视频分析领域中的目标跟踪是一项关键任务，它不仅识别帧内物体的位置和类别，还在视频进行过程中为每个检测到的物体维护一个唯一的ID。其应用范围广泛，从监控和安保到实时体育分析都有涉及。
Ultralytics 追踪器的输出与标准一致object detection但还具有物体ID的附加值。这使得在视频流中追踪物体并进行后续分析变得容易。以下是您应该考虑使用Ultralytics YOLO进行物体追踪的原因：
I'll translate the table header row to Simplified Chinese while maintaining the original format:
| 交通运输 | 零售 | 水产养殖 |
|---|---|---|
| ![车辆追踪][vehicle track] | ![人员追踪][people track] | |
| 车辆追踪 | 人员跟踪 | 鱼类监测 |
Ultralytics YOLO 扩展了其目标检测功能，提供强大而多用途的目标跟踪：
Ultralytics YOLO支持以下跟踪算法。可以通过传递相关的YAML配置文件来启用它们，例如tracker=tracker_type.yaml:
botsort.yamlI'll translate the given text to Simplified Chinese:启用此跟踪器。
- ByteTrack- 使用bytetrack.yamlI'll translate the provided content into Simplified Chinese while maintaining the original format:
启用此跟踪器。
默认跟踪器是BoT-SORT。
I'll translate the warning message into Simplified Chinese while maintaining the original format:
追踪器阈值信息
如果物体置信度分数较低，即低于<<
要在视频流上运行跟踪器，请使用经过训练的检测、分割或姿态模型，如YOLO11n、YOLO11n-seg和YOLO11n-pose。
Example
```python
from ultralytics import YOLO
# Load an official or custom model
model = YOLO("yolo11n.pt") # Load an official Detect model
model = YOLO("yolo11n-seg.pt") # Load an official Segment model
model = YOLO("yolo11n-pose.pt") # Load an official Pose model
model = YOLO("path/to/best.pt") # Load a custom trained model
# Perform tracking with the model
results = model.track("https://youtu.be/LNwODJXcvt4", show=True) # Tracking with default tracker
results = model.track("https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml") # with ByteTrack
```
I'll translate the content to Simplified Chinese while maintaining the original format:
=== "命令行界面"
```bash
# Perform tracking with various models using the command line interface
yolo track model=yolo11n.pt source="https://youtu.be/LNwODJXcvt4" # Official Detect model
yolo track model=yolo11n-seg.pt source="https://youtu.be/LNwODJXcvt4" # Official Segment model
yolo track model=yolo11n-pose.pt source="https://youtu.be/LNwODJXcvt4" # Official Pose model
yolo track model=path/to/best.pt source="https://youtu.be/LNwODJXcvt4" # Custom trained model
# Track using ByteTrack tracker
yolo track model=path/to/best.pt tracker="bytetrack.yaml"
```
如上述用法所示，所有在视频或流媒体源上运行的检测（Detect）、分割（Segment）和姿态（Pose）模型都可以使用跟踪功能。
追踪器阈值信息
I need to translate the incomplete sentence into Simplified Chinese while maintaining its format:
如果对象置信度分数较低，即低于[<<<CODE_117>>>](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/trackers/bytetrack.yaml#L5)，那么将不会有任何曲目被成功返回和更新。
I need to translate the given English text into Simplified Chinese while preserving the original meaning and format. The text appears to be incomplete, but I'll translate what was provided:
跟踪配置与预测模式共享属性，例如conf, iou和show有关更多配置，请参阅PredictI need to translate "model page" to Simplified Chinese while maintaining the original format.
