Winograd YOLOv2 target detection model method based on FPGA acceleration

A target detection and model technology, applied in the field of computer vision and edge computing, can solve problems such as high power consumption and unreasonable on-chip resource allocation

CN111459877AActive Publication Date: 2020-07-28BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY +1
4 Cites 11 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2020-07-28

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a Winograd YOLOv2 target detection model method based on FPGA acceleration. The method comprises the steps: employing a PYNQ board card, and enabling a main control chip of thePYNQ board card to comprise a processing system end PS and a programmable logic end PL; wherein the PS end caches a YOLO model and feature map data of a to-be-detected image; the PL end caches the parameters of the YOLO model and the to-be-detected image into an on-chip RAM, deploys a YOLO accelerator with a Winograd algorithm, completes acceleration operation on the model, forms a data path of ahardware accelerator, and realizes target detection of the to-be-detected image; and an operation result of the acceleration circuit can be read out, and image preprocessing and display are carried out. By adopting the technical scheme of the invention, the calculation complexity of the YOLO algorithm can be reduced, the FPGA accelerator storage optimization algorithm reduces the calculation timeof the FPGA when accelerating the YOLO algorithm, accelerates the target detection, and effectively improves the performance of the target detection.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of computer vision and edge computing, and relates to an FPGA accelerator design method for a target detection model. Background technique

[0002] In recent years, with the development of machine vision and edge computing, the network model of target detection and recognition based on deep learning network has been greatly developed, and has achieved a lot in the fields of video scene monitoring, robot control, and unmanned vehicles. Applications. Representative models include single-shot-multibox-detection (SSD), FasterR-CNN, and you-only-look-once (YOLO network model) series. Among them, the YOLO algorithm has faster and more accurate performance advantages.

[0003] Most of the target detection and recognition models based on deep learning networks are completed in Graphic Processing Units (GPUs). The performance advantages are more prominent. However, edge computing needs to run on computing devices ...

Examples

Embodiment Construction

[0088] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0089] The overall hardware architecture of the accelerator designed by the present invention is as follows: figure 1 As shown, first complete the training of the YOLOv2 model on the host computer, use the VOC data set (VOC2007+2012), randomly select 16551 pictures as the training set, and 16492 pictures as the test set. Then carry out the fixed-point task of the model, and complete the edge algorithm on the embedded side. The PS side integrates the ARM core and is equipped with a Linux operating system. When transplanting the operating system, the Python language environment is reserved. The CPU can control all interfaces between the PS and PL, and the accelerator Through CPU scheduling, the feature map of the YOLO model is input into the DDR cache, and the bus interacts with the peripheral circuit...