Thesis Proposal: 3D Tracking & Recognition of Natural Objects
نویسنده
چکیده
This is a proposal for a thesis topic of robust tracking and recognition of finger gestures. It is anticipated that this work will also provide and demonstrate a design framework for combining multiple sources of information. These will including stereo range images, color segmentations, motion images, shape information, and various constraints about the information. This information will be used in robust model fitting techniques to track highly overconstrained models of deformable objects such as fingers. Other key contributions will be that this thesis will examine the utility of stereo range images for certain tasks and will provide an example of a robust vision system.
منابع مشابه
Video Tracking for Human-Computer Interface
Interfaces to three-dimensional (3D) virtual environments are restrictive in the way that they take advantage of the potential for 3D human-computer interaction. Restrictive because they are either too complex for users to easily learn, or the range of expressions they permit is too limited. Two application areas where this is a common problem is in computer aided design and gaming, where it is...
متن کاملResearch on Interaction - oriented Gesture Recognition
This thesis designs a series of gesture interaction with the features of the natural human-machine interaction; besides, it utilizes the 3D acceleration sensors as interactive input. Afterwards, it builds the Discrete Hidden Markov Model to make gesture recognition by introducing the collection proposal of gesture interaction based on the acceleration sensors and pre-handling the gesture accele...
متن کاملTowards Natural Language Understanding using Multimodal Deep Learning
This thesis describes how multimodal sensor data from a 3D sensor and microphone array can be processed with deep neural networks such that its fusion, the trained neural network, is a) more robust to noise, b) outperforms unimodal recognition and c) enhances unimodal recognition in absence of multimodal data. We built a framework for a complete workflow to experiment with multimodal sensor dat...
متن کاملApplying mean shift and motion detection approaches to hand tracking in sign language
Hand gesture recognition is very important to communicate in sign language. In this paper, an effective object tracking and hand gesture recognition method is proposed. This method is combination of two well-known approaches, the mean shift and the motion detection algorithm. The mean shift algorithm can track objects based on the color, then when hand passes the face occlusion happens. Several...
متن کاملNon-rigid object tracking in video sequences
The goal of my work is to develop a tracking system capable of tracking complex objects like humans in cluttered environments. In this PhD thesis proposal, the state of the art approaches to tracking are categorized and reviewed from different points of view. Topics for my own future research are overviewed.
متن کامل