Low-power portable real-time image target detection and tracking system and method

Abstract

The invention provides a low-power consumption portable real-time image target detecting and tracking system and a method thereof, which can realize automatic cell cultivation process control and online observation in space and equivalent harsh environments. The system comprises a PL (Programmable Logic) subsystem and a PS (Processing System) subsystem; an image acquisition unit comprises a camera interface module, an image pre-processing module and an AXI-DMA module; the camera interface module is used for reading camera data and controlling parameters of an image resolution, an acquisition frame rat and a data format; the image pre-processing module is used for carrying out pre-processing operation such as color correction, histogram equalization and space transformation on an acquired image flow; the AXI-DMA module is used for realizing self return from image data to DDR3 RAM via an AXI-HP interface; an image acceleration unit comprises a reconfigurable image accelerator and the AXI-DMA module; the reconfigurable image accelerator is used for dynamically loading an image target detecting or image target tracking accelerator according to a system working stage; and the AXI-DMA module is used for realizing self return from image data to DDR3 RAM via an AXI-ACP interface.

Description

technical field [0001] The invention belongs to the technical field of image target detection and tracking, and relates to a low-power consumption portable real-time image target detection and tracking system and method. Background technique [0002] Image target detection and tracking is an important part of computer vision technology. It mainly realizes its recognition, matching or positioning by extracting the color, outline, texture, motion parameters and other characteristics of the target object. The auxiliary light source is used to irradiate the characteristic area of ​​the target with visible light or infrared light to obtain a clearer target image; the camera realizes the acquisition of the target image; the image acquisition and transmission circuit is used to read and transmit the image data collected by the camera; Image processing equipment includes various optional forms such as computers and embedded systems, and is mainly used to deploy and run algorithms su...

AI Technical Summary

Problems solved by technology

In 2014, Wang Shuling of Nanjing University of Science and Technology implemented a real-time face detection system using Zynq-7000SoC design, but it only used the PS subsystem, the algorithm used by the system was relatively simple, and the real-time performance was poor

In 2014, Yang Xiaoan from Zhuhai Radio and Television University implemented a high-speed image acquisition and real-time processing system using the Zynq-7000SoC design, but only used the PL subsystem to realize the data acquisition interface, without involving image calculation and processing

In 2014, Wang Zhibin of Jiangnan University implemented the dense optical flow method with Zynq-7000SoC design. It used the technology of software and hardware co-processing, but it was limited to the extraction of image optical flow features, and did not involve advanced abstract applications such as image target detection and tracking.

In 2014, Dalian Maritime University, Mo Libao and others used the Zynq-7000SoC design to realize the license plate recognition system, but it only used the PL subsystem to realize image acquisition and preprocessing, and did not involve advanced abstract applications such as image target detection and tracking

In 2015, Jiao Zaiqiang from Taiyuan University of Technology implemented an embedded digital image processing system using Zynq-7000SoC design, but it only verified simple image processing functions such as Sobel filters in the PL subsystem, and did not involve software and hardware collaborative image processing

Images