Sökning: "motion cues"
Visar resultat 1 - 5 av 17 uppsatser innehållade orden motion cues.
1. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. LÄS MER
2. Experiments with Visual Odometry for Hydrobatic Autonomous Underwater Vehicles
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Hydrobatic Autonomous Underwater Vehicles (AUVs) are underactuated robots that can perform agile maneuvers in challenging underwater environments with high efficiency in speed and range. The challenge lies in localizing and navigating these AUVs particularly for performing manipulation tasks because common sensors such as GPS become very unreliable underwater due to their poor accuracy. LÄS MER
3. VISUAL CUES : A WAY TO ENHANCE ACCURATE JUDGEMENTS OF TRAVEL SPEED IN DRIVER SIMULATORS
Kandidat-uppsats, Umeå universitet/Institutionen för psykologiSammanfattning : Drivers in simulators tend to drive faster than in a real car. The study aimed to examine if visual cues impact driver velocity in a simulator. This is important because of the tendency for users of to drive faster in simulators than in authentic driving situations. LÄS MER
4. How About Running on Mars ? Influence of Sensory Coherence on the Running Pattern and on Spatial Perception in Simulated Reduced Gravity
Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)Sammanfattning : Motor control, including locomotion, strongly depends on the gravitational field. Recent developments like lower-body positive pressure treadmills (LBPPTs) have enabled Earth- based studies on the effects of reduced body weight (BW) on walking and running. Yet, the observed adaptations to simulated hypogravity are not optimal. LÄS MER
5. Multimodal Machine Learning in Human Motion Analysis
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Currently, most long-term human motion classification and prediction tasks are driven by spatio-temporal data of the human trunk. In addition, data with multiple modalities can change idiosyncratically with human motion, such as electromyography (EMG) of specific muscles and respiratory rhythm. LÄS MER