Method of establishing adjustable-block background model for detecting real-time image object

摘要

A method of establishing an adjustable-block background model for detecting a real-time image object is provided to obtain a surveillance image by a surveillance apparatus. The surveillance image has a plurality of pixels. The method includes steps of: segmenting the surveillance image into a plurality of blocks each having a first pixel and at least one second pixel; defining the first pixel as a major color and comparing the first pixel with the at least one second pixel to determine a number and color information of the major color in the block; merging the blocks having the same major color into a large block to obtain a block background model; and performing image comparison to identify a moving object image. With the establishment of the block background model, a required memory space is effectively reduced while outstanding image display performance is still maintained.

主权项

1. A method of establishing an adjustable-block background model for detecting a real-time image object, which obtains a surveillance image by a surveillance apparatus, the method comprising steps of:
S1) segmenting the surveillance image into a plurality of blocks, each of which comprising a first pixel and at least one second pixel; S2) selecting a color of the first pixel as a major color, and determining a difference between color of the at least one second pixel and the color of the first pixel by an operation processing unit, and adding the color of the at least one second pixel into the major color when the difference is greater than a threshold; S3) determining a number and color information of the major color in each of the blocks by the operation processing unit, and storing the determined number and color information; S4) selecting and defining one of the blocks as an initial block, and defining the initial block and the blocks adjacent to the initial block as a search region; when the number of the major color in the initial block is smaller than a block threshold, reorganizing and integrating the number and the color information of the major color in the search region by the operation processing unit; S5) when the number of the major color in the search region is smaller than a region threshold, merging the search region into a large block; S6) completing analysis on the surveillance image, and sequentially repeating the steps S4 and S5 to obtain a block background model of the surveillance image; S7) inputting a new surveillance image by the surveillance apparatus, and performing color comparison between the new surveillance image and the block background model; and obtaining a moving object image when a color comparison result indicates a large difference; and S8) extracting a pixel in each of the blocks in the large block and comparing with a corresponding position in the new surveillance image; and updating data of the blocks when a pixel comparison result does not match.