ZYNQ-based GigE interface camera target identification method and system

Abstract

The invention discloses a ZYNQ-based GigE interface camera target identification method and system, and the system comprises a GigE interface camera which is connected with a ZYNQ module through a GigE Vision protocol, and is used for collecting a video image and transmitting the video image to the ZYNQ module; the ZYNQ module which is used for controlling a GigE interface camera parameter, carrying out preprocessing and target identification on the received video image, and sending the identified and marked target image to a display; the display which is connected with an HDMI interface module in the ZYNQ module and used for receiving and displaying the target image; and a DDR memory which is connected with the ZYNQ module and used for storing the video image and sending the video image to a PL unit through a VDMA soft core IP. The invention provides an integrated target identification display system integrating image acquisition, image processing and target identification, the advantage of high-speed parallelism of an FPGA is kept, the size of a chip is kept unchanged, the requirement for integration is met, and the research and development period is greatly shortened.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a ZYNQ-based GigE interface camera target recognition method and system. Background technique [0002] The image acquisition system based on high-speed industrial cameras has been widely used in many fields of production and life, such as making PCB circuit boards in the industrial field, product qualification inspection, precise cutting, etc., which can improve production efficiency and product quality, such as in the security field Surveillance cameras, license plate recognition in road traffic, unmanned driving, intelligent robots in the field of artificial intelligence, etc., it can be seen that the image acquisition system based on industrial cameras has played a huge role in people's production and life. [0003] In the prior art, the interface of industrial cameras mostly adopts the Camera Link interface. Although the interface has a high transmission rate, it usu...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the interface of industrial cameras mostly adopts the Camera Link interface. Although this interface has a high transmission rate, it usually requires an acquisition card, which is inconvenient to carry and has a high cost.

Others use USB interface. Although the development cycle is short and the cost is low, the transmission rate is slow and the transmission distance is short.

[0004] In the prior art, some use the DSP+FPGA solution to realize image data processing, but two chips, DSP and FPGA, are needed, which not only occupy a large area, but also have complicated implementation methods; some use a single chip of FPGA, but there are many matching cameras CMOS cameras are used, the data interface is mostly IIC or SPI interface, the data transmission rate is low, and long-distance transmission cannot be realized; some use FPGA single-chip supporting industrial camera GigE interface, but the NIOSII soft core is generated inside the FPGA to act as a processor. Responsible for task scheduling, but the specific data sending and receiving and encapsulation are still implemented by the FPGA hardware logic language. The defect of this solution is that NIOSII is generated based on the internal logic resources of the FPGA, which will consume a large amount of RAM inside the FPGA, and is not suitable for low-end FPGA implementation increases the implementation cost, and secondly, NIOSII runs at a low speed, far lower than ARM, DSP and other processors

Images