我们正在尝试通过以下代码使用 Python 和 YOLOv8 获取检测到的对象名称。
import cv2
from ultralytics import YOLO
def main():
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 1280)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)
model = YOLO("yolov8n.pt")
while True:
ret, frame = cap.read()
result = model(frame, agnostic_nms=True)[0]
print(result)
if cv2.waitKey(30) == 27:
break
cap.release()
cv2.destroyAllWindows()
if __name__ == "__main__":
main()
日志中显示以下两种类型
0: 384x640 1 person, 151.2ms
Speed: 0.6ms preprocess, 151.2ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640)
第二条日志是我们用
printpersonpersonnamesultralytics.yolo.engine.results.Results object with attributes:
boxes: ultralytics.yolo.engine.results.Boxes object
keypoints: None
keys: ['boxes']
masks: None
names: {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'}
orig_img: array([[[51, 58, 64],
[52, 59, 65],
[54, 59, 65],
...,
[64, 68, 74],
[62, 67, 73],
[62, 67, 73]],
[[51, 58, 64],
[53, 59, 65],
[54, 59, 65],
...,
[63, 68, 74],
[62, 67, 73],
[62, 67, 73]],
[[53, 58, 64],
[53, 58, 64],
[53, 58, 64],
...,
[61, 67, 73],
[61, 67, 73],
[61, 67, 73]],
...,
[[43, 48, 58],
[42, 47, 57],
[41, 46, 56],
...,
[24, 35, 49],
[23, 34, 48],
[23, 34, 48]],
[[44, 48, 59],
[43, 47, 57],
[42, 46, 56],
...,
[26, 35, 49],
[26, 35, 49],
[24, 33, 48]],
[[45, 48, 59],
[43, 45, 56],
[40, 43, 54],
...,
[26, 35, 49],
[26, 35, 49],
[25, 33, 48]]], dtype=uint8)
orig_shape: (720, 1280)
path: 'image0.jpg'
probs: None
speed: {'preprocess': 1.6682147979736328, 'inference': 79.47301864624023, 'postprocess': 1.0020732879638672}
我们想通过这种方式知道解决方案。但是如果不行的话，我们可以使用另一种方法，如果是Python和YOLOv8的结合。我们计划显示边界框和对象名称。
我改了代码如下。
ret, frame = cap.read()
# result = model(frame, agnostic_nms=True)[0]
result = model([frame])[0]
boxes = result.boxes
masks = result.masks
probs = result.probs
print("[boxes]==============================")
print(boxes)
print("[masks]==============================")
print(masks)
print("[probs]==============================")
print(probs)
毕竟不包括下面的
person[boxes]==============================
WARNING ⚠️ 'Boxes.boxes' is deprecated. Use 'Boxes.data' instead.
ultralytics.yolo.engine.results.Boxes object with attributes:
boxes: tensor([[4.7356e+01, 7.2858e+00, 1.1974e+03, 7.1092e+02, 8.6930e-01, 0.0000e+00]])
cls: tensor([0.])
conf: tensor([0.8693])
data: tensor([[4.7356e+01, 7.2858e+00, 1.1974e+03, 7.1092e+02, 8.6930e-01, 0.0000e+00]])
id: None
is_track: False
orig_shape: tensor([ 720, 1280])
shape: torch.Size([1, 6])
xywh: tensor([[ 622.4028, 359.1004, 1150.0942, 703.6293]])
xywhn: tensor([[0.4863, 0.4988, 0.8985, 0.9773]])
xyxy: tensor([[ 47.3557, 7.2858, 1197.4500, 710.9150]])
xyxyn: tensor([[0.0370, 0.0101, 0.9355, 0.9874]])
[masks]==============================
None
[probs]==============================
None
inputs = [img, img] # list of numpy arrays
results = model(inputs) # list of Results objects
for result in results:
boxes = result.boxes # Boxes object for bbox outputs
masks = result.masks # Masks object for segmentation masks outputs
probs = result.probs # Class probabilities for classification outputs
参考Yolov8文档
我试着按如下方式得到它我还没有弄清楚这是否正确。
print(result.names[int(result.boxes.cls[0])])
可能有更好的解决方案，但我也找不到任何有用的东西，所以我这样做了：
while True:
ret, frame = cap.read()
results = model(frame, agnostic_nms=True)[0]
if not results or len(results) == 0:
continue
for result in results:
detection_count = result.boxes.shape[0]
for i in range(detection_count):
cls = int(result.boxes.cls[i].item())
name = result.names[cls]
confidence = float(result.boxes.conf[i].item())
bounding_box = result.boxes.xyxy[i].cpu().numpy()
x = int(bounding_box[0])
y = int(bounding_box[1])
width = int(bounding_box[2] - x)
height = int(bounding_box[3] - y)