Extracting accurate information from video data in the surveillance system plays a key role in understanding the field situation and solving the problem. In this paper, a new method for estimating the height of a tilted object from a single image is proposed. The existing single view metrology method has the limitation that it can be applied only when the object is perpendicular to the ground. On the other hand, the proposed method is designed to be able to estimate the height even if the object is not perpendicular. The tilted angle of the object was estimated through gravity direction detection and the ground point was estimated by using the estimated angle and geometric characteristics. Using the estimated tilt and ground point, the actual tilted angle and vertical height of the distorted object in the image can be estimated, and finally the height of the tilted object can be accurately measured. As a result of the experiment, the proposed method achieved the average error 1.09 cm and the average error ratio 1.21% to the object, proving the accurate estimation performance close to the actual object height.

Accurate cerebrovascular segmentation is crucial for the early diagnosis and treatment of stroke and aneurysm, both of which pose significant health risks. Time-of-Flight Magnetic Resonance Angiography is widely used for noninvasive vascular assessment, but manual segmentation remains time-consuming, labor-intensive, and highly dependent on the skill level of medical experts. To address this challenge, we propose a fully automated cerebrovascular segmentation framework that integrates conventional voxel-based image analysis with graph-derived vascular features. Our model employs a dual-encoder architecture, where a CNN-based encoder processes MRA images while a second encoder extracts structural vessel information from graph feature-based images. The fusion of these complementary feature representations enhances segmentation accuracy by preserving vessel morphology and improving connectivity. The proposed model was trained and validated on the IXI dataset, which is included as part of the COSTA dataset and further evaluated on two other subsets of COSTA: ADAM and LocH1 datasets. The model achieved a Dice similarity score of 0.8510, Hausdorff distance (HD95) of 3.1150 mm, and average surface distance (ASD) of 0.4646 mm on the IXI dataset, outperforming the conventional 3D UNet model. The proposed model also demonstrated superior performance on external datasets, surpassing the baseline model and proving its generalizability. These results indicate that the proposed model provides a more robust and accurate cerebrovascular segmentation framework, demonstrating its potential for clinical applications.

Abstract Fundus image is widely used diagnosis method and involves the retinal tissues which can be important biomarkers for diagnosing diseases. Many studies have proposed automatic algorithms to detect the optic disc (OD) and fovea. However, they showed some limitations. Although the precise regions of retinal tissues are clinically important, most of these studies focused on the localization not the segmentation. Also, they did not sufficiently prove the clinical effectiveness of the methods using quantitative analysis. Furthermore, many of them have researched about the single retinal tissue. To compensate for these limitations, this study proposed automated segmentation method for both of the OD and fovea. In this study, the dataset was acquired from the DRIVE and Drions databases, and additional ground truth dataset was obtained from an ophthalmologist. The original fundus image was preprocessed to remove noise and enhance contrast. And the retinal vessel was segmented to use for the OD and fovea segmentation. In the OD and fovea segmentation step, a region of interest was designated based on the image features to increase the segmentation accuracy. To segment the OD, the retinal vessel was removed and substituted based on the intensity value of the four nearest non-vessel pixels. Finally, the OD and fovea regions were segmented based on the image features including intensity, shape and size. The proposed method was evaluated by quantitative analysis using eight methods. As a result, the proposed method showed high segmentation performance for the OD and fovea with accuracy of 99.18 and 99.80 % on the DRIVE database.

