File size: 1,528 Bytes
aa975a2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | import cv2, numpy as np
from typing import List, Tuple, Dict
def read_video_meta(video_path: str):
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
raise RuntimeError(f'无法打开视频: {video_path}')
fps = cap.get(cv2.CAP_PROP_FPS) or 30.0
total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT) or 0)
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) or 0)
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) or 0)
cap.release()
return {'fps': fps, 'total': total, 'w': w, 'h': h}
def sample_indices_uniform(total: int, n: int) -> List[int]:
if n<=1 or total<=1:
return [0]
idxs = np.linspace(0, total-1, n, dtype=int).tolist()
return sorted(set(int(i) for i in idxs))
def sample_indices_fps(total: int, native_fps: float, target_fps: float) -> List[int]:
if target_fps <= 0:
target_fps = 1.0
step = max(int(round(native_fps / target_fps)), 1)
idxs = list(range(0, total, step))
return idxs
def grab_frames(video_path: str, indices: List[int]) -> Tuple[List[np.ndarray], Dict[int,int]]:
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
raise RuntimeError(f'无法打开视频: {video_path}')
frames = []
mapping = {} # t -> global index
for i, gi in enumerate(indices):
cap.set(cv2.CAP_PROP_POS_FRAMES, gi)
ok, frame = cap.read()
if not ok:
break
frames.append(frame[:, :, ::-1]) # BGR->RGB for model
mapping[i] = gi
cap.release()
return frames, mapping
|