YouTube Livestream Detection (#2752)

* Youtube livestream detection

* dependancy update to auto install pafy

* Remove print

* include youtube_dl in deps

* PEP8 reformat

* youtube url check fix

* reduce lines

* add comment

* update check_requirements

* stream framerate fix

* Update README.md

* cleanup

* PEP8

* remove cap.retrieve() failure code

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

README.md

@@ -92,9 +92,8 @@ $ python detect.py --source 0  # webcam
                             file.mp4  # video
                             path/  # directory
                             path/*.jpg  # glob
-                            rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
-                            rtmp://192.168.1.105/live/test  # rtmp stream
-                            http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream
+                            'https://youtu.be/NUsoVlDFqZg'  # YouTube video
+                            'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
 ```
 
 To run inference on example images in `data/images`:

detect.py

@@ -19,7 +19,7 @@ def detect(save_img=False):
     source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
     save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
     webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
-        ('rtsp://', 'rtmp://', 'http://'))
+        ('rtsp://', 'rtmp://', 'http://', 'https://'))
 
     # Directories
     save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run

utils/datasets.py

@@ -20,8 +20,8 @@
 from torch.utils.data import Dataset
 from tqdm import tqdm
 
-from utils.general import xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, segment2box, segments2boxes, resample_segments, \
-    clean_str
+from utils.general import check_requirements, xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, segment2box, segments2boxes, \
+    resample_segments, clean_str
 from utils.torch_utils import torch_distributed_zero_first
 
 # Parameters
@@ -275,14 +275,20 @@ def __init__(self, sources='streams.txt', img_size=640, stride=32):
         for i, s in enumerate(sources):
             # Start the thread to read frames from the video stream
             print(f'{i + 1}/{n}: {s}... ', end='')
-            cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s)
+            url = eval(s) if s.isnumeric() else s
+            if 'youtube.com/' in url or 'youtu.be/' in url:  # if source is YouTube video
+                check_requirements(('pafy', 'youtube_dl'))
+                import pafy
+                url = pafy.new(url).getbest(preftype="mp4").url
+            cap = cv2.VideoCapture(url)
             assert cap.isOpened(), f'Failed to open {s}'
             w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
             h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-            fps = cap.get(cv2.CAP_PROP_FPS) % 100
+            self.fps = cap.get(cv2.CAP_PROP_FPS) % 100
+
             _, self.imgs[i] = cap.read()  # guarantee first frame
             thread = Thread(target=self.update, args=([i, cap]), daemon=True)
-            print(f' success ({w}x{h} at {fps:.2f} FPS).')
+            print(f' success ({w}x{h} at {self.fps:.2f} FPS).')
             thread.start()
         print('')  # newline
 
@@ -303,7 +309,7 @@ def update(self, index, cap):
                 success, im = cap.retrieve()
                 self.imgs[index] = im if success else self.imgs[index] * 0
                 n = 0
-            time.sleep(0.01)  # wait time
+            time.sleep(1 / self.fps)  # wait time
 
     def __iter__(self):
         self.count = -1
@@ -444,7 +450,7 @@ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, r
                 gb += self.imgs[i].nbytes
                 pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB)'
             pbar.close()
-            
+
     def cache_labels(self, path=Path('./labels.cache'), prefix=''):
         # Cache dataset labels, check images and read shapes
         x = {}  # dict
@@ -489,7 +495,7 @@ def cache_labels(self, path=Path('./labels.cache'), prefix=''):
             pbar.desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels... " \
                         f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
         pbar.close()
-            
+
         if nf == 0:
             print(f'{prefix}WARNING: No labels found in {path}. See {help_url}')
 
@@ -1034,6 +1040,7 @@ def extract_boxes(path='../coco128/'):  # from utils.datasets import *; extract_
                     b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
                     assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
 
+
 def autosplit(path='../coco128', weights=(0.9, 0.1, 0.0), annotated_only=False):
     """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
     Usage: from utils.datasets import *; autosplit('../coco128')

utils/general.py

@@ -91,17 +91,20 @@ def check_git_status():
         print(e)
 
 
-def check_requirements(file='requirements.txt', exclude=()):
-    # Check installed dependencies meet requirements
+def check_requirements(requirements='requirements.txt', exclude=()):
+    # Check installed dependencies meet requirements (pass *.txt file or list of packages)
     import pkg_resources as pkg
     prefix = colorstr('red', 'bold', 'requirements:')
-    file = Path(file)
-    if not file.exists():
-        print(f"{prefix} {file.resolve()} not found, check failed.")
-        return
+    if isinstance(requirements, (str, Path)):  # requirements.txt file
+        file = Path(requirements)
+        if not file.exists():
+            print(f"{prefix} {file.resolve()} not found, check failed.")
+            return
+        requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
+    else:  # list or tuple of packages
+        requirements = [x for x in requirements if x not in exclude]
 
     n = 0  # number of packages updates
-    requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
     for r in requirements:
         try:
             pkg.require(r)
@@ -111,7 +114,8 @@ def check_requirements(file='requirements.txt', exclude=()):
             print(subprocess.check_output(f"pip install '{e.req}'", shell=True).decode())
 
     if n:  # if packages updated
-        s = f"{prefix} {n} package{'s' * (n > 1)} updated per {file.resolve()}\n" \
+        source = file.resolve() if 'file' in locals() else requirements
+        s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
             f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
         print(emojis(s))  # emoji-safe