番外篇-YOLOV10尝鲜

一、番外篇-YOLOV10尝鲜

最近由清华大学的研究团队研发的最新的YOLOV10模型。这一新一代的YOLO模型专注于实时端到端的目标检测。YOLOv10在多个方面进行了改进，包括优化模型架构、消除非极大值抑制（NMS）后处理步骤，并引入了高效的模型设计策略，从而在提高检测精度的同时显著降低了计算开销和推理延迟。
具体来说，YOLOv10的研发团队包括Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han和Guiguang Ding。这些研究人员通过广泛的实验，证明了YOLOv10在不同模型规模上实现了最先进的性能和效率。例如，与YOLOv9-C相比，YOLOv10-B在相同性能下延迟减少了46%，参数减少了25%。
通过这些改进，YOLOv10在实时性和精度方面都达到了新的高度，适用于各种实时目标检测应用，如自动驾驶、视频监控和智能安防等。

好奇心驱使尝试一下v10模型的效果。下载了yolov10s.pt版本，进行实时视频监控测试。
各版本下载和介绍如下：
模型下载：

YOLOv10-N:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10n.pt
YOLOv10-S:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10s.pt
YOLOv10-M:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10m.pt
YOLOv10-B:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10b.pt
YOLOv10-L:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10l.pt
YOLOv10-X:https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10x.pt

模型介绍：
在这里插入图片描述

二、YOLOv10实战：

1.实时检测

30行左右代码构建基于YOLOv10的实时视频监控**
代码如下：运行后电脑摄像头自动开启，实时检测摄像头内的目标。

import cv2
from ultralytics import YOLOv10

model = YOLOv10("yolov10s.pt")
cap = cv2.VideoCapture(0)
while True:
    ret, frame = cap.read()
    if not ret:
        break  # 如果没有读取到帧，退出循环
    results = model.predict(frame)
    # 遍历每个预测结果
    for result in results:
        # 结果中的每个元素对应一张图片的预测
        boxes = result.boxes  # 获取边界框信息
        for box in boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])
            cls = int(box.cls[0])
            conf = float(box.conf[0])
            cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
            cv2.putText(frame, f'{model.names[cls]} {conf:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
                        (255, 0, 0), 2)
    # 显示带有检测结果的帧
    cv2.imshow('YOLOv10实时检测', frame)
    # 按'q'键退出
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放资源
cap.release()
cv2.destroyAllWindows()

检测结果：
在这里插入图片描述
检测效果确实很赞！
参考:基于YOLOv10实现你的第一个视觉AI大模型
另附：基于YOLOv8的实时视频监控写法如下：
代码如下：运行后电脑摄像头自动开启，实时检测摄像头内的目标。
完整代码：

import cv2
from ultralytics import YOLO

model = YOLO("yolov8n.pt")  # 

cap = cv2.VideoCapture(0)

while True:
    ret, frame = cap.read()
    if not ret:
        break  # 如果没有读取到帧，退出循环

    results = model.predict(frame)
    class_counts = {}

    for result in results:
        boxes = result.boxes
        for box in boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])
            cls = int(box.cls[0])
            conf = float(box.conf[0])
            class_name = model.names[cls]

            # 统计每种类别的数量
            if class_name in class_counts:
                class_counts[class_name] += 1
            else:
                class_counts[class_name] = 1

            # 在图像上绘制边界框和标签
            cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
            cv2.putText(frame, f'{class_name} {conf:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
                        (255, 0, 0), 2)

    # 在图像上绘制类别数量
    y_offset = 30
    for class_name, count in class_counts.items():
        cv2.putText(frame, f'{class_name}: {count}', (10, y_offset), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
        y_offset += 30

    # 显示带有检测结果的帧
    cv2.imshow('YOLO实时检测', frame)

    # 按'q'键退出
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放资源
cap.release()
cv2.destroyAllWindows()

检测效果如下：
在这里插入图片描述

2.YOLOV10图片推理：

完整代码如下：


from ultralytics import YOLOv10
import supervision as sv
import cv2

MODEL_PATH = 'yolov10s.pt'
IMAGE_PATH = 'test_images_1/veh2.jpg'

model = YOLOv10(MODEL_PATH)
image  = cv2.imread(IMAGE_PATH)
results = model(source=image, conf=0.25, verbose=False)[0]
detections = sv.Detections.from_ultralytics(results)
box_annotator = sv.BoxAnnotator()

category_dict = {
    0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus',
    6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant',
    11: 'stop sign', 12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat',
    16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear',
    22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag',
    27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard',
    32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove',
    36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle',
    40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl',
    46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli',
    51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut', 55: 'cake',
    56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table',
    61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard',
    67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink',
    72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors',
    77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'
}

labels = [
    f"{category_dict[class_id]} {confidence:.2f}"
    for class_id, confidence in zip(detections.class_id, detections.confidence)
]
annotated_image = box_annotator.annotate(
    image.copy(), detections=detections, labels=labels
)

# cv2.imwrite('result.jpg', annotated_image)

cv2.imshow("res",annotated_image)
cv2.waitKey()
cv2.destroyAllWindows()

检测结果如下：
在这里插入图片描述
参考链接：https://github.com/THU-MIG/yolov10
下载权重：https://github.com/THU-MIG/yolov10/releases/download/v1.0/yolov10n.pt
参考：YOLOv10尝鲜测试五分钟极简配置