摘要:
A User Interface (UI) for a real-time panoramic image correction system and method that simplifies the use of the system for the user. The UI includes a control panel that allows a user to enter meeting table size and shape, camera position and orientation, and the amount of normalization desired (e.g. 0 to 100%). A window can also be implemented on a display that displays the corrected panoramic image. In this window, the head (either normalized or non-normalized) of a meeting participant, preferably one that is speaking, is extracted and displayed in a separate window. Additionally, the corrected panoramic image, whose size will vary in conjunction with the amount of warping applied, can be displayed and transmitted with extra pixels around its perimeter in order to allow the corrected or normalized panoramic image to adapt to any of the standard display size and resolutions and to simplify network transmission. The corrected image can also be transmitted with standard resolutions using non-unity pixel aspect ratios to simply network transmission.
摘要:
A foveated panoramic camera system includes multiple cameras oriented so that individual images captured by the cameras can be combined to form a panoramic image. Each of the cameras includes a lens having a focal length that corresponds to a field of view for the camera. A field of view for a camera overlaps with the field(s) of view of each adjacent camera. At least one of the cameras has a field of view that differs from fields of view of other cameras for capturing images that are situated at a greater distance from the camera system than are images captured by the other cameras. As a result, a more uniform resolution is achieved across all images captured by the multiple cameras. A mirror assembly is utilized to reflect object images into the multiple cameras to achieve a near center of projection for the camera system.
摘要:
A camera samples an image area that includes an active region that encompasses a captured photographed image and an extended region. The extended region includes a reference object that is fixed to the camera and is sampled with the photographed image. An image of the reference object is referenced and used for one or more color calibration procedures, such as white balancing, black level calibration, and red and blue channel gains. In a multi-camera configuration, each camera includes a reference object and color calibration is performed for each camera to achieve near-seamless mosaic panoramic images.
摘要:
By-bandwidth voice-switching is performed during doubletalk between a near-end teleconference device and a far-end teleconference device. This may involve receiving far-end voice data from the far-end teleconference device. Near-end voice data is also received at the near-end teleconference device. Frequency subbands of the near-end voice data that having substantial energy are identified. Before playing the far-end voice data on one or more loudspeakers of the near-end teleconference device, frequency subbands from the far-end voice data frequency subbands thereof that correspond to the identified frequency subbands of the near-end voice data are attenuated and/or eliminated.
摘要:
Provided herein are systems, methods, and software for facilitating a video conference environment. In at least one implementation, video captured of a scene is received. A modification to display of the video is identified based at least in part on a share of a display space associated with an object in the scene relative to a share of another display space associated with another object in another scene. The modification to the display of the video is then initiated. In another implementation, the modification may also be based on a target share indicated by way of an interactive graphic.
摘要:
A practical, real-time calibration of digital omnidirectional cameras in the areas of de-vignetting, brightness, contrast, and white balance control. Novel solutions for the color calibration of an omnidirectional camera rig, and an efficient method for devignetting images are presented. Additionally, a context-specific method of stitching images together into a panorama or a mosaic is provided.
摘要:
A method and system for producing normalized images of conference participants so that the participants appear to be approximately the same size when the images are displayed is provided. The normalizing system normalizes the size of images based on constraints relating to the distance of participants from the location of the camera. To normalize the image of a participant, the system zooms the camera to account for the distance of the participant from the camera.
摘要:
Improved camera calibration techniques, including an improved up look angle and an improved method for calibrating a virtual center of projection. By using a view camera technique for the up look angle, the image sensors can be mounted flat to a Printed Circuit Board (PCB). By using a sub-region of the image sensor for the active area of the camera it is possible to calibrate the virtual center of projection (C′).
摘要:
A system and process for discovery between endpoint component devices and computing devices residing in the same delimited space, such as conference room, in cases where the devices are connected to a common local network, is presented. The present invention allows a device in the space to discover the presence and network address of another device in the space, which then allows the first device to negotiate with the discovered device to facilitate the transfer of data and other communications over the common network. However, this discovery is accomplished without the use of the common network, and is limited to discovering devices residing in the same delimited space also containing the discoverable devices.