• Journal of the Korean Society of Radiology
• /
• v.9 no.6
• /
• pp.349-356
• /
• 2015

The study is to recognize the interactions with bone ages by measuring the length between the end of the bone and the growth plate on selected highest weight of regions of seven for bone maturity in TW3 method. The experiment is subjected on seventy-two children (36 males, 36 females) who have examined the growth plate test from March, 2014 to March, 2015 and implemented a regression analysis by measuring the length between the end of the bone and the growth plate in Hand AP image of the children. In result, each bone age has produced a mean value and a standard deviation corresponding to the specific range and as bone age increases the length between the end of the bone and the growth plate decreased. In addition, female children showed lower mean value in comparison to male and also the measurement of the length between the end of the bone and the growth plate and its bone age are shown to be statistically valid(p<0.001) according to the results of regression analysis using its result value. Therefore, the probability of prediction on the bone age read off through the applied TW3 method and regression equation in the Hand AP image of the children.

• Journal of radiological science and technology
• /
• v.33 no.4
• /
• pp.341-348
• /
• 2010

By accessing the current status of FPD system use in the hospitals located in Seoul and Gyeonggi Province as well as the entrance skin dose and the image quality evaluation realized by C-D Phantom, and the image assessment by the medical professionals regarding the radiography for the extremity, the following results were derived. 1. According to the evaluation made in the actual use of FPD system (12 machines), the grid ratio varied from 8:1 to 13:1, and 6 machines used the grid ratio with 12:1, realizing the largest number. Among the machines, there were 8 machines that allowed a removable grid while 3 machines did use a removable grid (25.0%). 2. When it came to the equipments used for the experiment, it showed that the amount of the entrance skin dose increased from 4.13 times up to 4.79 times with the grid use. 3. The difference in the entrance skin dose depending on the changes in the exposure condition(0.5times or 2.0times) was not significantly different regardless of the patients' thickness. 4. In terms of the image quality depending on C-D Phantom, the grid use was distinguished well. However, the images were well distinguishable as the exposure condition got increased. 5. In the clinical assessment, the grid use was less effective for the Hand PA, which was considered to shoot a thin body part. It was evaluated that the grid use was preferred for the Knee AP, which was shooting for a relatively thick body part. Nonetheless, 3 out of 5 people said that they would not use the grid if the entrance skin dose to reduced.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Journal of Advanced Navigation Technology
• /
• v.9 no.1
• /
• pp.48-55
• /
• 2005

In this paper, we propose an efficient moving object tracking technique for multi-camera surveillance system. Color CCD cameras used in this system are network cameras with their own IP addresses. Input image is transmitted to the media server through wireless connection among server, bridge, and Access Point (AP). The tracking system sends the received images through the network to the tracking module, and it tracks moving objects in real-time using color matching method. We compose two sets of cameras, and when the object is out of field of view (FOV), we accomplish hand-over to be able to continue tracking the object. When hand-over is performed, we use MHI(Motion History Information) based on color information and M-bin histogram for an exact tracking. By utilizing MHI, we can calculate direction and velocity of the object, and those information helps to predict next location of the object. Therefore, we obtain a better result in speed and stability than using template matching based on only M-bin histogram, and we verified this result by an experiment.