An autonomous robot that can localize itself and navigate around can be used in various real life... more An autonomous robot that can localize itself and navigate around can be used in various real life applications. In this research we have built a low cost, low power consuming, vision based autonomous robot. Our two wheel robot platform houses a single board computer Raspberry Pi for its computation and Arduino Uno to drive the motors as instructed. The visual sensory input is coming through a webcam mounted on the robot platform itself. When the robot is in motion, we compute optical flow from successive frame capture of the webcam using OpenCV's robust API. This allows us to navigate the robot in an unknown environment avoiding obstacles.
Hand gestures can be used for natural and intuitive human-computer interaction. To achieve this g... more Hand gestures can be used for natural and intuitive human-computer interaction. To achieve this goal, computers should be able to visually recognize hand gestures from video input. However, vision-based hand tracking and gesture recognition is an extremely challenging problem due to the complexity of hand gestures, which are rich in diversities due to high degrees of freedom involved by the human hand. On the other hand, computer vision algorithms are notoriously brittle and computation intensive, which make most current gesture recognition systems fragile and inefficient.
We intend to develop a gesture based mouse and application controller which we named "G-MAC". Our system will be developed with two major visions in mind:(1) to build a virtual mouse system which will virtually replace all the major mouse functionalities and (2) to build a gesture application which enables us to control various applications via hand gestures. Our Gesture Application will consists of two types of gesture recognition:(1) static gesture recognition which will open up an application based on matched gestures from image database, and (2) a simple linear swipe based motion gesture which will enable us to control selected application such as \Picasa" to move to next/previous images and even zoom in/out. The ultimate goal is to build a gesture based interface which will be more intuitive and flexible for users.
An autonomous robot that can localize itself and navigate around can be used in various real life... more An autonomous robot that can localize itself and navigate around can be used in various real life applications. In this research we have built a low cost, low power consuming, vision based autonomous robot. Our two wheel robot platform houses a single board computer Raspberry Pi for its computation and Arduino Uno to drive the motors as instructed. The visual sensory input is coming through a webcam mounted on the robot platform itself. When the robot is in motion, we compute optical flow from successive frame capture of the webcam using OpenCV's robust API. This allows us to navigate the robot in an unknown environment avoiding obstacles.
Hand gestures can be used for natural and intuitive human-computer interaction. To achieve this g... more Hand gestures can be used for natural and intuitive human-computer interaction. To achieve this goal, computers should be able to visually recognize hand gestures from video input. However, vision-based hand tracking and gesture recognition is an extremely challenging problem due to the complexity of hand gestures, which are rich in diversities due to high degrees of freedom involved by the human hand. On the other hand, computer vision algorithms are notoriously brittle and computation intensive, which make most current gesture recognition systems fragile and inefficient.
We intend to develop a gesture based mouse and application controller which we named "G-MAC". Our system will be developed with two major visions in mind:(1) to build a virtual mouse system which will virtually replace all the major mouse functionalities and (2) to build a gesture application which enables us to control various applications via hand gestures. Our Gesture Application will consists of two types of gesture recognition:(1) static gesture recognition which will open up an application based on matched gestures from image database, and (2) a simple linear swipe based motion gesture which will enable us to control selected application such as \Picasa" to move to next/previous images and even zoom in/out. The ultimate goal is to build a gesture based interface which will be more intuitive and flexible for users.
Uploads
Papers by Niaz Mohammad
houses a single board computer Raspberry Pi for its computation and Arduino Uno to drive the motors as instructed. The visual sensory input is coming through a webcam mounted on the robot platform itself. When the robot is in motion, we compute optical flow from successive frame capture of the webcam using OpenCV's robust API. This allows us to navigate the robot in an unknown environment avoiding obstacles.
We intend to develop a gesture based mouse and application controller which we named "G-MAC". Our system will be developed with two major visions in mind:(1) to build a virtual mouse system which will virtually replace all the major mouse functionalities and (2) to build a gesture application which enables us to control various applications via hand gestures. Our Gesture Application will consists of two types of gesture recognition:(1) static gesture recognition which will open up an application based on matched gestures from image database, and (2) a simple linear swipe based motion gesture which will enable us to control selected application such as \Picasa" to move to next/previous images and even zoom in/out. The ultimate goal is to build a gesture based interface which will
be more intuitive and flexible for users.
houses a single board computer Raspberry Pi for its computation and Arduino Uno to drive the motors as instructed. The visual sensory input is coming through a webcam mounted on the robot platform itself. When the robot is in motion, we compute optical flow from successive frame capture of the webcam using OpenCV's robust API. This allows us to navigate the robot in an unknown environment avoiding obstacles.
We intend to develop a gesture based mouse and application controller which we named "G-MAC". Our system will be developed with two major visions in mind:(1) to build a virtual mouse system which will virtually replace all the major mouse functionalities and (2) to build a gesture application which enables us to control various applications via hand gestures. Our Gesture Application will consists of two types of gesture recognition:(1) static gesture recognition which will open up an application based on matched gestures from image database, and (2) a simple linear swipe based motion gesture which will enable us to control selected application such as \Picasa" to move to next/previous images and even zoom in/out. The ultimate goal is to build a gesture based interface which will
be more intuitive and flexible for users.