Chengfang Lu
e72bc061c5
Major changes: - New frontend (platform/web/): Vite + React 18 + TypeScript + Tailwind - 4-module navigation: 数据送标 / 模型管理 / 车队管理 / 系统管理 - Data catalog with charts (DMS/ADAS/Lane 3-tab view) - Quality review workflow (标注质检): Good/Fine/Bad scoring with auto-advance - Audit enhancements: batch operations, rejection categories, Feishu notifications - Operation audit log (操作日志) - World model simulation studio (仿真工坊) - Dataset version management with snapshots and diff - ADAS 7-class dataset integration (138K images organized + compressed) - User management with Feishu integration and pagination - CRUD/search/filter on all pages, card layout redesign - PIL-optimized image overlay rendering - Auto-snapshot on build, in_review workflow stage - Removed embedded algorithm code (now in workspace)
68 lines
2.9 KiB
Python
68 lines
2.9 KiB
Python
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
|
|
|
from typing import Any
|
|
|
|
from ultralytics.solutions.solutions import BaseSolution, SolutionAnnotator, SolutionResults
|
|
from ultralytics.utils.plotting import colors
|
|
|
|
|
|
class VisionEye(BaseSolution):
|
|
"""A class to manage object detection and vision mapping in images or video streams.
|
|
|
|
This class extends the BaseSolution class and provides functionality for detecting objects, mapping vision points,
|
|
and annotating results with bounding boxes and labels.
|
|
|
|
Attributes:
|
|
vision_point (tuple[int, int]): Coordinates (x, y) where vision will view objects and draw tracks.
|
|
|
|
Methods:
|
|
process: Process the input image to detect objects, annotate them, and apply vision mapping.
|
|
|
|
Examples:
|
|
>>> vision_eye = VisionEye()
|
|
>>> frame = cv2.imread("frame.jpg")
|
|
>>> results = vision_eye.process(frame)
|
|
>>> print(f"Total detected instances: {results.total_tracks}")
|
|
"""
|
|
|
|
def __init__(self, **kwargs: Any) -> None:
|
|
"""Initialize the VisionEye class for detecting objects and applying vision mapping.
|
|
|
|
Args:
|
|
**kwargs (Any): Keyword arguments passed to the parent class and for configuring vision_point.
|
|
"""
|
|
super().__init__(**kwargs)
|
|
# Set the vision point where the system will view objects and draw tracks
|
|
self.vision_point = self.CFG["vision_point"]
|
|
|
|
def process(self, im0) -> SolutionResults:
|
|
"""Perform object detection, vision mapping, and annotation on the input image.
|
|
|
|
Args:
|
|
im0 (np.ndarray): The input image for detection and annotation.
|
|
|
|
Returns:
|
|
(SolutionResults): Object containing the annotated image and tracking statistics.
|
|
- plot_im: Annotated output image with bounding boxes and vision mapping
|
|
- total_tracks: Number of tracked objects in the frame
|
|
|
|
Examples:
|
|
>>> vision_eye = VisionEye()
|
|
>>> frame = cv2.imread("image.jpg")
|
|
>>> results = vision_eye.process(frame)
|
|
>>> print(f"Detected {results.total_tracks} objects")
|
|
"""
|
|
self.extract_tracks(im0) # Extract tracks (bounding boxes, classes, and masks)
|
|
annotator = SolutionAnnotator(im0, self.line_width)
|
|
|
|
for cls, t_id, box, conf in zip(self.clss, self.track_ids, self.boxes, self.confs):
|
|
# Annotate the image with bounding boxes, labels, and vision mapping
|
|
annotator.box_label(box, label=self.adjust_box_label(cls, conf, t_id), color=colors(int(t_id), True))
|
|
annotator.visioneye(box, self.vision_point)
|
|
|
|
plot_im = annotator.result()
|
|
self.display_output(plot_im) # Display the annotated output using the base class function
|
|
|
|
# Return a SolutionResults object with the annotated image and tracking statistics
|
|
return SolutionResults(plot_im=plot_im, total_tracks=len(self.track_ids))
|