-
Notifications
You must be signed in to change notification settings - Fork 1
/
deepstream_face_anonymizer_yolo.py
403 lines (336 loc) · 15.5 KB
/
deepstream_face_anonymizer_yolo.py
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
#!/usr/bin/env python3
################################################################################
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
################################################################################
""" Example of deepstream face annonymizer using YOLO V3 neural network. """
import sys
import io
sys.path.append("../")
import gi
gi.require_version("Gst", "1.0")
from gi.repository import GObject, Gst
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
from ssd_parser import nvds_infer_parse_custom_tf_ssd, DetectionParam, NmsParam, BoxSizeParam
import pyds
from common.FPS import GETFPS
import argparse
import os
from functools import partial
fps_streams={}
CLASS_NB = 91
UNTRACKED_OBJECT_ID = 0xffffffffffffffff
IMAGE_HEIGHT = 1080
IMAGE_WIDTH = 1920
def get_label_names_from_file(filepath):
""" Read a label file and convert it to string list """
f = io.open(filepath, "r")
labels = f.readlines()
labels = [elm[:-1] for elm in labels]
f.close()
return labels
def make_elm_or_print_err(factoryname, name, printedname, detail=""):
""" Creates an element with Gst Element Factory make.
Return the element if successfully created, otherwise print
to stderr and return None.
"""
print("Creating", printedname)
elm = Gst.ElementFactory.make(factoryname, name)
if not elm:
sys.stderr.write("Unable to create " + printedname + " \n")
if detail:
sys.stderr.write(detail)
return elm
def osd_sink_pad_buffer_probe(pad, info, u_datat, label_path):
frame_number = 0
# Intiallizing object counter with 0.
obj_counter = dict(enumerate([0] * CLASS_NB))
num_rects = 0
gst_buffer = info.get_buffer()
if not gst_buffer:
print("Unable to get GstBuffer ")
return
# Retrieve batch metadata from the gst_buffer
# Note that pyds.gst_buffer_get_nvds_batch_meta() expects the
# C address of gst_buffer as input, which is obtained with hash(gst_buffer)
batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
l_frame = batch_meta.frame_meta_list
while l_frame is not None:
try:
# Note that l_frame.data needs a cast to pyds.NvDsFrameMeta
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone.
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
except StopIteration:
break
frame_number = frame_meta.frame_num
num_rects = frame_meta.num_obj_meta
l_obj = frame_meta.obj_meta_list
while l_obj is not None:
try:
# Casting l_obj.data to pyds.NvDsObjectMeta
obj_meta = pyds.NvDsObjectMeta.cast(l_obj.data)
except StopIteration:
break
obj_counter[obj_meta.class_id] += 1
rect_params = obj_meta.rect_params
text_params = obj_meta.text_params
text_params.display_text = ""
width = int(rect_params.width / 1.5)
height = int(rect_params.height / 4)
left = rect_params.left
top = rect_params.top
rect_params.left += int(width / 2)
rect_params.top -= int(height / 3)
rect_params.width = width
rect_params.height = height
rect_params.has_bg_color = 1
rect_params.bg_color.set(0, 0, 0, 0.85)
# Red border of width 3
rect_params.border_width = 3
rect_params.border_color.set(.6, .6, .6, 1)
try:
l_obj = l_obj.next
except StopIteration:
break
# Acquiring a display meta object. The memory ownership remains in
# the C code so downstream plugins can still access it. Otherwise
# the garbage collector will claim it when this probe function exits.
display_meta = pyds.nvds_acquire_display_meta_from_pool(batch_meta)
display_meta.num_labels = 1
py_nvosd_text_params = display_meta.text_params[0]
# Setting display text to be shown on screen
# Note that the pyds module allocates a buffer for the string, and the
# memory will not be claimed by the garbage collector.
# Reading the display_text field here will return the C address of the
# allocated string. Use pyds.get_string() to get the string content.
id_dict = {
val: index
for index, val in enumerate(get_label_names_from_file(label_path))
}
disp_string = "Frame Number={} FPS={} Person_count={}"
py_nvosd_text_params.display_text = disp_string.format(
frame_number,
fps_streams["stream{0}".format(frame_meta.pad_index)].get_fps(),
obj_counter[id_dict["person"]]
)
# Now set the offsets where the string should appear
py_nvosd_text_params.x_offset = 10
py_nvosd_text_params.y_offset = 12
# Font , font-color and font-size
py_nvosd_text_params.font_params.font_name = "Serif"
py_nvosd_text_params.font_params.font_size = 10
# set(red, green, blue, alpha); set to White
py_nvosd_text_params.font_params.font_color.set(1.0, 1.0, 1.0, 1.0)
# Text background color
py_nvosd_text_params.set_bg_clr = 1
# set(red, green, blue, alpha); set to Black
py_nvosd_text_params.text_bg_clr.set(0.0, 0.0, 0.0, 1.0)
# Using pyds.get_string() to get display_text as string
print(pyds.get_string(py_nvosd_text_params.display_text))
pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
fps_streams["stream{0}".format(frame_meta.pad_index)].get_fps()
try:
l_frame = l_frame.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def cb_newpad(decodebin, decoder_src_pad, data):
print("In cb_newpad\n")
caps = decoder_src_pad.get_current_caps()
gststruct = caps.get_structure(0)
gstname = gststruct.get_name()
source_bin = data
features = caps.get_features(0)
