HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add arguments for solutions in usage/cfg docs page (#17920)

Browse source 
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Muhammad Rizwan Munawar 2024-12-02 19:50:23 +05:00 • committed by GitHub
parent d59a66f7c2
commit 9cf7b50392
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 19 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/en/guides/instance-segmentation-and-tracking.md
View file

@ -82,15 +82,11 @@ There are two types of instance segmentation tracking available in the Ultralyti
=== "Instance Segmentation with Object Tracking"
```python
from collections import defaultdict
import cv2
from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator, colors
track_history = defaultdict(lambda: [])
model = YOLO("yolo11n-seg.pt") # segmentation model
cap = cv2.VideoCapture("path/to/video/file.mp4")
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
@ -205,15 +201,11 @@ To implement object tracking, use the `model.track` method and ensure that each
=== "Python"
```python
from collections import defaultdict
import cv2
from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator, colors
track_history = defaultdict(lambda: [])
model = YOLO("yolo11n-seg.pt") # segmentation model
cap = cv2.VideoCapture("path/to/video/file.mp4")
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))

11
docs/en/macros/solutions-args.md Normal file
View file

@ -0,0 +1,11 @@
| Argument | Type | Default | Description |
| ---------------- | -------------- | -------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `region` | `list` | `[(20, 400), (1080, 400), (1080, 360), (20, 360)]` | Defines the region points for object counting, queue monitoring, trackzone or speed estimation. The points are defined as coordinates forming a polygonal area for analysis. |
| `show_in` | `bool` | `True` | Indicates whether to display objects that are counted as entering the defined region. Essential for real-world analytics, such as monitoring ingress trends. |
| `show_out` | `bool` | `True` | Indicates whether to display objects that are counted as exiting the defined region. Useful for applications requiring egress tracking and analytics. |
| `colormap` | `int or tuple` | `COLORMAP_PARULA` | Specifies the OpenCV-supported colormap for heatmap visualization. Default is `COLORMAP_PARULA`, but other colormaps can be used for different visualization preferences. |
| `up_angle` | `float` | `145.0` | Angle threshold for detecting the "up" position in workouts monitoring. Can be adjusted based on the position of keypoints for different exercises. |
| `down_angle` | `float` | `90.0` | Angle threshold for detecting the "down" position in workouts monitoring. Adjust this based on keypoint positions for specific exercises. |
| `kpts` | `list` | `[6, 8, 10]` | List of keypoints used for monitoring workouts. These keypoints correspond to body joints or parts, such as shoulders, elbows, and wrists, for exercises like push-ups, pull-ups, squats, ab-workouts. |
| `analytics_type` | `str` | `line` | Specifies the type of analytics visualization to generate. Options include `"line"`, `"pie"`, `"bar"`, or `"area"`. The default is `"line"` for trend visualization. |
| `json_file` | `str` | `None` | Path to the JSON file defining regions for parking systems or similar applications. Enables flexible configuration of analysis areas. |

8
docs/en/usage/cfg.md
View file

@ -130,6 +130,14 @@ It is crucial to thoughtfully configure these settings to ensure the exported mo
[Export Guide](../modes/export.md){ .md-button }
## Solutions Settings
The configuration settings for Ultralytics Solutions offer a flexible way to customize the model for various tasks like object counting, heatmap creation, workout tracking, data analysis, zone tracking, queue management, and region-based counting. These options make it easy to adjust the setup for accurate and useful results tailored to specific needs.
{% include "macros/solutions-args.md" %}
[Solutions Guide](../solutions/index.md){ .md-button }
## Augmentation Settings
Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the [training data](https://www.ultralytics.com/glossary/training-data), helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: