DIP-football - A football video analyse system based on Yolov5, alphapose, Qt6

Overview

足球视频分析系统

作者

简介

本项目是SJTU 21-22学年CS386 数字图像处理课程的大作业,本文是足球视频分析系统的参考文档。我们主要实现了以下功能:

  1. 基于Yolo v5和PastaNet搭建了足球视频的分析神经网络,能够对球员位置、球员姿态和动作进行识别,也能对球队战术进行初步识别
  2. 基于Qt6搭建了一套足球分析系统,包括服务端和客户端:客户端上传视频到服务端,分析完成后再下载结果并展示

使用方法

  • 服务端:

    1. 需要一台装有NVIDIA20系列显卡,并且装有cuda10.2的Linux电脑(如果你打算用CPU运行神经网络,没有显卡也可以)
    2. 配置python环境,输入conda env create -n activity2vec -f DIP/HAKE-Action-Torch-Activity2Vec/activity2vec.yamlconda env create -n yolo -f DIP/Yolov5_DeepSort_Pytorch/yolo.yaml
    3. 在Linux环境下用Qt6编译src/server-console/server-console.pro,如果是在docker中,那么还需用ldd命令找到所需的库文件,将编译好的可执行文件和库文件一起拷贝到docker
    4. 修改DIP文件夹下面三个.sh脚本,将其中的$PYTHON_PATH改成自己conda环境中对应的python位置
    5. 将编译好的server-console放到DIP文件夹下,运行之
  • 客户端:

    1. 下载并安装Qt6
    2. 用Qt6打开src/layouts/basiclayouts.pro,编译之
    3. DIP/GUI中的get_place.py打包成get_place.exe,并与第二步编译好的文件放在同一目录下
    4. 运行第二步编译好的文件

文件夹

DIP  神经网络方面
|-- GUI            人工校准GUI
|-- inputfile      输入文件
|-- Yolov5_DeepSort_Pytorch
|-- HAKE-Action-Torch-Activity2Vec
...

src  图像界面方面
|-- layouts        客户端
|-- server-console 服务端

report 报告

注意

  • 我们在此处没有提供全套DIP文件夹,它足足有7.2G,您可以根据下面的链接下载环境

    链接: https://pan.baidu.com/s/1PiAyDIr59o5IvgcjAnUylw  密码: 0gso
    --来自百度网盘超级会员V5的分享
    

Football Video Analyse System

Introduction

This project is a major assignment of cs386 digital image processing course of SJTU 21-22 academic year. This tutorial is a reference document for football video analysis system. We mainly realize the following functions:

  1. We build a football video analysis neural network, which can identify the player's position, player's posture and action, and also preliminarily identify the team's tactics.
  2. We construct a football analysis system based on Qt-6, including server and client: the client uploads the video to the server, downloads the results and displays them after analysis.

Usage

  • Server:

    1. You need a CUDA 10.2 Linux computer with NVIDIA 20 series graphics card (If you plan to run neural networks with CPU, you can do it without a graphics card)
    2. Build the python environment, enter conda env create -n activity2vec -f DIP/HAKE-Action-Torch-Activity2Vec/activity2vec.yaml and conda env create -n yolo -f DIP/Yolov5_DeepSort_Pytorch/yolo.yaml
    3. Compile src/server-console/server-console.pro in Linux Qt6. If you decide to run it in docker, you also need ldd command to find the required library, then copy the executable file and the library to docker
    4. Modify the three .sh script in folder DIP, change $PYTHON_PATH to the corresponding Python location in your conda environment
    5. Put the executable server-console into the DIP folder, then run it
  • Client:

    1. Download and install Qt6
    2. Open src/layouts/basiclayouts.pro with Qt6, then compile it
    3. Pack the DIP/GUI/get_place.py to get_place.exe and put it in the same directory as the files compiled in step 2
    4. Run the file compiled in step 2

Directory

DIP  # about neural network
|-- GUI            # calibrate GUI
|-- inputfile      
|-- Yolov5_DeepSort_Pytorch
|-- HAKE-Action-Torch-Activity2Vec
...

src  # about GUI
|-- layouts        # client
|-- server-console # server

report 报告

Note

  • We don't provide a full set of DIP folders here. It takes up 7.2G of space. You can download the environment according to the link below:

    URL: https://pan.baidu.com/s/1PiAyDIr59o5IvgcjAnUylw
    password: 0gso
    
You might also like...
This repository is based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes.
This repository is based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes.

