[detectors] Implement Koala-36M

Add `KoalaDetector` and `detect-koala` command. #441

Author: Breakthrough

dist/requirements_windows.txt

@@ -2,6 +2,7 @@
 av==13.1.0
 click>=8.0
 opencv-python-headless==4.10.0.84
+scikit-image==0.24.0
 
 imageio-ffmpeg
 moviepy

requirements.txt

@@ -8,3 +8,4 @@ opencv-python
 platformdirs
 pytest>=7.0
 tqdm
+scikit-image

requirements_headless.txt

@@ -7,4 +7,5 @@ numpy
 opencv-python-headless
 platformdirs
 pytest>=7.0
-tqdm
+scikit-image
+tqdm

scenedetect/_cli/__init__.py

@@ -42,6 +42,7 @@
     ContentDetector,
     HashDetector,
     HistogramDetector,
+    KoalaDetector,
     ThresholdDetector,
 )
 from scenedetect.platform import get_cv2_imwrite_params, get_system_version_info
@@ -1577,3 +1578,16 @@ def save_qp_command(
 scenedetect.add_command(list_scenes_command)
 scenedetect.add_command(save_images_command)
 scenedetect.add_command(split_video_command)
+
+
+@click.command("detect-koala", cls=Command, help="""WIP""")
+@click.pass_context
+def detect_koala_command(
+    ctx: click.Context,
+):
+    ctx = ctx.obj
+    assert isinstance(ctx, CliContext)
+    ctx.add_detector(KoalaDetector, {"min_scene_len": None})
+
+
+scenedetect.add_command(detect_koala_command)

scenedetect/detectors/__init__.py

@@ -40,6 +40,7 @@
 from scenedetect.detectors.adaptive_detector import AdaptiveDetector
 from scenedetect.detectors.hash_detector import HashDetector
 from scenedetect.detectors.histogram_detector import HistogramDetector
+from scenedetect.detectors.koala_detector import KoalaDetector
 
 # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
 #                                                                             #

scenedetect/detectors/koala_detector.py

@@ -0,0 +1,87 @@
+#
+#            PySceneDetect: Python-Based Video Scene Detector
+#   -------------------------------------------------------------------
+#     [  Site:    https://scenedetect.com                           ]
+#     [  Docs:    https://scenedetect.com/docs/                     ]
+#     [  Github:  https://github.com/Breakthrough/PySceneDetect/    ]
+#
+# Copyright (C) 2014-2024 Brandon Castellano <http://www.bcastell.com>.
+# PySceneDetect is licensed under the BSD 3-Clause License; see the
+# included LICENSE file, or visit one of the above pages for details.
+#
+""":class:`KoalaDetector` uses the detection method described by Koala-36M.
+See https://koala36m.github.io/ for details.
+
+TODO: Cite correctly.
+
+This detector is available from the command-line as the `detect-koala` command.
+"""
+
+import typing as ty
+
+import cv2
+import numpy as np
+from skimage.metrics import structural_similarity
+
+from scenedetect.scene_detector import SceneDetector
+
+
+class KoalaDetector(SceneDetector):
+    def __init__(self, min_scene_len: int = None):
+        self._start_frame_num: int = None
+        self._min_scene_len: int = min_scene_len if min_scene_len else 0
+        self._last_histogram: np.ndarray = None
+        self._last_edges: np.ndarray = None
+        self._scores: ty.List[ty.List[int]] = []
+
+    def process_frame(self, frame_num: int, frame_img: np.ndarray) -> ty.List[int]:
+        # TODO: frame_img is already downscaled here. The same problem exists in HashDetector.
+        # For now we can just set downscale factor to 1 in SceneManager to work around the issue.
+        frame_img = cv2.resize(frame_img, (256, 256))
+        histogram = np.asarray(
+            [cv2.calcHist([c], [0], None, [254], [1, 255]) for c in cv2.split(frame_img)]
+        )
+        frame_gray = cv2.resize(cv2.cvtColor(frame_img, cv2.COLOR_BGR2GRAY), (128, 128))
+        edges = np.maximum(frame_gray, cv2.Canny(frame_gray, 100, 200))
+        if self._start_frame_num is not None:
+            delta_histogram = cv2.compareHist(self._last_histogram, histogram, cv2.HISTCMP_CORREL)
+            delta_edges = structural_similarity(self._last_edges, edges, data_range=255)
+            score = 4.61480465 * delta_histogram + 3.75211168 * delta_edges - 5.485968377115124
+            self._scores.append(score)
+        if self._start_frame_num is None:
+            self._start_frame_num = frame_num
+        self._last_histogram = histogram
+        self._last_edges = edges
+        return []
+
+    def post_process(self, frame_num: int) -> ty.List[int]:
+        self._scores = np.asarray(self._scores)
+        num_frames = len(self._scores)
+        convolution = self._scores.copy()
+        convolution[1:-1] = np.convolve(convolution, np.array([1, 1, 1]) / 3.0, mode="valid")
+        cut_found = np.zeros(num_frames + 1, bool)
+        cut_found[-1] = True
+
+        WINDOW_SIZE = 8
+        for frame_num in range(num_frames):
+            if self._scores[frame_num] < 0:
+                cut_found[frame_num] = True
+            elif frame_num >= 8:
+                last_cut = max(frame_num - WINDOW_SIZE, 0)
+                if convolution[frame_num] < 0.75:
+                    M = len(convolution[last_cut:frame_num])
+                    arr = np.sort(convolution[last_cut:frame_num])
+                    arr = arr[int(M * 0.2) : int(M * 0.8)]
+                    mu = arr.mean()
+                    std = arr.std()
+                    if convolution[frame_num] < mu - 3 * max(0.2, std):
+                        cut_found[frame_num] = True
+
+        cuts = []
+        last_cut = 0
+        for frame_num in range(len(cut_found)):
+            if cut_found[frame_num]:
+                if (frame_num - last_cut) > WINDOW_SIZE:
+                    cuts.append(last_cut)
+                last_cut = frame_num + 1
+        return [cut + self._start_frame_num for cut in cuts][1:]

tests/test_detectors.py

@@ -29,6 +29,7 @@
     ContentDetector,
     HashDetector,
     HistogramDetector,
+    KoalaDetector,
     ThresholdDetector,
 )
 
@@ -37,6 +38,7 @@
     ContentDetector,
     HashDetector,
     HistogramDetector,
+    KoalaDetector,
 )
 
 ALL_DETECTORS: ty.Tuple[ty.Type[SceneDetector]] = (*FAST_CUT_DETECTORS, ThresholdDetector)
@@ -123,7 +125,9 @@ def get_fast_cut_test_cases():
             ),
             id="%s/m=30" % detector_type.__name__,
         )
+        # TODO: Make this work, right now min_scene_len isn't used by the detector.
         for detector_type in FAST_CUT_DETECTORS
+        if detector_type != KoalaDetector
     ]
     return test_cases