/tags/pose-estimation/ Recent content in Pose Estimation on ViCoS Lab Hugo en-us /publications/tabernik2023lokalizacija/ Mon, 01 Jan 0001 00:00:00 +0000 /publications/tabernik2023lokalizacija/ <p>In this paper, we propose an approach to localize and estimate the pose of objects in three degrees of freedom (3-DOF). Our method is based on point localization combined with regression of the orientation angle for each detected object. We extend existing point localization method to estimate the orientation of all detected objects in an image. The orientation regression is parameterized with trigonometric functions, similar to the direction to the object center. We evaluate our method on the proposed screw dataset, composed of a training set containing synthetic images with photorealistic appearance and a test set containing real images of screws. Compared to the state-of-the-art 6-DOF position estimation method applied to the 3-DOF problem, our approach achieves comparable results at a significantly lower computational cost.</p> /publications/stepec2022video-based/ Mon, 01 Jan 0001 00:00:00 +0000 /publications/stepec2022video-based/ <p>Ski jumping is one of the oldest winter sports and takes also part in the Winter Olympics from the very start in 1924. One of the components of the final score, which is used for ranking the competitors, is the style score, given by five judges. The goal of this work was to develop a prototype for automatic style scoring from videos. As the main source of information, the proposed approach uses the detected locations of the ski jumper body parts and his skis to capture a full-body movement through the entire ski jump. We extended a method for human pose estimation from images to detect also the tips and the tails of the skies and adapted it to the domain of ski jumping. We proposed a method to utilize the detected trajectories along with the scores given by real judges to build a model for predicting the style scores. The experimental results obtained on the data that we had available show that the proposed computer-vision-based system for automatic style scoring achieves an error comparable to the error of real judges.</p>