Scene cut detection with 2 detectors, and a fresh 9:16 crop at every cut

curl -o stream.mp4 https://api.clipsdk.com/f/lib/demo/silicon-valley-live-stream.mp4
pip install "scenedetect==0.7.2" "opencv-python-headless==5.0.0.93"

import json
from scenedetect import detect, AdaptiveDetector

scenes = detect("stream.mp4", AdaptiveDetector())
cuts = [start.seconds for start, _ in scenes[1:]]
json.dump(cuts, open("adaptive.json", "w"))

print(len(cuts), "cuts")
print([round(t, 2) for t in cuts[:8]])

# $ python adaptive.py
# 61 cuts
# [15.07, 32.47, 38.33, 40.77, 45.67, 62.87, 69.23, 74.37]

ffmpeg -i stream.mp4 -an -vf "scale=640:-2:flags=area,scdet=threshold=8,metadata=mode=print:key=lavfi.scd.time:file=cuts.txt" -f null -
grep -c pts_time cuts.txt
grep -o 'pts_time:[0-9.]*' cuts.txt | head -8

# output:
# 61
# pts_time:15.066667
# pts_time:32.466667
# pts_time:38.333333
# pts_time:40.766667
# pts_time:45.666667
# pts_time:62.866667
# pts_time:69.233333
# pts_time:74.366667

import json
import re

adaptive = json.load(open("adaptive.json"))
scdet = [float(t) for t in re.findall(r"pts_time:([\d.]+)", open("cuts.txt").read())]
agree = [t for t in scdet if any(abs(t - a) < 0.5 for a in adaptive)]
print(len(adaptive), "adaptive cuts,", len(scdet), "scdet cuts,", len(agree), "found by both")

# Split one clip at every cut, and fold slivers under 0.5 s into the shot before
CLIP_START, CLIP_END, MIN_SHOT_S = 35.95, 91.56, 0.5
edges = [CLIP_START]
for t in scdet:
    if CLIP_START + MIN_SHOT_S <= t <= CLIP_END - MIN_SHOT_S and t - edges[-1] >= MIN_SHOT_S:
        edges.append(t)
edges.append(CLIP_END)

shots = list(zip(edges, edges[1:]))
print(len(shots), "shots")
for start, end in shots:
    print(f"{start:6.2f} {end:6.2f}")

# $ python shots.py
# 61 adaptive cuts, 61 scdet cuts, 61 found by both
# 9 shots
#  35.95  38.33
#  38.33  40.77
#  40.77  45.67
#  45.67  62.87
#  62.87  69.23
#  69.23  74.37
#  74.37  85.10
#  85.10  88.43
#  88.43  91.56