• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.8-16
• /
• 2016

In the field of computer vision and robotics, bin picking is an important application area in which object pose estimation is necessary. Different approaches, such as 2D feature tracking and 3D surface reconstruction, have been introduced to estimate the object pose accurately. We propose a new approach where we can use both 2D image features and 3D surface information to identify the target object and estimate its pose accurately. First, we introduce a label detection technique using Maximally Stable Extremal Regions (MSERs) where the label detection results are used to identify the target objects separately. Then, the 2D image features on the detected label areas are utilized to generate 3D surface information. Finally, we calculate the 3D position and the orientation of the target objects using the information of the 3D surface.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.155-156
• /
• 2007

This paper presents the vision-based camber and optimal cutting line detection algorithm for hot-rolling process. It is important to measure the camber of head and tail part of strips because many problems are caused by the camber in the hot-rolling process. The hot-rolling process has time constraints. The camber detection algorithm of head and tail parts requires fast and less complex for satisfying time constraints. The proposed algorithm consists of two parts: measurement of the camber in the head and tail part of strips and decision part of the optimal cutting line of hot-rolled strip. First, we obtain the camber value of the strip from the difference between the real center line and the center line of head, tail part. Second, the head and tail part of strips isn't suitable for strips connections. Therefore, the cutting process is needed in the hot-rolling process. The optimal cutting line is determined by the head and tail images obtained from cameras. The algorithm is applied into the vision system with two area cameras, Matrox image processing board and host PC for verification.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.377-382
• /
• 2006

Precision approach and landing of aircraft in a remote landing zone autonomously present several challenges. Firstly, the exact location, orientation and elevation of the landing zone are not always known; secondly, the accuracy of the navigation solution is not always sufficient for this type of precision maneuver if there is no DGPS availability within close proximity. This paper explores an alternative approach for estimating the navigation parameters of the aircraft to the landing area using only time-differenced GPS carrier phase measurement and range measurements from a vision system. Distinct ground landmarks are marked before the landing zone. The positions of these landmarks are extracted from the vision system then the ranges relative to these locations are used as measurements for the extended Kalman filter (EKF) in addition to the precise time-differenced GPS carrier phase measurements. The performance of this navigation algorithm is demonstrated using simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.698-703
• /
• 2006

This paper proposes an approach to search for the odor source using an autonomous mobile robot equipped with vision and odor sensors. The robot is initially navigating around the specific area with vision system until it looks for an object in the camera image. The robot approaches the object found in the field of view and checks it with the odor sensors if it is releasing odor. If so, the odor is classified and localized with the classification algorithm based on neural network The AMOR(Autonomous Mobile Olfactory Robot) was built up and used for the experiments. Experimental results on the classification and localization of odor sources show the validity of the proposed algorithm.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.133-134
• /
• 2022

This study proposed vision artificial intelligence-based automated supervision technology for external insulation and finishing system, and basic research was conducted for it. The automated supervision technology proposed in this study consists of the object detection model (YOLOv5) and the part that derives necessary information based on the object detection result and then determines whether the external insulation-related adhesion regulations are complied with. As a result of a test, the judgement accuracy of the proposed model showed about 70%. The results of this study are expected to contribute to securing the external insulation quality and further contributing to the realization of energy-saving eco-friendly buildings. As further research, it is necessary to develop a technology that can improve the accuracy of the object detection model by supplementing the number of data for model training and determine additional related regulations such as the adhesive area ratio.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.95-105
• /
• 2006

This paper proposes a novel approach to represent the image by using shape descriptor having an information of area. The proposed descriptor is a set of vectors, consists of radius, area and direction parameters in the concentrated center point. Due to the area parameter, we know our descriptor can obtain the information of area. Also, we give an extended shape descriptor to get more detailed representation. To do this, we move the center point of our vision to that point for region of interest. By doing so about all of region of interest, we can get our descriptor for detailed information of the image. From more detailed descriptor, it's natural that it's more efficient fur representation, retrievals and so on. We make it the normalized pattern and expand to improve its quality. The proposed method is invariant to scale, position and rotation. The results show that it can be used efficiently for image representation as we can see in retrievals of silhouette images.

• Journal of Korean Ophthalmic Optics Society
• /
• v.18 no.2
• /
• pp.137-142
• /
• 2013

Purpose: This study was designed to investigate the current status of visual acuity for elementary school students in Muan-gun and to analyze improvements of their visual function after vision training for the elementary school students who have either insufficiency of accommodation or vergence. Methods: Subjective refraction, objective refraction and binocular function were examined for 335 elementary school children from year 1 to year 6 live in Muan area, and then 47 students who have symptoms of binocular dysfunction among them were selected. We analyzed and compared between before and after vision training (VT) in binocular vision function results. Results: The results show that most of the subjects had much problem in near point convergence (NPC) than accommodation. After the vision training, the average of subjects NPC was improved about 5.93 cm, from $11.57 {\pm}1.850$ cm for before VT to $5.66{\pm}0.965$ cm for after VT. After VT positive fusional vergence at near distance after VT was $19.64{\pm}3.66$ $\Delta$, which was as much as double of near phoria. Accommodative amplitude was improved from $10.02{\pm}2.566$ D for before VT to $12.30{\pm}1.397$ D for after VT, which similar to mean of expected accommodative amplitude of 11.27 years old. Conclusions: Among insufficiency of accommodation and vergence NPC was improved specially, and accommodative facility and other ocular functions were also improved. Therefore, it is considered the vision training is very effective to recover from visual function problems.

• Korean Journal of Child Education & Care
• /
• v.19 no.1
• /
• pp.27-43
• /
• 2019

Objective: The purpose of this study is to investigate how the child care teachers experience about professional vision development through participating in video clubs with their peers while watching videos about their interactions with children in the classroom. Methods: We selected three child care teachers in a day care center in Seoul area and conducted the qualitative case study. Video clubs were designed to support the quality of teacher-child interaction by developing child-care teachers' professional vision. And the video clubs used the self-reflection process and cooperative self-reflection process as an important educational method. Results: Teachers were able to experience the change of attention in watching their interaction scene through the 4-time video club participation and to have opportunity for educational (knowledge based) reasoning. Particularly, through participation in the video club, the teacher could pay attention to teachers' intention, teachers' decision making process, and child's intention. In addition, through video club participation, the teachers experienced educational interpretation based on children's thinking and interest; and reasoning through reflective thinking about the results of teaching behavior. This change of professional vision was possible through mutual scaffolding through cooperative reflection among participating teachers. Conclusion/Implications: Based on the results of this study we discussed the importance of the professional vision development of the child care teachers and the effectiveness of the video club for supporting their professional vision development.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1748-1751
• /
• 1991

Generally, we can't acquire clear boundary or area from an image having obscure boundary like allergy image by using Sobel or Lapalace operator. Also, when the image not uniform in some part of a image in brightness, there are difficulties to use the global operator such as histogram, for the contour line doesn't have the same grey level. In this paper, we will propose an algorithm to improve those difficulties. The main idea of the algorithm is that we divide the image into many rectangular parts like a chess board, calculate the average of each part, and decide the local threshold for each pixel on the calculated value. In experiment, we can get the contour and area by this algorithm which is much like to the contour and area measured by a doctor. Also, This algorithm has many advantages such as short processing time and little influences of noises and can be used in the robot vision, etc..