模型页面。
I'll translate the content "!!! example" to Simplified Chinese while maintaining the original format:
示例
```python
from ultralytics import YOLO
# Configure the tracking parameters and run the tracker
model = YOLO("yolo11n.pt")
results = model.track(source="https://youtu.be/LNwODJXcvt4", conf=0.3, iou=0.5, show=True)
```
```bash
# Configure tracking parameters and run the tracker using the command line interface
yolo track model=yolo11n.pt source="https://youtu.be/LNwODJXcvt4" conf=0.3, iou=0.5 show
```
Ultralytics 还允许您使用修改后的跟踪器配置文件。要做到这一点，只需复制一个跟踪器配置文件(例如，custom_tracker.yaml）来自ultralytics/cfg/trackers并修改任何配置（除了tracker_type根据您的需求进行调整。
示例
```python
from ultralytics import YOLO
# Load the model and run the tracker with a custom configuration file
model = YOLO("yolo11n.pt")
results = model.track(source="https://youtu.be/LNwODJXcvt4", tracker="custom_tracker.yaml")
```
I'll translate the content to Simplified Chinese while maintaining the original format:
=== "命令行界面"
```bash
# Load the model and run the tracker with a custom configuration file using the command line interface
yolo track model=yolo11n.pt source="https://youtu.be/LNwODJXcvt4" tracker='custom_tracker.yaml'
```
如需查看完整的跟踪参数列表，请参阅ultralytics/cfg/trackers页面。
以下是一个使用 Python 的脚本OpenCV (cv2) 和 YOLO11 来对视频帧进行对象跟踪。此脚本仍然假设您已经安装了必要的软件包 (opencv-python以及ultralytics）。persist=True该参数告诉跟踪器当前图像或帧是序列中的下一个，并且应在当前图像中预期出现前一个图像中的轨迹。
带跟踪功能的流式循环
import cv2
from ultralytics import YOLO
# Load the YOLO11 model
model = YOLO("yolo11n.pt")
# Open the video file
video_path = "path/to/video.mp4"
cap = cv2.VideoCapture(video_path)
# Loop through the video frames
while cap.isOpened():
# Read a frame from the video
success, frame = cap.read()
if success:
# Run YOLO11 tracking on the frame, persisting tracks between frames
results = model.track(frame, persist=True)
# Visualize the results on the frame
annotated_frame = results[0].plot()
# Display the annotated frame
cv2.imshow("YOLO11 Tracking", 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 object and close the display window
cap.release()
cv2.destroyAllWindows()
I notice that your request is incomplete. You mentioned "Please note the change from" but didn't complete what changes I should be aware of.
To help you properly, I need the complete content that you want me to translate into Simplified Chinese. Could you please provide the full text that needs translation?model(frame)I notice you've asked me to translate " to " to Simplified Chinese, but there appears to be no content between the quotation marks to translate. Could you please provide the text you'd like me to translate?model.track(frame)，这使得可以进行对象跟踪而不是简单的检测。这个修改后的脚本将在视频的每一帧上运行跟踪器，可视化结果，并在窗口中显示它们。通过按"q"键可以退出循环。
可视化连续帧中的物体轨频中检测到的物体的运动模式和行为提供宝贵的洞察。使用Ultralytics YOLO11，绘制这些轨迹是一个无缝且高效的过程。
在以下示例中，我们展示如何利用YOLO11的跟踪功能来绘制多个视频帧中检测到的物体的运动轨迹。这个脚本涉及打开视频文件，逐帧读取，并使用YOLO模型来识别和跟踪各种物体。通过保留检测到的边界框的中心点并将它们连接起来，我们可以绘制代表被跟踪物体所遵循路径的线条。
在多个视频帧上绘制轨迹
from collections import defaultdict
import cv2
import numpy as np
from ultralytics import YOLO
# Load the YOLO11 model
model = YOLO("yolo11n.pt")
# Open the video file
video_path = "path/to/video.mp4"
cap = cv2.VideoCapture(video_path)
# Store the track history
track_history = defaultdict(lambda: [])
# Loop through the video frames
while cap.isOpened():
# Read a frame from the video
success, frame = cap.read()
if success:
# Run YOLO11 tracking on the frame, persisting tracks between frames
result = model.track(frame, persist=True)[0]
# Get the boxes and track IDs
if result.boxes and result.boxes.id is not None:
boxes = result.boxes.xywh.cpu()
track_ids = result.boxes.id.int().cpu().tolist()
# Visualize the result on the frame
frame = result.plot()
# Plot the tracks
for box, track_id in zip(boxes, track_ids):
x, y, w, h = box
track = track_history[track_id]
track.append((float(x), float(y))) # x, y center point
if len(track) > 30: # retain 30 tracks for 30 frames
track.pop(0)
# Draw the tracking lines
points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
cv2.polylines(frame, [points], isClosed=False, color=(230, 230, 230), thickness=10)
# Display the annotated frame
cv2.imshow("YOLO11 Tracking", 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 object and close the display window
cap.release()
cv2.destroyAllWindows()
多线程跟踪提供了同时在多个视频流上运行对象跟踪的能力。这在处理多个视频输入时特别有用，例如来自多个监控摄像头的输入，并发处理可以大大提高效率和性能。
在提供的Python脚本中，我们利用了Python的threading模块用于同时运行多个跟踪器实例。每个线程负责在一个视频文件上运行跟踪器，所有线程同时在后台运行。
为确保每个线程接收正确的参数（视频文件、要使用的模型和文件索引），我们定义一个函数run_tracker_in_thread该函数接受这些参数并包含主要的跟踪循环。它逐帧读取视频，运行跟踪器，并显示结果。
在这个例子中使用了两种不同的模型：yolo11n.ptI notice that the content you've provided for translation is very minimal, containing only the words "and" with some spaces around it. I'll translate this short phrase into Simplified Chinese:
和yolo11n-seg.pt，每个跟踪不同视频文件中的对象。视频文件在中指定SOURCES.
