def get_video_annotation():
setup_tensorflow()
output_dir = mkdtemp()
png_output = join(output_dir, "png")
oflow_output = join(output_dir, "oflow")
de = DataExtraction(FrameInput(
input_path="test-data/video-clip.mp4", bsize=256
))
freq = 128
de.run_annotators([
ColorHistogramAnnotator(freq=freq),
DominantColorAnnotator(freq=freq),
DiffAnnotator(quantiles=[40]),
EmbedAnnotator(embedding=EmbedFrameKerasResNet50(), freq=freq),
FaceAnnotator(
detector=FaceDetectMtcnn(),
embedding=FaceEmbedVgg2(),
freq=freq
),
HOFMAnnotator(freq=freq),
ObjectAnnotator(detector=ObjectDetectRetinaNet(), freq=freq),
OpticalFlowAnnotator(output_dir=oflow_output, freq=freq),
PngAnnotator(output_dir=png_output, freq=freq)
], max_batch=2)
return de, output_dir
def get_video_frame_annotation():
setup_tensorflow()
output_dir = mkdtemp()
png_output = join(output_dir, "png")
oflow_output = join(output_dir, "oflow")
de = DataExtraction(FrameInput(
input_path="test-data/video-clip.mp4", bsize=128
))
frames = [1, 3, 310] # make sure there is an empty batch: 128-255
de.run_annotators([
ColorHistogramAnnotator(frames=frames, colorspace="lab"),
DominantColorAnnotator(frames=frames),
DiffAnnotator(quantiles=[40]),
EmbedAnnotator(embedding=EmbedFrameKerasResNet50(), frames=frames),
FaceAnnotator(
detector=FaceDetectMtcnn(),
embedding=FaceEmbedVgg2(),
frames=frames
),
HOFMAnnotator(frames=frames),
ObjectAnnotator(detector=ObjectDetectRetinaNet(), frames=frames),
OpticalFlowAnnotator(output_dir=oflow_output, frames=frames),
PngAnnotator(output_dir=png_output, frames=frames),
ImgAnnotator()
])
return de, output_dir
def test_max_batch(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=8)
fpobj.process(finput, max_batch=3)
obj_diff = fpobj.collect("diff")
assert obj_diff.shape[0] == (3 * 8)
def test_process_full_output(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=128)
fpobj.process(finput)
obj_diff = fpobj.collect("diff")
assert obj_diff.shape[0] == (128 * 3)
def test_no_quantiles(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=8)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect("diff")
assert set(obj_out.keys()) == set(["video", "frame", "avg_value"])
assert issubclass(type(obj_out["avg_value"]), np.ndarray)
def test_collect_all(self):
fpobj = FrameProcessor()
fpobj.load_annotator(FrameAnnotator())
fpobj.load_annotator(DiffAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=8)
fpobj.process(finput, max_batch=2)
output = fpobj.collect_all()
assert output["base"] == DictFrame()
assert output["diff"].shape[0] == (2 * 8)
def test_cutoff_empty(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator(quantiles=[40]))
finput = FrameInput("test-data/video-clip.mp4", bsize=128)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect_all()
ca = CutAggregator()
agg = ca.aggregate(obj_out)
assert agg["frame_start"] == list(range(256))
def test_cutoff(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator(quantiles=[40]))
finput = FrameInput("test-data/video-clip.mp4", bsize=128)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect_all()
ca = CutAggregator(cut_vals={"h40": 0.2, "q40": 3})
agg = ca.aggregate(obj_out)
assert set(agg.keys()) == set(["video", "frame_start", "frame_end"])
def test_quantiles(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator(quantiles=[40, 50]))
finput = FrameInput("test-data/video-clip.mp4", bsize=8)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect("diff")
keys = list(obj_out.keys())
assert issubclass(type(obj_out["q40"]), np.ndarray)
assert issubclass(type(obj_out["q50"]), np.ndarray)
assert issubclass(type(obj_out["h40"]), np.ndarray)
assert issubclass(type(obj_out["h50"]), np.ndarray)
def test_cutoff_ignore(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator(quantiles=[40]))
finput = FrameInput("test-data/video-clip.mp4", bsize=128)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect_all()
ca = CutAggregator(
cut_vals={"h40": 0.2, "q40": 3}, ignore_vals={"avg_value": 70}
)
agg = ca.aggregate(obj_out)
assert agg == DictFrame()
def main(argv):
try:
opts, args = getopt.getopt(
argv, "hf:q:c:h:",
["file=", "quantiles=", "cutvals=", "histdiff="])
except getopt.GetoptError:
print(
'dvt_to_sat.py -f <filename> -q <quantiles> -c <cutvals> -h <histdiff>'
)
sys.exit(2)
filename = ''
quantiles = 40
cutvals = 3
histdiff = 0
for opt, arg in opts:
if opt == '-h':
print(
'dvt_to_sat.py -f <filename> -q <quantiles> -c <cutvals> -h <histdiff>'
)
sys.exit()
elif opt in ("-f", "--file"):
filename = arg
elif opt in ("-q", "--quantiles"):
quantiles = arg
elif opt in ("-c", "--cutvals"):
cutvals = arg
elif opt in ("-h", "--histdiff"):
cutvals = arg
if (filename == ''):
print('missing param: filename is required')
sys.exit(2)
basename = os.path.basename(filename)
logging.basicConfig(level='INFO')
finput = FrameInput(filename, bsize=128)
fpobj = FrameProcessor()
fpobj.load_annotator(MetaAnnotator())
fpobj.load_annotator(DiffAnnotator(quantiles=[quantiles]))
fpobj.process(finput)
#fpobj.process(finput, max_batch=5)
obj = fpobj.collect_all()
meta = obj['meta'].todf()
obj['diff'].todf().head()
cagg = CutAggregator(cut_vals={
'h40': histdiff,
'q' + str(quantiles): cutvals
})
fps = meta['fps'][0]
print(fps)
df1 = cagg.aggregate(obj).todf()
df1['seconds_start'] = df1['frame_start'] / fps
df1['seconds_end'] = df1['frame_end'] / fps
out = df1.to_csv()
f = open(basename + ".csv", "w")
f.write(out)
f.close()