No description available.

No description available.

The aim of this thesis is to define a perceptual scale for the ‘Time-Frequency’ analysis of music signals. The equal tempered ‘Bach ’ scale is a suitable scale, since it covers most of the genres of music and the error is equally distributed for each semi-tone. However, it may be necessary to allow a tolerance of around 50 cents or half the interval of the Bach scale, so that the interval can accommodate other common intonation schemes. The thesis covers the formulation of the Bach scale filter-bank as a time-varying model. It makes a comparative study with other commonly used perceptual scales. Two applications for the Bach scale filter-bank are also proposed, namely automated segmentation of speech signals and transcription of singing voice for query-by-humming applications. Even though this filter-bank is suggested with a motivation from music, it could also be applied to speech. A method for automatically segmenting continuous speech into phonetic units is proposed. The results, obtained from the proposed method, show around 82% accuracy for the English and 85% accuracy for the Hindi databases. This is an improvement of around 2 -3% when the performance is compared with other popular methods in the literature. Interestingly, the Bach scale filters perform better than the filters designed for other common perceptual scales, such as Mel and Bark scales. ‘Musical transcription’ refers to the process of converting a musical rendering or performance into a set of symbols or notations. A query in a ‘query-by-humming system’ can be made in several ways, some of which are singing with words, or with arbitrary syllables, or whistling. Two algorithms are suggested to annotate a query. The algorithms are designed to be fairly robust for these various forms of queries. The first algorithm is a frequency selection based method. It works on the basis of selecting the most likely frequency components at any given time instant. The second algorithm works on the basis of finding time-connected contours of high energy in the ‘Time-Frequency’ plane of the input signal. The time domain algorithm works better in terms of instantaneous pitch estimates. It results in an error of around 10 -15%, while the frequency domain method results in an error of around 12 -20%. A song rendered by two different people will have quite a few different properties. Their absolute pitches, rates of rendering, timbres based on voice quality and inaccuracies, may be different. The thesis discusses a method to quantify the distance between two different renderings of musical pieces. The distance function has been evaluated by attempting a search for a particular song from a database of a size of 315, made up of songs sung by both male and female singers and whistled queries. Around 90 % of the time, the correct song is found among the top five best choices picked. Thus, the Bach scale has been proposed as a suitable scale for representing the perception of music. It has been explored in two applications, namely automated segmentation of speech and transcription of singing voices. Using the transcription obtained, a measure of the distance between renderings of musical pieces has also been suggested.

This diploma thesis deals with the tracking of objects using a robotic manipulator Epson C3 and a color camera. The work describes the basic qualities of the device to be used. The OpenCV library and its wrapper EmguCV are used as software tools for computer vision. It discusses the basic issues and principles of tracking objects in the image and introduces some methods of tracking. These methods have been tested and therefore their strengths and weaknesses, which appeared during testing, are listed here. Furthermore, there is a procedure for calculating the new coordinates of the camera and the manipulator effector using homogeneous transformations. The work contains the results of testing the algorithms and their evaluation. The output of the work is a test application for the Epson C3 robot.

No description available.

Фитнес занимает важное место в жизни людей. Хорошие привычки фитнеса могут улучшить работу сердца и легких, повысить концентрацию, предотвратить ожирение и эффективно снизить риск смерти. Люди получают свои знания о фитнесе в основном из социальных сетей. Исследования показывают, что поддержание фитнеса имеет решающее значение для пропаганды здорового образа жизни и используется для оценки качества жизни, связанного со здоровьем. Хотя привлечение фитнес-тренера может быть эффективным подходом к поощрению регулярных упражнений и общего благополучия, это не всегда может быть осуществимо или доступно в определенных ситуациях. Стоит отметить, что упражнения имеют многочисленные преимущества для здоровья, но при неправильном выполнении они могут быть как неэффективными, так и потенциально опасными. Люди, которые тренируются без надлежащего контроля, часто совершают ошибки, такие как использование неправильных форм, что может привести к серьезным последствиям, таким как травмы подколенных сухожилий или падения. но способность к обучению ограничена. Неполная физическая подготовка может привести к травмам, а дешевая, своевременная и точная система определения физической подготовки может снизить риск травм и эффективно улучшить осведомленность людей о своей физической форме. В прошлом многие исследования были посвящены обнаружению фитнес-движений, среди которых обнаружение фитнес-движений на основе носимых устройств, узлов тела и глубокого обучения изображений достигло более высокой производительности. Однако носимое устройство не может обнаруживать различные фитнес-движения, может мешать физическим упражнениям пользователя и имеет высокую стоимость. Оба метода, основанные на узлах тела и на глубоком обучении изображений, имеют более низкую стоимость, но у каждого есть некоторые недостатки. Поэтому в этой статье использовался алгоритм оценки позы человека, такой как Yolov7, OpenPose и, в частности, Mediapipe, для оптимизации производительности приседаний на разных уровнях мастерства; эта система обеспечивает анализ техник приседаний в реальном времени. Настраиваемые режимы, предназначенные для новичков и профессионалов, обеспечивают персонализированную обратную связь, позволяя пользователям эффективно совершенствовать свою форму. Используя методы компьютерного зрения и машинного обучения, включая MediaPipe, OpenCV и Python, система отслеживает движения пользователей, предоставляя на экране руководство и слуховые подсказки для коррекции осанки и прогресса тренировки. AI-Fit предлагает решение, позволяющее людям безопасно заниматься спортом под руководством экспертов, и удовлетворяет потребность в персонализированных фитнес-тренировках, профилактике травм и мотивации, в конечном итоге улучшая общую физическую форму и самочувствие пользователей. / Fitness is important in people’s lives. Good fitness habits can improve cardiopulmonary capacity, increase concentration, prevent obesity, and effectively reduce the risk of death. People obtain their fitness knowledge mostly from social media. Research indicates that maintaining fitness is crucial for promoting a healthy way of living and is used to assess one's health-related quality of life. While engaging a fitness trainer can be an effective approach to encouraging regular exercise and overall well-being, it may not always be feasible or affordable in certain situations. It is worth noting that exercise has numerous health benefits, but if performed incorrectly, it can be both ineffective and potentially hazardous. Individuals who work out without proper supervision often make mistakes such as using improper forms, which can lead to severe consequences, such as hamstring injuries or falls. but learning ability is limited. Incomplete fitness is likely to lead to injury, and a cheap, timely, and accurate fitness detection system can reduce the risk of fitness injuries and can effectively improve people’s fitness awareness. In the past, many studies have engaged in the detection of fitness movements, among which the detection of fitness movements based on wearable devices, body nodes, and image deep learning has achieved better performance. However, a wearable device cannot detect a variety of fitness movements, may hinder the exercise of the fitness user, and has a high cost. Both body-node-based and image-deep-learning-based methods have lower costs, but each has some drawbacks. Therefore, this paper used a human pose estimation algorithm such as Yolov7, OpenPose and particularly Mediapipe, to optimize squat performance across various skill levels, this system provides real-time analysis of squat techniques. Customized modes tailored for beginners and professionals deliver personalized feedback, empowering users to refine their form effectively. By employing techniques from computer vision and machine learning, including MediaPipe, OpenCV, and Python, the system tracks users' movements, providing on-screen guidance and auditory cues for posture correction and workout progression. AI-Fit offers a solution for individuals to exercise safely with expert guidance and addresses the need for personalized fitness training, injury prevention, and motivation, ultimately enhancing users' overall physical fitness and well-being.