• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.5
• /
• pp.564-570
• /
• 2014

This paper propose a method to detect and track a human face using depth information as well as color images for detection of drowsy driving. It consists of a face detection procedure and a face tracking procedure. The face detection procedure basically uses the Adaboost method which shows the best performance so far. But it restricts the area to be searched as the region where the face is highly possible to exist. The face detected in the detection procedure is used as the template to start the face tracking procedure. The experimental results showed that the proposed detection method takes only about 23 % of the execution time of the existing method. In all the cases except a special one, the tracking error ratio is as low as about 1 %.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.67-80
• /
• 2017

This paper presents a hole-filling method using extrapolated spatio-temporal background information to obtain a synthesized view. A new temporal background model using non-overlapped patch based background codebook is introduced to extrapolate temporal background information In addition, a depth-map driven spatial local background estimation is addressed to define spatial background constraints that represent the lower and upper bounds of a background candidate. Background holes are filled by comparing the similarities between the temporal background information and the spatial background constraints. Additionally, a depth map-based ghost removal filter is described to solve the problem of the non-fit between a color image and the corresponding depth map of a virtual view after 3-D warping. Finally, an inpainting is applied to fill in the remaining holes with the priority function that includes a new depth term. The experimental results demonstrated that the proposed method led to results that promised subjective and objective improvement over the state-of-the-art methods.

• Journal of the Optical Society of Korea
• /
• v.19 no.3
• /
• pp.303-310
• /
• 2015

An image-space telecentric lens for an intra-oral 3D scanner was designed and fabricated for dental application. Since a telecentric function can provide the same results regardless of image plane position, it helps to realize a more accurate image for an intra-oral scanner. The performance of the designed lens meets the required properties for HD resolution. In particular, lateral color is corrected within 1 pixel. This system achieves depth of focus of more than 3 mm. For user convenience, the developed system consists of a prism part and an imaging part. Both parts are optimized to reduce the front size and weight of the system. In order to make the parallax sights, parallax angle was determined to be 8 degrees between two optical systems.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.485-488
• /
• 2002

In this paper, fuzzy logic controllers are designed for compensation of distance errors. Because we can't know information of the depth in a mono camera, these errors are occurred. Also, they are increased as a target object is to keep away from a center of image. Therefore, the errors for each position of joints of an arm robot should be modeled, but accurate models can't be obtained because of no information of the depth, uncertain feature points of image, parameter uncertainties, and illumination. Hence, fuzzy logic controllers for each error are designed for compensation. This paper consists of color image processing, error modeling, and the controller design. Experimental results are given to verify the effectiveness of our proposed method.

• Journal of the Korean Society of Costume
• /
• v.64 no.3
• /
• pp.142-154
• /
• 2014

The purpose of this study is to classify fashion images of senior women who have emerged as influential customers in the fashion industry. Characteristics of fashion images of senior women are identified by fashion style, preference color, and self-image. With the collected data, the Q group, consisting of Korean women who are in their 50s, was targeted using the Q methodology. The following factors were evaluated through in-depth interviews: fashion style, preference color and self-image. The fashion images of senior women were classified into the following 4 types: Characteristic modern, Reasonable basic, Comfortable contemporary, and Conservative elegance. Those classified fashion image types were influenced by the factors of nobleness, usefulness, personality, fashionableness, and youthfulness in accordance with fashion style, preference color, and self-image. The results of this study may provide basic information for fashion image planning for senior women and meaningful data for redefining and diversifying the concept of senior fashion brand which reflects the generation's changed taste and lifestyle.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2012

'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can't detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.

• Journal of IKEEE
• /
• v.18 no.2
• /
• pp.291-297
• /
• 2014

Since hand gesture recognition was realized thanks to improved image processing algorithms, sign language translation has been a critical issue for the hearing-impaired. In this paper, we extract human hand figures from a real time image stream and detect gestures in order to figure out which kind of hand language it means. We used depth-color calibrated image from the Kinect to extract human hands and made a decision tree in order to recognize the hand gesture. The decision tree contains information such as number of fingers, contours, and the hand's position inside a uniform sized image. We succeeded in recognizing 'Hangul', the Korean alphabet, with a recognizing rate of 98.16%. The average execution time per letter of the system was about 76.5msec, a reasonable speed considering hand language translation is based on almost still images. We expect that this research will help communication between the hearing-impaired and other people who don't know hand language.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.695-698
• /
• 2009

Three-dimensional (3D) shape recognition and distance recognition methods utilizing monocular camera systems have been required for field of virtual-reality, computer graphics, measurement technology and robot technology. There have been many studies regarding 3D shape and distance recognition based on geometric and optical information, and it is now possible to accurately measure the geometric information of an object at short range distances. However, these methods cannot currently be applied to long range objects. In the field of virtual-reality, all visual objects must be presented at widely varying ranges, even though some objects will be hazed over. In order to achieve distance recognition from a landscape image, we focused on the use of aerial perspective to simulate a type of depth perception and investigated the relationship between distance and color perception. The applicability of our proposed method was demonstrated in experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6A
• /
• pp.458-463
• /
• 2012

In this paper, we propose a direct depth map acquisition method for the convergence camera array as well as the parallel camera array. The conventional methods perform image rectification to reduce complexity and improve accuarcy. However, image rectification may lead to unwanted consequences for the convergence camera array. Thus, the proposed method excludes image rectification and directly extracts depth values using the epipolar constraint. In order to acquire a more accurate depth map, occlusion detection and handling processes are added. Reasonable depth values are assigned to the obtained occlusion region by the distance and color differences from neighboring pixels. Experimental results show that the proposed method has fewer limitations than the conventional methods and generates more accurate depth maps stably.

• Journal of Korea Multimedia Society
• /
• v.18 no.9
• /
• pp.1008-1018
• /
• 2015

In this paper, we propose a method that constructs a saliency map in which important regions are accurately specified and the colors of the regions are less influenced by the similar surrounding colors. Our method utilizes LBP(Local Binary Pattern) histogram information to compare and analyze texture information of surrounding regions in order to reduce the effect of color information. We extract the saliency of stereoscopic images by integrating a 2D saliency map with depth information of stereoscopic images. We then measure the distance between two different sizes of the LBP histograms that are generated from pixels. The distance we measure is texture difference between the surrounding regions. We then assign a saliency value according to the distance in LBP histogram. To evaluate our experimental results, we measure the F-measure compared to ground-truth by thresholding a saliency map at 0.8. The average F-Measure is 0.65 and our experimental results show improved performance in comparison with existing other saliency map extraction methods.