Rotate-Yolov5 This repository is based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes. Section I. Description The codes are

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.
This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their

Rewrite ultralytics/yolov5 v6.0 opencv inference code based on numpy, no need to rely on pytorch

Rewrite ultralytics/yolov5 v6.0 opencv inference code based on numpy, no need to rely on pytorch; pre-processing and post-processing using numpy instead of pytroch.

Yolov5+SlowFast:  Realtime Action Detection Based on PytorchVideo
Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

Yolov5+SlowFast: Realtime Action Detection A realtime action detection frame work based on PytorchVideo. Here are some details about our modification:

Video-Captioning - A machine Learning project to generate captions for video frames indicating the relationship between the objects in the video
Video-Captioning - A machine Learning project to generate captions for video frames indicating the relationship between the objects in the video

Video-Captioning - A machine Learning project to generate captions for video frames indicating the relationship between the objects in the video

Product-based-recommendation-system - A product based recommendation system which uses Machine learning algorithm such as KNN and cosine similarity Torchserve server using a YoloV5 model running on docker with GPU and static batch inference to perform production ready inference.
Torchserve server using a YoloV5 model running on docker with GPU and static batch inference to perform production ready inference.

Yolov5 running on TorchServe (GPU compatible) ! This is a dockerfile to run TorchServe for Yolo v5 object detection model. (TorchServe (PyTorch librar

Yolov5 deepsort inference,使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中
Yolov5 deepsort inference,使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中

使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中。

yolov5 deepsort 行人 车辆 跟踪 检测 计数
yolov5 deepsort 行人 车辆 跟踪 检测 计数

yolov5 deepsort 行人 车辆 跟踪 检测 计数 实现了 出/入 分别计数。 默认是 南/北 方向检测,若要检测不同位置和方向,可在 main.py 文件第13行和21行,修改2个polygon的点。 默认检测类别:行人、自行车、小汽车、摩托车、公交车、卡车。 检测类别可在 detect

Owner
null
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

YOLOv5-Lite:lighter, faster and easier to deploy Perform a series of ablation experiments on yolov5 to make it lighter (smaller Flops, lower memory, a

pogg 1.5k Jan 5, 2023
Yolov5-lite - Minimal PyTorch implementation of YOLOv5

Yolov5-Lite: Minimal YOLOv5 + Deep Sort Overview This repo is a shortened versio

Kadir Nar 57 Nov 28, 2022
AgeGuesser: deep learning based age estimation system. Powered by EfficientNet and Yolov5

AgeGuesser AgeGuesser is an end-to-end, deep-learning based Age Estimation system, presented at the CAIP 2021 conference. You can find the related pap

null 5 Nov 10, 2022
Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

Vector AI is a framework designed to make the process of building production grade vector based applications as quickly and easily as possible. Create

Vector AI 267 Dec 23, 2022
A new GCN model for Point Cloud Analyse

Pytorch Implementation of PointNet and PointNet++ This repo is implementation for VA-GCN in pytorch. Classification (ModelNet10/40) Data Preparation D

null 12 Feb 2, 2022
A scanpy extension to analyse single-cell TCR and BCR data.

Scirpy: A Scanpy extension for analyzing single-cell immune-cell receptor sequencing data Scirpy is a scalable python-toolkit to analyse T cell recept

ICBI 145 Jan 3, 2023
joint detection and semantic segmentation, based on ultralytics/yolov5,

Multi YOLO V5——Detection and Semantic Segmentation Overeview This is my undergraduate graduation project which based on ultralytics YOLO V5 tag v5.0.

null 477 Jan 6, 2023
This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes.

Polygon-Yolov5 This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes. Section I. Description The codes a

xinzelee 226 Jan 5, 2023
A graphical Semi-automatic annotation tool based on labelImg and Yolov5

??YOLOV5 semi-automatic annotation tool (Based on labelImg)

EricFang 247 Jan 5, 2023