摔倒检测+yolov5
摔倒检测
- 数据集来源
-
- 数据的处理
- 模型训练
数据集来源
开始使用目标检测检测人体，再通过宽高比值变化来判断是否摔倒，该方法在密集场景不管用，所以想着找一个摔倒数据集来进行检测是否摔倒，附上数据集来源：
中国华录杯——定向算法赛（人体摔倒姿态识别）这个训练集数据集我没有找到，官网下载的也只是未标注的测试集
Le2i Fall detection Dataset
• Annotations
- 标签格式为txt格式
- 标签前两行为跌倒帧数的起始与终止点，也存在没有这两行的文件
- 之后一行就是六个字段，帧编号， XX，人物bbx
Le2i Fall detection Dataset 原文下载速度不敢恭维，附上 百度云下载链接, 提取码：qghr
中国华录杯——定向算法赛（人体摔倒姿态识别）测试集，无标注，自己找的一些算法打的标注，还算过得去，需要自取百度云 百度云下载链接 , 提取码：asdh
以上两个数据集要是侵权了会删除
数据的处理
对Le2i Fall detection Dataset数据转换成voc格式的xml文件：
- 数据集解压后如下图，不知道有两个场景是没有标注文件的，号称假摔，所以我把他删了
- 解压后运行如下代码
# coding=utf-8
"""
@Time: 2021/3/9 10:23
@IDE: PyCharm
@Author: chengzhang
@File: processVideo.py
"""
import os
from tqdm import tqdm
import cv2
from xml.dom.minidom import Document
count = 0
def process(fileDir):
dataset = [os.path.join(fileDir, i) for i in os.listdir(fileDir)]
for dir in dataset:
Annotation = os.path.join(dir, "Annotation_files")
Annotations = [os.path.join(Annotation, i) for i in os.listdir(Annotation)]
for ann in tqdm(Annotations):
txt = open(ann).readlines()
if len(txt[0].split(',')) < 2:
videoPath = ann.replace('Annotation_files', 'Videos').replace('.txt', '.avi')
start, end = int(txt[0].replace('\n', '')), int(txt[1].replace('\n', ''))
video(videoPath, txt, start, end)
def video(videoPath, txt, start, end):
global count
vs = cv2.VideoCapture(videoPath)
ind = 1
while True:
success, frame = vs.read()
if frame is None:
break
if (ind + 8) >= start and ind <= end:
Jpg = '{:06d}.jpg'.format(count)
outPutJpg = os.path.join(save, Jpg)
outPutXML = outPutJpg.replace('jpg', 'xml')
cv2.imwrite(outPutJpg, frame)
count += 1
imgShape = frame.shape
info = txt[ind].replace('\n', '').split(',')
_, _, xmin, ymin, xmax, ymax = info
bboxsInfo = [[int(xmin), int(ymin), int(xmax), int(ymax)]]
bbox2xml(bboxsInfo, imgShape, Jpg, outPutXML)
ind += 1
def bbox2xml(bboxsInfo, imgShape, outPutJpg, outPutXML):
# for boxInfo in bboxsInfo:
xmlBuilder = Document()
annotation = xmlBuilder.createElement("annotation") # 创建annotation标签
xmlBuilder.appendChild(annotation)
Pheight, Pwidth, Pdepth = imgShape
folder = xmlBuilder.createElement("folder") # folder标签
folderContent = xmlBuilder.createTextNode("VOC2007")
folder.appendChild(folderContent)
annotation.appendChild(folder)
filename = xmlBuilder.createElement("filename") # filename标签
filenameContent = xmlBuilder.createTextNode(outPutJpg)
filename.appendChild(filenameContent)
annotation.appendChild(filename)
size = xmlBuilder.createElement("size") # size标签
width = xmlBuilder.createElement("width") # size子标签width
widthContent = xmlBuilder.createTextNode(str(Pwidth))
width.appendChild(widthContent)
size.appendChild(width)
height = xmlBuilder.createElement("height") # size子标签height
heightContent = xmlBuilder.createTextNode(str(Pheight))
height.appendChild(heightContent)
size.appendChild(height)
depth = xmlBuilder.createElement("depth") # size子标签depth
depthContent = xmlBuilder.createTextNode(str(Pdepth))
depth.appendChild(depthContent)
size.appendChild(depth)
annotation.appendChild(size)
for bbox in bboxsInfo:
label = "fall"
box_xmin, box_ymin, box_xmax, box_ymax = bbox
object = xmlBuilder.createElement("object")
picname = xmlBuilder.createElement("name")
nameContent = xmlBuilder.createTextNode(label)
picname.appendChild(nameContent)
object.appendChild(picname)
pose = xmlBuilder.createElement("pose")
poseContent = xmlBuilder.createTextNode("Unspecified")
pose.appendChild(poseContent)
object.appendChild(pose)
truncated = xmlBuilder.createElement("truncated")
truncatedContent = xmlBuilder.createTextNode("0")
truncated.appendChild(truncatedContent)
object.appendChild(truncated)
difficult = xmlBuilder.createElement("difficult")
difficultContent = xmlBuilder.createTextNode("0")
difficult.appendChild(difficultContent)
object.appendChild(difficult)
bndbox = xmlBuilder.createElement("bndbox")
xmin = xmlBuilder.createElement("xmin")
