time geometric parameter identification of moving ships based on a single shot multibox detector (SSD) by using transfer learning techniques and monocular vision. The identification framework consists of ship detection (coarse scale) and geometric parameter calculation (fine scale) modules. For the ship detection, the SSD, which is a deep learning algorithm, was employed and fine-tuned by ship image samples downloaded from the Internet to obtain the rectangle regions of interest in the coarse scale. Subsequently, for the geometric parameter calculation, an accurate ship contour is created using morphological operations within the saturation channel in hue, saturation, and value color space. Furthermore, a local coordinate system was constructed using projective geometry transformation to calculate the geometric parameters of ships, such as width, length, height, localization, and velocity. The application of the proposed method to in situ video images, obtained from cameras set on the girder of the Wuhan Yangtze River Bridge above the shipping channel, confirmed the efficiency, accuracy, and effectiveness of the proposed method.

• Journal of Korean Ophthalmic Optics Society
• /
• v.8 no.2
• /
• pp.135-151
• /
• 2003

This study compared the effect of Polaroid$^{(R)}$ lenses on binocular vision by assessing visual acuity, stereopsis, and visual evoked potential(VEP), through Polaroid$^{(R)}$, CR 39 and sunglass lenses. The spectral absorptions of Polaroid$^{(R)}$, CR 39 and sunglass lenses were measured using a spectrophotometer (Hitachi. U-3501). The VEP were recorded by the Nicolet system. Thirty normal adult(fifteen males, fifteen females, mean=21.9 years, range=20 to 25) subjects were recorded. The subjects were provided a history including : general health, family health, medication, genetics, allergy and disease. All had normal or corrected to normal acuity with no history of visual disorders. Corrected visual acuity, colour vision and stereopsis were recorded for each subject monocularly and binocularly. Each test was repealed through the sunglass, CR 39, and Polaroid$^{(R)}$ lenses. Subjects viewed the VEP stimulus both monocularly and binocularly through the test lenses while the VEPs were recorded. The results suggest that the binocular visual acuity and stereoacuity is better than with monocular vision. On other hand, the analysis of VEP suggests that the amplitude of wave is smaller when the monocular eye receives the VEP stimulus compared with that when the binocular eye is stimulated by the VEP target with the sunglass, CR 39, and Polaroid$^{(R)}$ lens. But, the latency period of each eye was similar to results between the dominant eye and the non-dominant eye by the CR 39, sunglass, and polaroid lens. In conclusion, this study indicates that the binocular vision appears to be better through the brown Polaroid$^{(R)}$ lens than through the other test lenses.

• The Journal of Korea Robotics Society
• /
• v.9 no.4
• /
• pp.197-205
• /
• 2014

As computer vision algorithms are developed on a continuous basis, the visual information from vision sensors has been widely used in the context of simultaneous localization and mapping (SLAM), called visual SLAM, which utilizes relative motion information between images. This research addresses a visual SLAM framework for online localization and mapping in an unstructured seabed environment that can be applied to a low-cost unmanned underwater vehicle equipped with a single monocular camera as a major measurement sensor. Typically, an image motion model with a predefined dimensionality can be corrupted by errors due to the violation of the model assumptions, which may lead to performance degradation of the visual SLAM estimation. To deal with the erroneous image motion model, this study employs a local bundle optimization (LBO) scheme when a closed loop is detected. The results of comparison between visual SLAM estimation with LBO and the other case are presented to validate the effectiveness of the proposed methodology.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.554-556
• /
• 2006

A key component for autonomous mobile robot is to localize ifself. In this paper we suggest a vision-based localization and compensation of robot's location using ultrasound. Mobile robot travels along wall and searches each feature in indoor environment and transformed absolute coordinates of actuality environment using these points and builds a map. And we obtain information of the environment because mobile robot travels along wall. Localzation search robot's location candidate point by ultrasound and decide position among candidate point by features matching.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.4
• /
• pp.33-40
• /
• 2005

