Method for realizing dynamic gesture recognition and control in integrated imaging display system

Abstract

The invention discloses a method for realizing dynamic gesture recognition and control in an integrated imaging display system and belongs to the technical field of image processing. According to theinvention, an image acquisition system of a light field camera, an image acquisition server side, a display system of a three-dimensional image, a server side of the display system and a dynamic gesture recognition system are utilized. The method comprises the following steps: acquiring a light field image, then carrying out image segmentation and virtual trial point generation on a shot viewpoint, displaying a three-dimensional image after three-dimensional reconstruction, and finally identifying and training a gesture of a control image. According to the invention, the problems of visual fatigue caused by wearing 3D glasses and the like for watching a three-dimensional scene, image movement control with the help of equipment and the like can be solved, and the effects of realizing dynamic gesture recognition and controlling a three-dimensional image in an integrated imaging display system are achieved.

Description

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a dynamic gesture recognition and control method in an integrated imaging display system. Background technique

[0002] In today's society, people's demand for viewing large-screen 3D content and scenes is increasing day by day, such as watching 3D movies, 3D game experience and so on. However, many 3D movies are made using sophisticated 3D video capture and stereoscopic photography. When watching 3D images or videos, visual fatigue and discomfort are still unsatisfactory experiences, and most of the scene viewers have to wear heavy 3D glasses. This series of problems hinders the widespread promotion of 3D services. In addition, computer human-computer interaction technology has made certain achievements, and somatosensory recognition technology is gradually playing a very critical role and value in the human-computer interface. Somatosensory gesture recogn...

Examples

Embodiment Construction

[0071] The present invention is described in detail below in conjunction with accompanying drawing:

[0072] see figure 1 , the implementation of the method includes a total of six major steps: image acquisition, foreground segmentation and depth estimation, 3D reconstruction, virtual pilot generation, 3D image display, gesture recognition and training.

[0073] For image acquisition steps, see figure 2 , in the acquisition process, first, the server uses the camera calibration software Calibration to obtain the internal parameters of the 16 cameras (including lens distortion coefficients, equivalent focal lengths, and optical axis imaging positions) and the relative positional relationship between the cameras. If the acquired positional relationship If the deviation from the theoretical value is too large, use the position adjustment function of the camera calibration software to manually fine-tune the camera that deviates from the position, and then calibrate the camera ar...

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a dynamic gesture recognition and control method in an integrated imaging display system. Background technique

[0002] In today's society, people's demand for viewing large-screen 3D content and scenes is increasing day by day, such as watching 3D movies, 3D game experience and so on. However, many 3D movies are made using sophisticated 3D video capture and stereoscopic photography. When watching 3D images or videos, visual fatigue and discomfort are still unsatisfactory experiences, and most of the scene viewers have to wear heavy 3D glasses. This series of problems hinders the widespread promotion of 3D services. In addition, computer human-computer interaction technology has made certain achievements, and somatosensory recognition technology is gradually playing a very critical role and value in the human-computer interface. Somatosensory gesture recogn...

Examples

Embodiment Construction

[0071] The present invention is described in detail below in conjunction with accompanying drawing:

[0072] see figure 1 , the implementation of the method includes a total of six major steps: image acquisition, foreground segmentation and depth estimation, 3D reconstruction, virtual pilot generation, 3D image display, gesture recognition and training.

[0073] For image acquisition steps, see figure 2 , in the acquisition process, first, the server uses the camera calibration software Calibration to obtain the internal parameters of the 16 cameras (including lens distortion coefficients, equivalent focal lengths, and optical axis imaging positions) and the relative positional relationship between the cameras. If the acquired positional relationship If the deviation from the theoretical value is too large, use the position adjustment function of the camera calibration software to manually fine-tune the camera that deviates from the position, and then calibrate the camera ar...

Images