OpenCV与AI深度学习 | 如何使用YOLOv9检测图片和视频中的目标-白红宇

OpenCV与AI深度学习 | 如何使用YOLOv9检测图片和视频中的目标

阅读量：792 次

发布时间：2023-02-23

本文共 3049 字，大约阅读时间需要 10 分钟。

YOLOv9?????????????

?????????????YOLOv8??????????????YOLOv9??????????????????????????

YOLOv9???????????????????15%?????40%??????????????

????YOLOv9???????

??????????

???????????????

pip install opencv-python ultralytics

???????

??????YOLOv9??

import cv2
from ultralytics import YOLO

????????

??YOLOv9???

model = YOLO("yolov9c.pt")

??????????????????????????????????

https://docs.ultralytics.com/de/models/yolov9/#impact-on-lightweight-models

?????????????

???????predict() ? predict_and_detect()?

def predict(chosen_model, img, classes=[], conf=0.5):
    if classes:
        results = chosen_model.predict(img, classes=classes, conf=conf)
    else:
        results = chosen_model.predict(img, conf=conf)
    return results
def predict_and_detect(chosen_model, img, classes=[], conf=0.5, rectangle_thickness=2, text_thickness=1):
    results = predict(chosen_model, img, classes, conf)
    for result in results:
        for box in result.boxes:
            cv2.rectangle(img, (int(box.xyxy[0][0]), int(box.xyxy[0][1])),
                          (int(box.xyxy[0][2]), int(box.xyxy[0][3])),
                          (255, 0, 0), rectangle_thickness)
            cv2.putText(img, f"{result.names[int(box.cls[0])}",
                        (int(box.xyxy[0][0]), int(box.xyxy[0][1]) - 10),
                        cv2.FONT_HERSHEY_PLAIN, 1, (255, 0, 0), text_thickness)
    return img, results

predict() ?????????

chosen_model??????????

img?????????

classes??????????????

conf??????????

????????????????????????????????????????

predict_and_detect() ??? predict() ????????????????????????

????YOLOv9????????

??????????

image = cv2.imread("YourImagePath")
result_img, _ = predict_and_detect(model, image, classes=[], conf=0.5)

?????????????????????????????????????????ID?

https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml

???YOLOv9?????

???????????

video_path = r"YourVideoPath"
cap = cv2.VideoCapture(video_path)
while True:
    success, img = cap.read()
    if not success:
        break
    result_img, _ = predict_and_detect(model, img, classes=[], conf=0.5)
    cv2.imshow("Image", result_img)
    cv2.waitKey(1)

????????

???????????

def create_video_writer(video_cap, output_filename):
    frame_width = int(video_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    frame_height = int(video_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    fps = int(video_cap.get(cv2.CAP_PROP_FPS))
    fourcc = cv2.VideoWriter_fourcc(*'MP4V')
    writer = cv2.VideoWriter(output_filename, fourcc, fps,
                             (frame_width, frame_height))
    return writer
output_filename = "YourFilename"
writer = create_video_writer(cap, output_filename)
video_path = r"YourVideoPath"
cap = cv2.VideoCapture(video_path)
while True:
    success, img = cap.read()
    if not success:
        break
    result_img, _ = predict_and_detect(model, img, classes=[], conf=0.5)
    writer.write(result_img)
    cv2.imshow("Image", result_img)
    cv2.waitKey(1)
writer.release()