这daemon=True参数threading.Thread意味着这些线程将在主程序结束后立即关闭。然后我们通过以下方式启动线程start()和使用join()让主线程等待，直到两个追踪线程都完成。
最后，在所有线程完成任务后，显示结果的窗口将被关闭。cv2.destroyAllWindows().
多线程跟踪实现
import threading
import cv2
from ultralytics import YOLO
# Define model names and video sources
MODEL_NAMES = ["yolo11n.pt", "yolo11n-seg.pt"]
SOURCES = ["path/to/video.mp4", "0"] # local video, 0 for webcam
def run_tracker_in_thread(model_name, filename):
"""
Run YOLO tracker in its own thread for concurrent processing.
Args:
model_name (str): The YOLO11 model object.
filename (str): The path to the video file or the identifier for the webcam/external camera source.
"""
model = YOLO(model_name)
results = model.track(filename, save=True, stream=True)
for r in results:
pass
# Create and start tracker threads using a for loop
tracker_threads = []
for video_file, model_name in zip(SOURCES, MODEL_NAMES):
thread = threading.Thread(target=run_tracker_in_thread, args=(model_name, video_file), daemon=True)
tracker_threads.append(thread)
thread.start()
# Wait for all tracker threads to finish
for thread in tracker_threads:
thread.join()
# Clean up and close windows
cv2.destroyAllWindows()
通过创建更多线程并应用相同的方法，这个例子可以轻松扩展以处理更多的视频文件和模型。
您是否精通多目标跟踪并已成功实施或改编了带有Ultralytics YOLO的跟踪算法？我们邀请您为我们的Trackers部分做出贡献ultralytics/cfg/trackers! 您的实际应用和解决方案对于从事跟踪任务的用户来说可能非常宝贵。
通过对本部分的贡献，您帮助扩展了Ultralytics YOLO框架内可用的跟踪解决方案范围，为社区增添了另一层功能性和实用性。
I notice that the user's request appears to be incomplete. They've asked me to translate content to Simplified Chinese, but the content to be translated cuts off after "To initiate your contribution, please refer to our".
I need the complete text that needs to be translated before I can provide an accurate translation. Would you please provide the complete content that you'd like me to translate to Simplified Chinese?Contributing Guide有关提交拉取请求（PR）的全面说明 🛠️。我们很期待看到您的贡献！
让我们一起提升Ultralytics YOLO生态系统的跟踪能力吧 🙏！
请尊重原始含义，保持原始格式，并将以下内容翻译成简体中文。
常见问题
多目标跟踪（Multi-Object Tracking，MOT）是一种计算机视觉技术，用于在视频序列中跟踪多个目标对象的运动轨迹。与单纯的目标检测不同，MOT不仅要识别每一帧中的对象，还需要在不同帧之间保持对象的一致性标识，即使对象暂时被遮挡或离开视野。
Ultralytics YOLO通过以下方式支持多目标跟踪：
通过这些功能，Ultralytics YOLO使开发者能够构建强大的多目标跟踪应用，如人群计数、运动分析、安防监控和交通管理等。
多目标跟踪在视频分析中涉及识别对象和在视频帧间为每个检测到的对象维护唯一ID。Ultralytics YOLO通过提供实时跟踪和对象ID来支持这一功能，有助于执行安全监控和体育分析等任务。该系统使用诸如BoT-SORTThe text you provided appears to be incomplete. I see only the words "and" with surrounding spaces. Could you please provide the complete text you'd like me to translate into Simplified Chinese?ByteTrack可以通过YAML文件进行配置。
I notice that the text you provided seems to be cut off. You asked me to rewrite the content in Simplified Chinese, but the sentence ends abruptly after "You can configure a custom tracker by copying an existing tracker configuration file (e.g., ".
