<iframe allowfullscreen="true" data-mediaembed="bilibili" frameborder="0" id="eF14zu4z-1729786699365" src="https://player.bilibili.com/player.html?aid=113363279418709"></iframe>
数据集&yolo关键点模型 -关键点系列- 手部关键点数据集 handpose keypoints >> DataBall
该示例用3k+数据训练，模型采用yolo11n架构，对于一些简单场景可以满足左右手检测及21关键点检测，运算量小，模型效能高。
后期会推出 yolo11s,yolo11m架构模型或其它yolo系列。
一、模型推理
预训练模型地址：yolo11关键点模型-手部关键点数据集handposekeypoints>>DataBall资源-CSDN文库
模型参数：yolo11n 手部关键点模型
21个手部关键点检测 类别：左手 【0】，右手 【1】
模型推理代码如下：
# -*-coding:utf-8-*-
# date:2024-10
# Author: DataBall - XIAN
# Function: ultralytics yolo handpose 手部关键点推理
from ultralytics import YOLO
import cv2
import os
import supervision as sv
import time
'''
function: 绘制二维关键点连线
'''
def draw_joints(img_,hand_,x,y):
thick = 2
colors = [(0,215,255),(255,115,55),(5,255,55),(25,15,255),(225,15,55)]
#
cv2.line(img_, (int(hand_['0']['x']+x), int(hand_['0']['y']+y)),(int(hand_['1']['x']+x), int(hand_['1']['y']+y)), colors[0], thick)
cv2.line(img_, (int(hand_['1']['x']+x), int(hand_['1']['y']+y)),(int(hand_['2']['x']+x), int(hand_['2']['y']+y)), colors[0], thick)
cv2.line(img_, (int(hand_['2']['x']+x), int(hand_['2']['y']+y)),(int(hand_['3']['x']+x), int(hand_['3']['y']+y)), colors[0], thick)
cv2.line(img_, (int(hand_['3']['x']+x), int(hand_['3']['y']+y)),(int(hand_['4']['x']+x), int(hand_['4']['y']+y)), colors[0], thick)
cv2.line(img_, (int(hand_['0']['x']+x), int(hand_['0']['y']+y)),(int(hand_['5']['x']+x), int(hand_['5']['y']+y)), colors[1], thick)
cv2.line(img_, (int(hand_['5']['x']+x), int(hand_['5']['y']+y)),(int(hand_['6']['x']+x), int(hand_['6']['y']+y)), colors[1], thick)
cv2.line(img_, (int(hand_['6']['x']+x), int(hand_['6']['y']+y)),(int(hand_['7']['x']+x), int(hand_['7']['y']+y)), colors[1], thick)
cv2.line(img_, (int(hand_['7']['x']+x), int(hand_['7']['y']+y)),(int(hand_['8']['x']+x), int(hand_['8']['y']+y)), colors[1], thick)
cv2.line(img_, (int(hand_['0']['x']+x), int(hand_['0']['y']+y)),(int(hand_['9']['x']+x), int(hand_['9']['y']+y)), colors[2], thick)
cv2.line(img_, (int(hand_['9']['x']+x), int(hand_['9']['y']+y)),(int(hand_['10']['x']+x), int(hand_['10']['y']+y)), colors[2], thick)
cv2.line(img_, (int(hand_['10']['x']+x), int(hand_['10']['y']+y)),(int(hand_['11']['x']+x), int(hand_['11']['y']+y)), colors[2], thick)
cv2.line(img_, (int(hand_['11']['x']+x), int(hand_['11']['y']+y)),(int(hand_['12']['x']+x), int(hand_['12']['y']+y)), colors[2], thick)
cv2.line(img_, (int(hand_['0']['x']+x), int(hand_['0']['y']+y)),(int(hand_['13']['x']+x), int(hand_['13']['y']+y)), colors[3], thick)
cv2.line(img_, (int(hand_['13']['x']+x), int(hand_['13']['y']+y)),(int(hand_['14']['x']+x), int(hand_['14']['y']+y)), colors[3], thick)
cv2.line(img_, (int(hand_['14']['x']+x), int(hand_['14']['y']+y)),(int(hand_['15']['x']+x), int(hand_['15']['y']+y)), colors[3], thick)
cv2.line(img_, (int(hand_['15']['x']+x), int(hand_['15']['y']+y)),(int(hand_['16']['x']+x), int(hand_['16']['y']+y)), colors[3], thick)
cv2.line(img_, (int(hand_['0']['x']+x), int(hand_['0']['y']+y)),(int(hand_['17']['x']+x), int(hand_['17']['y']+y)), colors[4], thick)