Retinal fundus images provide an opportunity to visualize vessels directly and non-invasively. Here, we develop a deep learning model that estimates the patients' age using only retinal fundus images and investigate its association with abnormal carotid artery intima-media thickness (CIMT) and all-cause mortality. Using the database at the Health Promotion Center of Seoul National University Hospital, the model was trained on 96,968 fundus images and validated using 6,579 independent participants via cross-sectional and retrospective cohort analysis. The primary exposure of the study was the fundus age difference (FAD), or the fundus age minus the actual age, where the fundus age was defined as the averaged predicted age of both left and right fundus images. Compared to participants with fundus age younger than their actual age ( FAD \leqslant 0), those with had significantly higher odds of abnormal CIMT (OR, 95%CI; 1.55, 1.07-2.23; p-trend, 0.002). Over a median follow-up of 5.6 years among 6,579 persons, was associated with all-cause mortality (HR, 95%CI; 2.13, 1.08-4.21; p-trend, 0.040). The fundus age difference was significantly associated with abnormal CIMT and all-cause mortality. With deep learning, retinal fundus images can be used to stratify risks of atherosclerosis and all-cause mortality and may benefit the clinical evaluation of patients.

This study presents a geometric deformable model‐based segmentation approach to segmentation of the intima and media‐adventitial (MA) borders in sequential intravascular ultrasound (IVUS) images. The initial estimation of the vessel borders was done manually only for the first frame of each sequence. After the border initialisation, pre‐processing including edge preservation, noise reduction, and dead zone preservation was successively performed on each IVUS frame. To improve segmentation performance, the image masks were determined preliminarily by local binary pattern‐based mask initialisation. Then, the inner and outer borders were approximated using a modified distance regularised level set evolution model. The results showed superior performance of the suggested approach for estimating intima and MA layers from the IVUS images. The corresponding correlation coefficients of area, vessel perimeter, maximum vessel diameter, and maximum lumen diameter were r = 0.782, r = 0.716, r = 0.956, and r = 0.874 for the 20 MHz images, respectively, and r = 0.990, r = 0.995, r = 0.989, and r = 0.996 for the 45 MHz images, respectively. In addition, linear regression analysis indicated that the manual segmentation had significantly high similarity at r > 0.967 and r > 0.993 for 20 and 45 MHz images, respectively.

For accurate and stable haptic rendering, collision detection for interactive haptic applications has to be done by filling in or covering target objects as tightly as possible with bounding volumes (spheres, axis-aligned bounding boxes, oriented bounding boxes, or polytopes). In this paper, we propose a method for creating bounding spheres with respect to the contact levels of details (CLOD), which can fit objects while maintaining the balance between high speed and precision of collision detection. Our method is composed mainly of two parts: bounding sphere formation and two-level collision detection. To specify further, bounding sphere formation can be divided into two steps: creating spheres and clustering spheres. Two-level collision detection has two stages as well: fast detection of spheres and precise detection in spheres. First, bounding spheres are created for initial fast probing to detect collisions of spheres. Once a collision is probed, a more precise detection is executed by examining the distance between a haptic pointer and each mesh inside the colliding boundaries. To achieve this refined level of detection, a special data structure of a bounding volume needs to be defined to include all mesh information in the sphere. After performing a number of experiments to examine the usefulness and performance of our method, we have concluded that our algorithm is fast and precise enough for haptic simulations. The high speed detection is achieved through the clustering of spheres, while detection precision is realized by voxel-based direct collision detection. Our method retains its originality through the CLOD by distance-based clustering.

In this paper, we present a mood-based music recommendation player: Smoodi. The Smoodi provides smart mood recommendation by touch and drag and it has three different views: Mood Square, Cover Flow and Mood Cloud. In the Mood Square, users can check the mood distribution of local clips and generate playlists by touching mood cells. In the Cover Flow, users can find music information and generate similar songs list by dragging a seed song. In the Tag Cloud, users can make playlists by selecting mood tags. For this application, we developed new mood model from collected mood tags and arousal-valence position values and designed a regression function to estimate mood probabilities.

Theoretical approach to predict the error vector magnitude (EVM) performance of an orthogonal frequency-division multiplexing (OFDM) system in the presence of nonlinear distortion caused by RF amplifiers is described. It is shown that the EVM model can be described by means of the autocorrelation of uncorrelated distortion noise term and a common complex gain. For the experimental validation, an EVM value of modulated signals through the fabricated HBT MMIC power amplifier is derived by the proposed method and compared with the measurement results.