xminContent = xmlBuilder.createTextNode(str(box_xmin))
xmin.appendChild(xminContent)
bndbox.appendChild(xmin)
ymin = xmlBuilder.createElement("ymin")
yminContent = xmlBuilder.createTextNode(str(box_ymin))
ymin.appendChild(yminContent)
bndbox.appendChild(ymin)
xmax = xmlBuilder.createElement("xmax")
xmaxContent = xmlBuilder.createTextNode(str(box_xmax))
xmax.appendChild(xmaxContent)
bndbox.appendChild(xmax)
ymax = xmlBuilder.createElement("ymax")
ymaxContent = xmlBuilder.createTextNode(str(box_ymax))
ymax.appendChild(ymaxContent)
bndbox.appendChild(ymax)
object.appendChild(bndbox)
annotation.appendChild(object)
f = open(outPutXML, 'w')
xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
f.close()
if __name__ == '__main__':
fileDir = r"E:\数据集\FallDataset\dataset" # 源数据集路径
save = r"E:\数据集\FallDataset\FallDataset" # 保存voc格式路径
process(fileDir)
模型训练
- 使用U神的yolov5，链接
- 将voc格式的数据集转换成yolov5所需要的格式，数据格式如下：其中txt标注为下面代码生成的归一化数据
# coding=utf-8
"""
@Time: 2020/9/17 9:07
@IDE: PyCharm
@Author: chengzhang
@File: voc2v5.py
"""
import os
import glob
from tqdm import tqdm
import xml.etree.ElementTree as ET
import shutil
import argparse
from random import shuffle
import cv2
def check_x_y_w_h(norm_x, norm_y, norm_w, norm_h):
norm_x = 0.00001 if norm_x <= 0 else norm_x
norm_x = 0.99999 if norm_x >= 1 else norm_x
norm_y = 0.00001 if norm_y <= 0 else norm_y
norm_y = 0.99999 if norm_y >= 1 else norm_y
norm_w = 0.00001 if norm_w <= 0 else norm_w
norm_w = 0.99999 if norm_w >= 1 else norm_w
norm_h = 0.00001 if norm_h <= 0 else norm_h
norm_h = 0.99999 if norm_h >= 1 else norm_h
return norm_x, norm_y, norm_w, norm_h
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
x, y, w, h = check_x_y_w_h(x, y, w, h)
return (x, y, w, h)
def write_txt(train_xml, dataset):
with open(dataset, "w", encoding="utf-8") as f:
for xml in tqdm(train_xml):
f.write(xml.replace('.xml', '.jpg') + '\n')
target_label_txt = xml.replace('.xml', '.txt')
img = cv2.imread(xml.replace('.xml', '.jpg'))
h, w, c = img.shape
# 输入文件xml
in_file = open(xml)
# 输出label txt
out_file = open(target_label_txt, 'w')
tree = ET.parse(in_file)
root = tree.getroot()
for obj in root.iter('object'):
try:
cls = obj.find('name').text
except:
continue
if cls not in classes:
continue
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
bb = convert((w, h), b)
out_file.write(str(0) + " " + " ".join([str(a) for a in bb]) + '\n')
def check_dir(dir):
try:
shutil.rmtree(dir)
except:
os.makedirs(dir)
if not os.path.exists(dir):
os.makedirs(dir)
def parse_annotation(img_dir):
all_imgs = []
all_xmls = []
for tmpdir in img_dir:
for home, dirs, files in os.walk(tmpdir):
for filename in files:
# 文件名列表，包含完整路径
if filename.endswith((".jpg", ".jpeg", ".png")):
filePath = os.path.join(home, filename)
all_imgs.append(filePath)
elif filename.endswith(".xml"):
filePath = os.path.join(home, filename)
all_xmls.append(filePath)
return all_xmls
if __name__ == '__main__':
classes = ['fall']
parser = argparse.ArgumentParser()
parser.add_argument("--train_txt", default="/data/share/imageAlgorithm/zhangcheng/code/yolov5/data/train_fall.txt")
parser.add_argument("--test_txt", default="/data/share/imageAlgorithm/zhangcheng/code/yolov5/data/val_fall.txt")
flags = parser.parse_args()
imgPathList = [
"/data/share/imageAlgorithm/zhangcheng/dataset/falldataset/FallDataset/",
"/data/share/imageAlgorithm/zhangcheng/dataset/falldataset/FallDataset_A/"
]
dataset = parse_annotation(imgPathList)
shuffle(dataset)
num = len(dataset)
trainNum = int(0.9 * num)
trainList = dataset[: trainNum]
testList = dataset[trainNum:]
write_txt(trainList, flags.train_txt)
write_txt(testList, flags.test_txt)
- 根据上面处理的数据进行训练
CUDA_VISIBLE_DEVICES=4,5,6,7 nohup python train.py --img 640 --batch 16 --epochs 600 --data ./data/fallDown.yaml --weights ./weights/yolov5l.pt > train_fall.log 2>&1 &
- 训练曲线如下：
30个epoch结果
