跳至内容

使用Ultralytics YOLOv8 绘制 VisionEye 视图对象映射 🚀

什么是 VisionEye Object Mapping?

Ultralytics YOLOv8VisionEye 可让计算机模拟人眼的观察精度,识别并精确定位物体。这一功能使计算机能够辨别并聚焦于特定物体,就像人眼从特定视角观察细节一样。

样品

VisionEye 视图 带有物体跟踪功能的 VisionEye 视图 带有距离计算功能的 VisionEye 视图
使用 VisionEye 视图对象映射Ultralytics YOLOv8 使用 VisionEye 视图对象映射与对象跟踪功能Ultralytics YOLOv8 使用 VisionEye View 进行距离计算Ultralytics YOLOv8
使用 VisionEye 视图对象映射Ultralytics YOLOv8 使用 VisionEye 视图对象映射与对象跟踪功能Ultralytics YOLOv8 使用 VisionEye View 进行距离计算Ultralytics YOLOv8

使用 VisionEye 物体映射YOLOv8

import cv2

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

model = YOLO("yolov8n.pt")
names = model.model.names
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))

out = cv2.VideoWriter("visioneye-pinpoint.avi", cv2.VideoWriter_fourcc(*"MJPG"), fps, (w, h))

center_point = (-10, h)

while True:
    ret, im0 = cap.read()
    if not ret:
        print("Video frame is empty or video processing has been successfully completed.")
        break

    results = model.predict(im0)
    boxes = results[0].boxes.xyxy.cpu()
    clss = results[0].boxes.cls.cpu().tolist()

    annotator = Annotator(im0, line_width=2)

    for box, cls in zip(boxes, clss):
        annotator.box_label(box, label=names[int(cls)], color=colors(int(cls)))
        annotator.visioneye(box, center_point)

    out.write(im0)
    cv2.imshow("visioneye-pinpoint", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

out.release()
cap.release()
cv2.destroyAllWindows()
import cv2

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

model = YOLO("yolov8n.pt")
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))

out = cv2.VideoWriter("visioneye-pinpoint.avi", cv2.VideoWriter_fourcc(*"MJPG"), fps, (w, h))

center_point = (-10, h)

while True:
    ret, im0 = cap.read()
    if not ret:
        print("Video frame is empty or video processing has been successfully completed.")
        break

    annotator = Annotator(im0, line_width=2)

    results = model.track(im0, persist=True)
    boxes = results[0].boxes.xyxy.cpu()

    if results[0].boxes.id is not None:
        track_ids = results[0].boxes.id.int().cpu().tolist()

        for box, track_id in zip(boxes, track_ids):
            annotator.box_label(box, label=str(track_id), color=colors(int(track_id)))
            annotator.visioneye(box, center_point)

    out.write(im0)
    cv2.imshow("visioneye-pinpoint", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

out.release()
cap.release()
cv2.destroyAllWindows()
import math

import cv2

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

model = YOLO("yolov8s.pt")
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))

out = cv2.VideoWriter("visioneye-distance-calculation.avi", cv2.VideoWriter_fourcc(*"MJPG"), fps, (w, h))

center_point = (0, h)
pixel_per_meter = 10

txt_color, txt_background, bbox_clr = ((0, 0, 0), (255, 255, 255), (255, 0, 255))

while True:
    ret, im0 = cap.read()
    if not ret:
        print("Video frame is empty or video processing has been successfully completed.")
        break

    annotator = Annotator(im0, line_width=2)

    results = model.track(im0, persist=True)
    boxes = results[0].boxes.xyxy.cpu()

    if results[0].boxes.id is not None:
        track_ids = results[0].boxes.id.int().cpu().tolist()

        for box, track_id in zip(boxes, track_ids):
            annotator.box_label(box, label=str(track_id), color=bbox_clr)
            annotator.visioneye(box, center_point)

            x1, y1 = int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2)  # Bounding box centroid

            distance = (math.sqrt((x1 - center_point[0]) ** 2 + (y1 - center_point[1]) ** 2)) / pixel_per_meter

            text_size, _ = cv2.getTextSize(f"Distance: {distance:.2f} m", cv2.FONT_HERSHEY_SIMPLEX, 1.2, 3)
            cv2.rectangle(im0, (x1, y1 - text_size[1] - 10), (x1 + text_size[0] + 10, y1), txt_background, -1)
            cv2.putText(im0, f"Distance: {distance:.2f} m", (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 1.2, txt_color, 3)

    out.write(im0)
    cv2.imshow("visioneye-distance-calculation", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

out.release()
cap.release()
cv2.destroyAllWindows()

visioneye 论据

名称 类型 默认值 说明
color tuple (235, 219, 11) 线条和对象中心点颜色
pin_color tuple (255, 0, 255) VisionEye 精确定位色彩

备注

如有任何疑问,请随时在Ultralytics 问题板块或下面提到的讨论板块发布您的问题。



Created 2023-12-18, Updated 2024-06-10
Authors: glenn-jocher (11), IvorZhu331 (1), RizwanMunawar (1)

评论