3.7

绘图

绘制注释

Ultralytics 包含一个注释器类，可用于注释任何类型的数据。它最容易用于对象检测边界框、姿势关键点和定向边界框。

Ultralytics 扫频注释

Python 使用YOLO11 🚀 的示例

Python

 

 

 

import cv2

from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator, colors

# User defined video path and model file
cap = cv2.VideoCapture("Path/to/video/file.mp4")
model = YOLO(model="yolo11s-seg.pt")  # Model file i.e. yolo11s.pt or yolo11m-seg.pt

if not cap.isOpened():
    print("Error: Could not open video.")
    exit()

# Initialize the video writer object.
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
video_writer = cv2.VideoWriter("ultralytics.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))

masks = None  # Initialize variable to store masks data
f = 0  # Initialize frame count variable for enabling mouse event.
line_x = w  # Store width of line.
dragging = False  # Initialize bool variable for line dragging.
classes = model.names  # Store model classes names for plotting.
window_name = "Ultralytics Sweep Annotator"


def drag_line(event, x, y, flags, param):  # Mouse callback for dragging line.
    global line_x, dragging
    if event == cv2.EVENT_LBUTTONDOWN or (flags & cv2.EVENT_FLAG_LBUTTON):
        line_x = max(0, min(x, w))
        dragging = True


while cap.isOpened():  # Loop over the video capture object.
    ret, im0 = cap.read()
    if not ret:
        break
    f = f + 1  # Increment frame count.
    count = 0  # Re-initialize count variable on every frame for precise counts.
    annotator = Annotator(im0)
    results = model.track(im0, persist=True)  # Track objects using track method.
    if f == 1:
        cv2.namedWindow(window_name)
        cv2.setMouseCallback(window_name, drag_line)

    if results[0].boxes.id is not None:
        if results[0].masks is not None:
            masks = results[0].masks.xy
        track_ids = results[0].boxes.id.int().cpu().tolist()
        clss = results[0].boxes.cls.cpu().tolist()
        boxes = results[0].boxes.xyxy.cpu()

        for mask, box, cls, t_id in zip(masks or [None] * len(boxes), boxes, clss, track_ids):
            color = colors(t_id, True)  # Assign different color to each tracked object.
            if mask is not None and mask.size > 0:
                # If you want to overlay the masks
                # mask[:, 0] = np.clip(mask[:, 0], line_x, w)
                # mask_img = cv2.fillPoly(im0.copy(), [mask.astype(int)], color)
                # cv2.addWeighted(mask_img, 0.5, im0, 0.5, 0, im0)

                if box[0] > line_x:
                    count += 1
                    annotator.seg_bbox(mask=mask, mask_color=color, label=str(classes[cls]))
            else:
                if box[0] > line_x:
                    count += 1
                    annotator.box_label(box=box, color=color, label=str(classes[cls]))

    annotator.sweep_annotator(line_x=line_x, line_y=h, label=f"COUNT:{count}")  # Display the sweep
    cv2.imshow(window_name, im0)
    video_writer.write(im0)
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

cap.release()  # Release the video capture.
video_writer.release()  # Release the video writer.
cv2.destroyAllWindows()  # Destroy all opened windows.

水平边界框

import cv2 as cv
import numpy as np

from ultralytics.utils.plotting import Annotator, colors

names = {  
    0: "person",
    5: "bus",
    11: "stop sign",
}

image = cv.imread("ultralytics/assets/bus.jpg")
ann = Annotator(
    image,
    line_width=None,  # default auto-size
    font_size=None,  # default auto-size
    font="Arial.ttf",  # must be ImageFont compatible
    pil=False,  # use PIL, otherwise uses OpenCV
)

xyxy_boxes = np.array(
    [
        [5, 22.878, 231.27, 804.98, 756.83],  # class-idx x1 y1 x2 y2
        [0, 48.552, 398.56, 245.35, 902.71],
        [0, 669.47, 392.19, 809.72, 877.04],
        [0, 221.52, 405.8, 344.98, 857.54],
        [0, 0, 550.53, 63.01, 873.44],
        [11, 0.0584, 254.46, 32.561, 324.87],
    ]
)

for nb, box in enumerate(xyxy_boxes):
    c_idx, *box = box
    label = f"{str(nb).zfill(2)}:{names.get(int(c_idx))}"
    ann.box_label(box, label, color=colors(c_idx, bgr=True))

image_with_bboxes = ann.result()

定向边框（OBB）

import cv2 as cv
import numpy as np

from ultralytics.utils.plotting import Annotator, colors

obb_names = {10: "small vehicle"}
obb_image = cv.imread("datasets/dota8/images/train/P1142__1024__0___824.jpg")
obb_boxes = np.array(
    [
        [0, 635, 560, 919, 719, 1087, 420, 803, 261],  # class-idx x1 y1 x2 y2 x3 y2 x4 y4
        [0, 331, 19, 493, 260, 776, 70, 613, -171],
        [9, 869, 161, 886, 147, 851, 101, 833, 115],
    ]
)
ann = Annotator(
    obb_image,
    line_width=None,  # default auto-size
    font_size=None,  # default auto-size
    font="Arial.ttf",  # must be ImageFont compatible
    pil=False,  # use PIL, otherwise uses OpenCV
)
for obb in obb_boxes:
    c_idx, *obb = obb
    obb = np.array(obb).reshape(-1, 4, 2).squeeze()
    label = f"{obb_names.get(int(c_idx))}"
    ann.box_label(
        obb,
        label,
        color=colors(c_idx, True),
        rotated=True,
    )

image_with_obb = ann.result()