Adaptive real-time image background removing method and system

Abstract

The invention discloses an adaptive real-time image background removing method and system, and the system comprises a data storage module which is used for storing image data or a background model; an image reading and writing module which is used for receiving image data and storing the received image data in the data storage module; and a background removing module which reads the image data and the corresponding background module from the data storage module, and carries out the background discrimination of the image data according to the background model. The background removing module generates a mask code corresponding to the image data according to a discrimination result, and the image data with the background being removed, and enables the image data with the background being removed and / or the mask code to be stored in the data storage module. The system designs a hardware circuit through employing a Verilog hardware description language, is implemented on an FPGA, and is high in transplantability. Moreover, the background removing module can serve as an IP core to be used in other systems, thereby meeting more demands.

Description

technical field [0001] The invention relates to the field of computer hardware, in particular to an adaptive real-time image background removal method and system. Background technique [0002] At present, the research on the algorithm of background removal has been extensive, and it has been widely used in traffic monitoring, access control monitoring, moving object monitoring and so on. Most applications implement background removal through software, and few implement background removal through hardware. The advantages of software implementation are strong replicability and simple implementation, but the disadvantages are slow speed and strong platform dependence. The advantages of hardware implementation are fast processing speed, strong real-time performance, low cost, and flexible use. The disadvantage is that the implementation is complicated. [0003] On the surface, the cost of software implementation should be lower than that of hardware implementation, but in fact...

AI Technical Summary

Problems solved by technology

The advantages of software implementation are strong replicability and simple implementation, but the disadvantages are slow speed and strong platform dependence

The advantages of hardware implementation are fast processing speed, strong real-time performance, low cost, and flexible use. The disadvantage is that the implementation is complicated

[0003] On the surface, the cost of software implementation should be lower than that of hardware implementation, but in fact it is higher than the cost of hardware, because the software runs on a platform such as a computer, and the high price of the computer itself also makes the entire system more expensive. become complex

This introduces a series of problems, the whole system is not portable, and the power consumption is high

For example, on the expressway, it is necessary to collect the real-time information of the car. It would be inconvenient if the software is equipped with hardware devices such as a computer for real-time monitoring. At the same time, the power consumption of the computer is high, and the supply of electric energy is also a problem on the expressway.

Or use the camera and network equipment to send the picture back to the monitoring room, and then use the software to remove the background. In the case of insufficient network bandwidth, the real-time transmission of the picture will become a bottleneck

Images