<annotation>
	<folder></folder>
	<filename>images276_jpg.rf.514a43be2736c3e7785c8b047496f4cf.jpg</filename>
	<path>images276_jpg.rf.514a43be2736c3e7785c8b047496f4cf.jpg</path>
	<source>
		<database>roboflow.com</database>
	</source>
	<size>
		<width>640</width>
		<height>640</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>pothole</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>149</xmin>
			<xmax>305</xmax>
			<ymin>199</ymin>
			<ymax>300</ymax>
		</bndbox>
	</object>
	<object>
		<name>pothole</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>289</xmin>
			<xmax>620</xmax>
			<ymin>380</ymin>
			<ymax>641</ymax>
		</bndbox>
	</object>
	<object>
		<name>pothole</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>270</xmin>
			<xmax>615</xmax>
			<ymin>184</ymin>
			<ymax>402</ymax>
		</bndbox>
	</object>
	<metadata>
	</metadata>
</annotation>

0 0.46953125 0.51328125 0.0953125 0.0765625
0 0.63359375 0.47421875 0.07734375 0.0640625

import os
import random

trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = 'data/Annotations'
txtsavepath = 'data/ImageSets'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('data/ImageSets/trainval.txt', 'w')
ftest = open('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/train.txt', 'w')
fval = open('data/ImageSets/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ['pothole'] # 根据标签名称填写类别
abs_path = os.getcwd()
print(abs_path)


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
    return x, y, w, h


def convert_annotation(image_id):
    in_file = open('data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('data/labels/%s.txt' % (image_id), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


wd = getcwd()
for image_set in sets:
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

train: data/train.txt
val: data/val.txt
test: data/test.txt

nc: 1
names: ['pothole']

model = YOLO('yolov8s.pt')
results = model.train(data='data.yaml', epochs=200, imgsz=640, batch=16, workers=0)

yolo train data=data.yaml model=yolov8s.pt epochs=200 imgsz=640 batch=16 workers=0 device=0

import cv2
from ultralytics import YOLO

# Load the YOLOv8 model
model = YOLO("./best.pt") # 自定义预测模型加载路径

# Open the video file
video_path = "./demo.mp4" # 自定义预测视频路径
cap = cv2.VideoCapture(video_path) 

# Get the video properties
frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS)

# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # Be sure to use lower case
out = cv2.VideoWriter('./outputs.mp4', fourcc, fps, (frame_width, frame_height)) # 自定义输出视频路径

# Loop through the video frames
while cap.isOpened():
    # Read a frame from the video
    success, frame = cap.read()

    if success:
        # Run YOLOv8 inference on the frame
        # results = model(frame)
        results = model.predict(source=frame, save=True, imgsz=640, conf=0.5)

        results[0].names[0] = "道路积水"
        # Visualize the results on the frame
        annotated_frame = results[0].plot()

        # Write the annotated frame to the output file
        out.write(annotated_frame)

        # Display the annotated frame (optional)
        cv2.imshow("YOLOv8 Inference", annotated_frame)

        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break

# Release the video capture and writer objects
cap.release()
out.release()
cv2.destroyAllWindows()

import warnings

warnings.filterwarnings('ignore')
from ultralytics import YOLO

if __name__ == '__main__':
    model = YOLO('models/best.pt')
    model.predict(source='test_pic',
                  imgsz=640,
                  save=True,
                  conf=0.25
                  )

yolo predict model="best.pt" source='demo.jpg'

conda create -n ultralytics-env python=3.10
conda activate ultralytics-env
pip install -r requirements.txt

python app.py

<!doctype html>
<html lang="zh-CN">

<head>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width,initial-scale=1">
    <title>视觉检测系统 - Web UI</title>
    <link rel="stylesheet" href="/static/style.css">
    <link rel="icon" href="/favicon.ico">
</head>

<body>
    <div class="container main-flex">
        <!-- 左侧内容区 -->
        <div class="left-content">
            <header>
                <h1>YOLO道路病害检测系统</h1>
                <div id="currentModelDisplay" class="modelDisplay" title="当前模型">当前模型：未上传模型</div>
            </header>
            <main>
                <div class="videoPanel">
                    <div class="pane">
                        <h3>原图 / 视频</h3>
                        <div class="preview" id="srcPreview">预览区</div>
                    </div>
                    <div class="pane">
                        <h3>检测结果</h3>
                        <div class="preview" id="detPreview">检测结果</div>
                    </div>
                </div>
                <section class="logArea">
                    <div class="logHeader">
                        <h3>日志</h3>
                    </div>
                    <div class="logInner">
                        <div id="logs" class="logs"></div>
                    </div>
                </section>
            </main>
        </div>
        <!-- 右侧按钮栏 -->
        <aside class="right-bar">
            <!-- 1. 模型上传/加载区 -->
            <section class="model-section">
                <button id="uploadModelBtn" class="ghost">上传模型
                    <input id="modelFileInput" type="file" accept=".pt" title="选择 .pt 模型文件">
                </button>
                <button id="loadModel">加载模型</button>
            </section>

            <!-- 2. 检测方式选择区 -->
            <section class="detect-mode-section">
                <div class="detect-mode-title">请选择检测方式</div>
                <div class="detect-mode-radio-group">
                    <label><input type="radio" name="detectMode" value="upload" checked> 图片/视频</label>
                    <label><input type="radio" name="detectMode" value="camera"> 摄像头</label>
                </div>
                <div id="detectModeUpload" class="detect-mode-panel">
                    <div class="uploaded-file-name">
                        <span id="uploadedFileName" class="placeholder">未选择文件</span>
                    </div>
                    <div style="height: 22px;"></div>
                    <button id="uploadBtn">上传文件
                        <input id="fileInput" type="file" accept="image/*,video/*" title="上传图片或视频" aria-label="上传图片或视频">
                    </button>
                </div>
                <div id="detectModeCamera" class="detect-mode-panel" style="display:none;">
                    <button id="cameraDetectBtn" class="ghost">开启摄像头</button>
                    <div id="cameraPreview" class="camera-preview">
                        <video id="localCameraVideo" autoplay muted playsinline></video>
                        <div class="camera-controls">
                            <button id="stopCameraBtn" class="ghost">关闭摄像头</button>
                        </div>
                    </div>
                </div>
                <div class="confWrap">
                    <label class="conf">置信度
                        <input id="confRange" type="range" min="0.01" max="0.99" step="0.01" value="0.5">
                        <input id="confValue" type="number" min="0.01" max="0.99" step="0.01" value="0.5">
                    </label>
                </div>
            </section>

            <!-- 3. 操作按钮区 -->
            <section class="action-btn-section">
                <button id="startBtn" disabled class="start">开始检测</button>
                <button id="stopBtn" disabled class="stop">停止</button>
                <button id="clearLogs" class="ghost">清空日志</button>
            </section>
        </aside>
    </div>
    <script src="/static/app.js"></script>
</body>

</html>