在下面的代码中，我使用开放式简历和带字节轨道的监督来跟踪和计数视频，当视频正常工作并提供良好的输出时。当我实时工作时，它会丢失一些帧，因此视频编辑器也会提供非常快速的视频。请检查运行的代码，您可以看到它。 请帮助我真的很感激。我真的很感动
`https://www.youtube.com/watch?v=OS5qI9YBkfk 我用上面的视频..
from typing import List
import supervision
import cv2
from supervision.draw.color import ColorPalette
from supervision.geometry.dataclasses import Point
from supervision.video.dataclasses import VideoInfo
from supervision.video.source import get_video_frames_generator
from supervision.video.sink import VideoSink
from supervision.notebook.utils import show_frame_in_notebook
from supervision.tools.detections import Detections, BoxAnnotator
from supervision.tools.line_counter import LineCounter, LineCounterAnnotator
from yolox.tracker.byte_tracker import BYTETracker, STrack
from onemetric.cv.utils.iou import box_iou_batch
from dataclasses import dataclass
import numpy as np
from ultralytics import YOLO
from tqdm.notebook import tqdm
import time
import os
import random
import sys
LINE_START = Point(630, 300)
LINE_END = Point(50, 300)
model = YOLO("best_yolov8.pt")
CLASS_NAMES_DICT = model.model.names
# class_ids of interest - car, motorcycle, bus and truck
CLASS_ID = [0]
fps = 30
width = 1280
height = 1280
video_codec = cv2.VideoWriter_fourcc("D", "I", "V", "X")
@dataclass(frozen=True)
class BYTETrackerArgs:
track_thresh: float = 0.25
track_buffer: int = 30
match_thresh: float = 0.8
aspect_ratio_thresh: float = 3.0
min_box_area: float = 1.0
mot20: bool = False
# converts Detections into format that can be consumed by match_detections_with_tracks function
def detections2boxes(detections: Detections) -> np.ndarray:
return np.hstack((
detections.xyxy,
detections.confidence[:, np.newaxis]
))
# converts List[STrack] into format that can be consumed by match_detections_with_tracks function
def tracks2boxes(tracks:List[STrack]) -> np.ndarray:
return np.array([
track.tlbr
for track
in tracks
], dtype=float)
# matches our bounding boxes with predictions
def match_detections_with_tracks(
detections: Detections,
tracks: List[STrack]
) -> Detections:
if not np.any(detections.xyxy) or len(tracks) == 0:
return np.empty((0,))
tracks_boxes = tracks2boxes(tracks=tracks)
iou = box_iou_batch(tracks_boxes, detections.xyxy)
track2detection = np.argmax(iou, axis=1)
tracker_ids = [None] * len(detections)
for tracker_index, detection_index in enumerate(track2detection):
if iou[tracker_index, detection_index] != 0:
tracker_ids[detection_index] = tracks[tracker_index].track_id
return tracker_ids
byte_tracker = BYTETracker(BYTETrackerArgs())
# create VideoInfo instance
name = random.randint(0, 1000)
print(name)
if os.path.isdir(str(name)) is False:
name = random.randint(0, 1000)
name = str(name)
name = os.path.join(os.getcwd(), str(name))
print("ALl logs saved in dir:", name)
os.mkdir(name)
#video_info = VideoInfo.from_video_path("cocnrec.mp4")
# create frame generator
#generator = get_video_frames_generator("cocnrec.mp4")
# create LineCounter instance
line_counter = LineCounter(start=LINE_START, end=LINE_END)
# create instance of BoxAnnotator and LineCounterAnnotator
box_annotator = BoxAnnotator(color=ColorPalette(), thickness=4, text_thickness=4, text_scale=2)
line_annotator = LineCounterAnnotator(thickness=4, text_thickness=4, text_scale=2)
#cap = cv2.VideoCapture("cocnrec.mp4")
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)
ret = cap.set(3, 864)
ret = cap.set(4, 480)
cur_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
#fps_MS = int(fps * 1000)
start = time.time()
video_file_count = 1
video_file = os.path.join(name, str(video_file_count) + ".avi")
print("Capture video saved location : {}".format(video_file))
video_writer = cv2.VideoWriter(
video_file, video_codec, fps, (int(cap.get(3)), int(cap.get(4)))
)
# open target video file
#with VideoSink("test.mp4", video_info) as sink:
# loop over video frames
#for frame in tqdm(generator, total=video_info.total_frames):
while cap.isOpened():
start_time = time.time()
ret, frame = cap.read()
if ret == True:
# model prediction on single frame and conversion to supervision Detections
results = model(frame)
detections = Detections(
xyxy=results[0].boxes.xyxy.cpu().numpy(),
confidence=results[0].boxes.conf.cpu().numpy(),
class_id=results[0].boxes.cls.cpu().numpy().astype(int)
)
# filtering out detections with unwanted classes
mask = np.array([class_id in CLASS_ID for class_id in detections.class_id], dtype=bool)
detections.filter(mask=mask, inplace=True)
# tracking detections
tracks = byte_tracker.update(
output_results=detections2boxes(detections=detections),
img_info=frame.shape,
img_size=frame.shape
)
tracker_id = match_detections_with_tracks(detections=detections, tracks=tracks)
detections.tracker_id = np.array(tracker_id)
# filtering out detections without trackers
mask = np.array([tracker_id is not None for tracker_id in detections.tracker_id], dtype=bool)
detections.filter(mask=mask, inplace=True)
# format custom labels
labels = [
f"#{tracker_id} {CLASS_NAMES_DICT[class_id]} {confidence:0.2f}"
for _, confidence, class_id, tracker_id
in detections
]
# updating line counter
line_counter.update(detections=detections)
# annotate and display frame
frame = box_annotator.annotate(frame=frame, detections=detections, labels=labels)
line_annotator.annotate(frame=frame, line_counter=line_counter)
cv2.imshow("frame", frame)
if time.time() - start > 1000:
start = time.time()
video_file_count += 1
video_file = os.path.join(name, str(video_file_count) + ".avi")
video_writer = cv2.VideoWriter(
video_file, video_codec, fps, (int(cap.get(3)), int(cap.get(4)))
)
# No sleeping! We don't want to sleep, we want to write
# time.sleep(10)
# Write the frame to the current video writer
video_writer.write(frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
else:
break
cap.release()
cv2.destroyAllWindows()
#sink.write_frame(frame
我想获得正确的处理结果并减少或删除丢失的帧。并得到正确的计数和记录。