Visible video camera screening method based on scenery space bidirectional detection

Abstract

The invention discloses a visible video camera screening method based on scenery space bidirectional detection, and the method comprises the steps: carrying out the bidirectional detection of a video camera and a main camera in a scenery space, and carrying out the forward detection and reverse detection; the forward detection realization process comprises the following steps: obtaining a plane equation of six surfaces of a view cone of a main camera; constructing a discriminant according to the plane equation, and calculating six-bit binary feature codes of all vertexes of the view cone of the video camera; bit-by-bit "amp;" for feature codes of all vertexes Operating to obtain a detection code; if the detection code is not equal to 0, determining that the video camera is invisible, and exiting; otherwise, continuing reverse detection; the reverse detection is realized in the same process as the forward detection. According to the method, the high efficiency of screening is realized by utilizing binary feature codes and bit operation in a scene space, the accuracy of screening is realized by utilizing bidirectional detection, and the efficiency of video and three-dimensional fusion in a video enhancement scene is improved.

Description

technical field [0001] The invention belongs to the field of spatial information, and in particular relates to a visual video camera screening method based on two-way detection of scene space. Background technique [0002] In a video-enhanced 3D scene, the video needs to be decoded frame by frame and loaded into the GPU for fusion. The number of videos involved in fusion has a great impact on fusion efficiency. One case is to let all video cameras participate in the fusion calculation. This method is suitable for scenes with a small number of video cameras; the other case is to group video cameras. Since each group has fewer video cameras, the fusion efficiency can be improved. . However, the grouping needs to be manually specified in advance, and the grouping results may not completely match the actual situation, which limits the application of this method. Therefore, efficient screening of visible video cameras is an effective means to improve fusion efficiency. [0003]...

AI Technical Summary

Problems solved by technology

However, grouping needs to be manually specified in advance, and the grouping results may not be completely consistent with the actual situation, which limits the application of this method, so efficient screening of visible video cameras is an effective means to improve fusion efficiency

[0003] Among the methods for screening visible cameras, the method based on the viewing distance can only be judged in one direction (direction of sight), the method based on the angle of sight can only be used to eliminate cameras with poor fusion effect, and the method based on the frustum bounding box The method is too simple and rough, which may cause the invisible video camera to be incorrectly screened

Patent ZL201711057783.7 proposes a method of screening visible cameras by calculating the visible pixel ratio of the video camera frustum. Although this method is relatively accurate, it involves a large amount of calculation due to the rasterization process involved.

Images