cv2.line(img_, (int(hand_['17']['x']+x), int(hand_['17']['y']+y)),(int(hand_['18']['x']+x), int(hand_['18']['y']+y)), colors[4], thick)
cv2.line(img_, (int(hand_['18']['x']+x), int(hand_['18']['y']+y)),(int(hand_['19']['x']+x), int(hand_['19']['y']+y)), colors[4], thick)
cv2.line(img_, (int(hand_['19']['x']+x), int(hand_['19']['y']+y)),(int(hand_['20']['x']+x), int(hand_['20']['y']+y)), colors[4], thick)
if __name__ == '__main__':
# Load a model
model = YOLO(r"runs\pose\train5\weights\yolo11n-handpose-epoch-3k.pt") # load an official model
path_root_ = "datasets/yolo_hand_pose_data-DataBall/images/test/"
# 设置颜色调色板
color_palette = sv.ColorPalette(colors=[
sv.Color(r=225, g=230, b=128), # 红色
sv.Color(r=0, g=255, b=0), # 绿色
sv.Color(r=0, g=0, b=255), # 蓝色
# 可以继续添加更多颜色
])
# 设置边界框绘制器，使用颜色映射策略为类别（CLASS）
box_annotator = sv.BoxAnnotator(color=color_palette, thickness=2)
for f_ in os.listdir(path_root_):
# img_path = "image/6.jpg" # 图片路径
img_path = path_root_ +f_
# Predict with the model
results = model(
source = img_path,
project='./', # 保存预测结果的根目录
name='exp', # 保存预测结果目录名称
exist_ok=True,
save=True,
imgsz=640, # 推理模型输入图像尺寸
iou = 0.3, # nms 阈值
conf=0.25 # 置信度阈值
) # predict on an image
img = cv2.imread(img_path) # 加载读取图片，用于模型推理结果可视化
#--------------------------------------------------------------------
# 遍历结果进行可视化
try:
for result in results:
boxes = result.boxes.xyxy.detach().cpu().numpy() # 获取检测目标边界框
confidences = result.boxes.conf.detach().cpu().numpy() # 获取检测目标置信度
cls = result.boxes.cls.detach().cpu().numpy() # 获取检测目标标签
conf = result.keypoints.conf.detach().cpu().numpy() # 获取检测关键点置信度
key_points = result.keypoints.data.detach().cpu().numpy()
for i in range(boxes.shape[0]):
box_ = boxes[i].reshape(-1,4)
det_ = sv.Detections(xyxy=box_)
conf_ =confidences[i]
print("conf_",conf_)
cls_ = int(cls[i])
img = box_annotator.annotate(scene=img, detections=det_, labels=["[{}] {:.2f}".format(cls_,conf_)])
RGB_ = [(255,0,255),(0,255,0),(0,255,255),(0,0,255),(255,255,0)]
for i in range(key_points.shape[0]):
for j in range(key_points.shape[1]):
conf_ = key_points[i][j][2]
x,y = int(key_points[i][j][0]),int(key_points[i][j][1])
if j == 0:
cv2.circle(img, (x,y), 3, (128,128,128), -1) #绘制实心圆
else:
cv2.circle(img, (x,y), 3, RGB_[(j-1)%5], -1) #绘制实心圆
#----------------------------------------------------------------------
pts2d_list = {}
for j in range(key_points.shape[1]):
x_,y_ = int(key_points[i][j][0]),int(key_points[i][j][1])
pts2d_list[str(j)]={"x":x_,"y":y_}
draw_joints(img,pts2d_list,0,0) # 绘制手部关键点连线
cv2.namedWindow("img",1)
cv2.imshow("img",img)
key_id = cv2.waitKey(1)
if key_id== 27:
break
except:
continue
助力快速掌握数据集的信息和使用方式。
数据可以如此美好！
生活如遇低谷，请让我们微笑面对，雨过终会见彩虹！
推理效果示例：
二、训练数据
训练数据量：3k +
想要进一步了解，请联系。
DataBall 助力快速掌握数据集的信息和使用方式，会员享有 百种数据集，持续增加中。
数据样例项目地址：
样品数据量：
* 相关项目
目前数据集暂时在该网址进行更新： https://blog.csdn.net/weixin_42140236/article/details/142447120?spm=1001.2014.3001.5501
标签：img,int,yolo,cv2,keypoints,hand,colors,thick,关键点 From： https://blog.csdn.net/weixin_42140236/article/details/143223142