This paper represents the stable path recognition by the ultrasonic sensor which gathers navigation environments and the monocular image sensor which generates the self localization information of mobile robot. The proposed ultrasonic sensor and vision camera system recognizes the target and extracts parameters for generating the world map and self localization. Therefore, this paper has developed an indoor mobile robot and has stably demonstrated in a corridor environment.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.65-72
• /
• 2009

This paper presents a vision based localization method for indoor mobile robots using the types of vertices from a monocular image. In the images captured from a camera of a robot, the types of vertices are determined by searching vertical edges and their branch edges with a geometric constraints. For obtaining correspondence between the comers of a 2-D map and the vertex of images, the type of vertices and geometrical constraints induced from a geometric analysis. The vertices are matched with the comers by a heuristic method using the type and position of the vertices and the comers. With the matched pairs, nonlinear equations derived from the perspective and rigid transformations are produced. The pose of the robot is computed by solving the equations using a least-squares optimization technique. Experimental results show that the proposed localization method is effective and applicable to the localization of indoor environments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2015

In this paper, we propose monocular visual simultaneous localization and mapping (SLAM) in the large-scale environment. The proposed method continuously computes the current 6-DoF camera pose and 3D landmarks position from video input. The proposed method successfully builds consistent maps from challenging outdoor sequences using a monocular camera as the only sensor. By using a binary descriptor and metric-topological mapping, the system demonstrates real-time performance on a large-scale outdoor dataset without utilizing GPUs or reducing input image size. The effectiveness of the proposed method is demonstrated on various challenging video sequences.

• Journal of Yeungnam Medical Science
• /
• v.24 no.2
• /
• pp.329-332
• /
• 2007

Solar retinopathy is a rare but well-recognized clinical entity of macular damage, caused by viewing a solar eclipse or direct sun gazing. A 21-year-old man gazed at the sun for approximately thirty seconds at noon using a monocular telescope with his left eye. Forty-eight hours after sun gazing, the patient experienced symptoms of blurred vision and central scotoma in the left eye. Eight months after sun gazing, the visual acuity decreased from 1.0 to 0.1 in the left eye and the fundus examination showed a round, yellowish-white discoid lesion at the left fovea. Fluorescein angiography showed an early window defect in the fovea of the left eye, that persisted without size change during the late phase resulting from atrophy of the retinal pigment epithelium. A small, central scotoma of the left eye was also found in the visual field test. The visual acuity was unchanged at the end of a one-year follow-up period.

• Journal of Korean Ophthalmic Optics Society
• /
• v.15 no.2
• /
• pp.169-174
• /
• 2010

Purpose: The purpose of this study is to evaluate the long-term stability of the improved symptoms and accommodative functions after completion of accommodative therapy. Methods: Seven children (mean age${\pm}$SD: $12{\pm}1.41$ years) who were successfully treated with a vision therapy program for either accommodative insufficiency or infacility were followed for 1 year. The visual symptoms of the subjects were measured by the College of Optometrists in Vision Development Quality of Life (COVD-QOL) checklist, and this was followed by measurement of the monocular and binocular accommodative facility with ${\pm}2.00$ D flipper lens. Results: The mean visual symptoms at the 1 year follow-up examination ($15.14{\pm}8.59$) showed a small increase, but there was no significant difference (p=0.446) from post-therapy ($11.86{\pm}7.22$). There was small regression in the monocular (left eye, $13.86{\pm}3.93cpm$) and binocular ($11.14{\pm}3.13cpm$) accommodative facility at the 1 year follow-up examination, but there were no significant different from the monocular ($15.86{\pm}4.14cpm$, p=0.147) and binocular ($13.21{\pm}3.76cpm$, p=0.066) accommodative facility measurements at post-therapy. Also, every subject met the normative values of ${\geq}7$ cpm for monocular accommodative facility and ${\geq}5$ cpm for binocular accommodative facility in the long-term. Conclusions: There was long-term maintenance of the improved visual symptoms and accommodative functions, and so it is clear that the positive therapeutic effects persist with accommodative therapy.