Method and device for performing irregular polygon mosaic processing on monitored image

Abstract

The invention relates to a video monitoring field, and discloses a method and device for performing irregular polygon mosaic processing on a monitored image. The method comprises the following steps: computing a maximum value and a minimum value of a coordinate of a shielding region, that is represented by a polygon, at a first dimensional direction; in the maximum value and minimum value range of the coordinate, scanning the shielding region line by line by using a scanning straight line vertical to the first dimension direction by using a predetermined step length, dividing the shielding region into a plurality of shielding rectangular blocks through the scanning, and copying data in the shielding rectangular blocks to a processor in a DMA (direct memory access) manner to process.

Description

technical field [0001] The invention relates to the field of video monitoring, in particular to irregular polygon mosaic processing technology. Background technique [0002] At present, privacy masking has been widely used in the surveillance industry, that is, with the rotation of the dome camera pan / tilt, the privacy area that needs to be masked is fixed and kept in a masked state. In order to ensure the real-time performance of masking, each frame of image needs to be processed. The transformation from the latitude and longitude coordinates transmitted by the upper layer to the plane coordinates and mosaic processing requires calculation and processing, which puts forward strict requirements on the performance of the processor and the efficiency of the algorithm. When processing a mosaic, because the rectangle has the advantages of simple processing and high algorithm efficiency, the current mosaic privacy blocks are mainly rectangles. In the process of rectangle privacy...

AI Technical Summary

Problems solved by technology

[0004] However, due to the limitations of processor performance in the prior art, whether the pixel points in the rectangular frame are judged point by point within the polygon, when the polygon area is large, a large amount of calculation is required, which makes the processing performance overall decline

When processing a single polygon with a large area, it will cause serious frame loss of video data, affecting privacy and masking data integrity, which may cause the consequences of making privacy public

Therefore, this method is far from meeting the requirements when multiple polygon privacy masks are required.

Images