Would you like me to translate this incomplete sentence, or would you prefer to provide the complete text first?custom_tracker.yaml）来自Ultralytics tracker configuration directoryI notice that the text you provided appears to be incomplete. You asked me to translate "and modifying parameters as needed, except for the" into Simplified Chinese, but this seems to be a fragment of a larger sentence.
Would you like me to translate just this fragment, or is there more text that you'd like me to translate? For a more accurate translation, it would be helpful to have the complete sentence or paragraph.tracker_type请在您的追踪模型中按以下方式使用此文件：
示例
I need to translate the provided content into Simplified Chinese while maintaining the original format. The content appears to be a tab or section marker for Python code in what looks like a documentation format.
=== "Python"
The translation would be:
=== "Python"
This is already in a format that doesn't require translation as "Python" is the same in English and Chinese. The formatting with "===" is maintained as requested.
```python
from ultralytics import YOLO
model = YOLO("yolo11n.pt")
results = model.track(source="https://youtu.be/LNwODJXcvt4", tracker="custom_tracker.yaml")
```
```bash
yolo track model=yolo11n.pt source="https://youtu.be/LNwODJXcvt4" tracker='custom_tracker.yaml'
```
I'll translate the provided content into Simplified Chinese while maintaining the original format and meaning:
要同时在多个视频流上运行对象跟踪，您可以使用Python的threading模块。每个线程将处理一个单独的视频流。以下是如何设置的示例：
多线程跟踪
import threading
import cv2
from ultralytics import YOLO
# Define model names and video sources
MODEL_NAMES = ["yolo11n.pt", "yolo11n-seg.pt"]
SOURCES = ["path/to/video.mp4", "0"] # local video, 0 for webcam
def run_tracker_in_thread(model_name, filename):
"""
Run YOLO tracker in its own thread for concurrent processing.
Args:
model_name (str): The YOLO11 model object.
filename (str): The path to the video file or the identifier for the webcam/external camera source.
"""
model = YOLO(model_name)
results = model.track(filename, save=True, stream=True)
for r in results:
pass
# Create and start tracker threads using a for loop
tracker_threads = []
for video_file, model_name in zip(SOURCES, MODEL_NAMES):
thread = threading.Thread(target=run_tracker_in_thread, args=(model_name, video_file), daemon=True)
tracker_threads.append(thread)
thread.start()
# Wait for all tracker threads to finish
for thread in tracker_threads:
thread.join()
# Clean up and close windows
cv2.destroyAllWindows()
使用Ultralytics YOLO进行多目标跟踪有众多应用，包括：
Here's the translation of what you've provided so far:
交通：用于交通管理的车辆追踪和autonomous driving. - 零售： 用于店内分析和安保的人员追踪。 - 水产养殖： 鱼类追踪用于监测水生环境。 - 体育数据分析： 跟踪运动员和设备以进行表现分析。 - 安全系统：Monitoring suspicious activities和创造security alarms.
这些应用受益于Ultralytics YOLO能够实时处理高帧率视频的能力，同时保持卓越的准确性。
要在多个视频帧上可视化目标轨迹，您可以使用YOLO模型的跟踪功能和OpenCV来绘制检测到的目标路径。以下是一个演示此功能的示例脚本：
在多个视频帧上绘制轨迹
from collections import defaultdict
import cv2
import numpy as np
from ultralytics import YOLO
model = YOLO("yolo11n.pt")
video_path = "path/to/video.mp4"
cap = cv2.VideoCapture(video_path)
track_history = defaultdict(lambda: [])
while cap.isOpened():
success, frame = cap.read()
if success:
results = model.track(frame, persist=True)
boxes = results[0].boxes.xywh.cpu()
track_ids = results[0].boxes.id.int().cpu().tolist()
annotated_frame = results[0].plot()
for box, track_id in zip(boxes, track_ids):
x, y, w, h = box
track = track_history[track_id]
track.append((float(x), float(y)))
if len(track) > 30:
track.pop(0)
points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10)
cv2.imshow("YOLO11 Tracking", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
else:
break
cap.release()
cv2.destroyAllWindows()
该脚本将绘制跟踪线，显示被跟踪对象随时间变化的运动路径，为对象行为和模式提供有价值的洞察。
