Spaces:
Sleeping
Sleeping
File size: 3,171 Bytes
b44c3e2 60dc102 0faef99 139dd3e 160ded7 0faef99 5b889a9 24c941c 049f239 5b889a9 139dd3e 5b889a9 049f239 c23be95 139dd3e 5b889a9 139dd3e 24c941c 139dd3e 24c941c b44c3e2 160ded7 b0bdee4 049f239 24c941c 049f239 b0bdee4 24c941c 5b889a9 b0bdee4 24c941c b0bdee4 5b889a9 049f239 60dc102 dd478fa 60dc102 160ded7 b0bdee4 139dd3e 24c941c 160ded7 24c941c 139dd3e 92ddd3a 4f30d97 160ded7 92ddd3a 139dd3e 160ded7 139dd3e 92ddd3a 160ded7 0faef99 |
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 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import tempfile
import cv2
import gradio as gr
import tensorflow as tf
from moviepy.editor import VideoFileClip
from moviepy.video.io.ImageSequenceClip import ImageSequenceClip
from configuration import Config
from model import load_classifier, load_detector
from inference import format_frame, detect_object, classify_action, draw_boxes, draw_classes
config = Config()
print(f'TensorFlow {tf.__version__}')
print(f'Load classifier from {config.classifier_path}')
classifier = load_classifier(config)
classifier.trainable = False
classifier.summary()
print('Load detector.')
detector = load_detector(config)
def fn(video: gr.Video, actions: list[int]):
print('Process video.')
do_detect = 0 in actions
do_classify = 1 in actions
if not do_detect and not do_classify:
return video
with tempfile.NamedTemporaryFile(delete=False, suffix='.mp4') as f:
output = f.name
clip = VideoFileClip(video)
processed_frames = []
frames = []
actions = []
detections = ([], [])
for i, frame in enumerate(clip.iter_frames()):
if i % config.classify_action_frame_step == 0:
if do_classify:
frames.append(format_frame(frame, config))
if i % config.detect_object_frame_step == 0:
print(f'Detect object: Frame {i}')
if do_detect:
detections = detect_object(detector, frame)
if len(frames) == config.classify_action_num_frames:
print(f'Classify action: Until frame {i}')
if do_classify:
actions = classify_action(classifier, frames, config.id_to_name)
frames = []
if do_detect:
frame = draw_boxes(frame, detections, actions, do_classify)
else:
frame = draw_classes(frame, actions)
processed_frames.append(frame)
if i % config.yield_frame_steps == 0:
quality = 9
image_array = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
_, image_encoded = cv2.imencode('.jpg', image_array, [int(cv2.IMWRITE_JPEG_QUALITY), quality])
with tempfile.NamedTemporaryFile(suffix='.jpeg') as f:
f.write(image_encoded)
yield f.name, None
processed_clip = ImageSequenceClip(processed_frames, clip.fps)
processed_clip.audio = clip.audio
processed_clip.write_videofile(output, fps=clip.fps, audio_codec='aac', logger=None)
yield frame, output
inputs = [
gr.Video(sources=['upload'], label='输入视频片段'),
gr.CheckboxGroup(
['飞机检测', '飞机行为识别'],
label='执行任务',
info='可以选择仅执行飞机检测任务或仅执行飞机行为识别任务作为演示。',
type='index')]
outputs = [
gr.Image(interactive=False, label='最新处理的视频帧'),
gr.Video(interactive=False, label='标记飞机位置及行为的视频片段')]
examples = [
['examples/ZFLFDfovqls_001310_001320.mp4'], # cspell: disable-line
['examples/Zv7GyH-fpEY_2023.0_2033.0.mp4']]
iface = gr.Interface(
title='Aeroplane Position and Action Detection',
description='Detect aeroplane position and action in a video.',
theme='soft',
fn=fn,
inputs=inputs,
outputs=outputs,
examples=examples,
cache_examples=False)
iface.launch()
|