# Need to check if the pad created by the decodebin is for video and not
# audio.
print("gstname=", gstname)
if gstname.find("video") != -1:
# Link the decodebin pad only if decodebin has picked nvidia
# decoder plugin nvdec_*. We do this by checking if the pad caps contain
# NVMM memory features.
print("features=", features)
if features.contains("memory:NVMM"):
# Get the source bin ghost pad
bin_ghost_pad = source_bin.get_static_pad("src")
if not bin_ghost_pad.set_target(decoder_src_pad):
sys.stderr.write("Failed to link decoder src pad to source bin ghost pad\n")
else:
sys.stderr.write(" Error: Decodebin did not pick nvidia decoder plugin.\n")
def decodebin_child_added(child_proxy, Object, name, user_data):
print("Decodebin child added:", name, "\n")
if name.find("decodebin") != -1:
Object.connect("child-added", decodebin_child_added, user_data)
def create_source_bin(index, uri):
print("Creating source bin")
# Create a source GstBin to abstract this bin's content from the rest of the
# pipeline
bin_name = "source-bin-%02d" % index
print(bin_name)
nbin = Gst.Bin.new(bin_name)
if not nbin:
sys.stderr.write(" Unable to create source bin \n")
# Source element for reading from the uri.
# We will use decodebin and let it figure out the container format of the
# stream and the codec and plug the appropriate demux and decode plugins.
uri_decode_bin = Gst.ElementFactory.make("uridecodebin", "uri-decode-bin")
if not uri_decode_bin:
sys.stderr.write(" Unable to create uri decode bin \n")
# We set the input uri to the source element
uri_decode_bin.set_property("uri", uri)
# Connect to the "pad-added" signal of the decodebin which generates a
# callback once a new pad for raw data has beed created by the decodebin
uri_decode_bin.connect("pad-added", cb_newpad, nbin)
uri_decode_bin.connect("child-added", decodebin_child_added, nbin)
# We need to create a ghost pad for the source bin which will act as a proxy
# for the video decoder src pad. The ghost pad will not have a target right
# now. Once the decode bin creates the video decoder and generates the
# cb_newpad callback, we will set the ghost pad target to the video decoder
# src pad.
Gst.Bin.add(nbin, uri_decode_bin)
bin_pad = nbin.add_pad(Gst.GhostPad.new_no_target("src", Gst.PadDirection.SRC))
if not bin_pad:
sys.stderr.write(" Failed to add ghost pad in source bin \n")
return None
return nbin
def main():
# Check input arguments
parser = argparse.ArgumentParser(description="Deepstream inference application")
parser.add_argument("--input_video", type=str, required=True, help="Input video path")
parser.add_argument("--out_dir", type=str, required=True, help="Directory to store result")
parser.add_argument("--config", type=str, required=True, help="Deepstream Config file")
parser.add_argument("--label_path", type=str, required=True, help="Label file Path")
args = parser.parse_args()
fps_streams["stream{0}".format(0)]=GETFPS(0)
# Standard GStreamer initialization
GObject.threads_init()
Gst.init(None)
# Create gstreamer elements
# Create Pipeline element that will form a connection of other elements
print("Creating Pipeline \n ")
pipeline = Gst.Pipeline()
if not pipeline:
sys.stderr.write(" Unable to create Pipeline \n")
# Source element for reading from the file
source = create_source_bin(0, "file:https://" + os.path.abspath(args.input_video))
# Since the data format in the input file is elementary h264 stream,
# we need a h264parser
# Create nvstreammux instance to form batches from one or more sources.
streammux = make_elm_or_print_err("nvstreammux", "Stream-muxer", "NvStreamMux")
pipeline.add(source)
# Use nvinferserver to run inferencing on decoder's output,
# behaviour of inferencing is set through config file
pgie = make_elm_or_print_err("nvinfer", "primary-inference", "Nvinferserver")
# Use convertor to convert from NV12 to RGBA as required by nvosd
nvvidconv = make_elm_or_print_err("nvvideoconvert", "convertor", "Nvvidconv")
# Create OSD to draw on the converted RGBA buffer
nvosd = make_elm_or_print_err("nvdsosd", "onscreendisplay", "OSD (nvosd)")
# Finally encode and save the osd output
queue = make_elm_or_print_err("queue", "queue", "Queue")
nvvidconv2 = make_elm_or_print_err("nvvideoconvert", "convertor2", "Converter 2 (nvvidconv2)")
capsfilter = make_elm_or_print_err("capsfilter", "capsfilter", "capsfilter")
caps = Gst.Caps.from_string("video/x-raw, format=I420")
capsfilter.set_property("caps", caps)
# On Jetson, there is a problem with the encoder failing to initialize
# due to limitation on TLS usage. To work around this, preload libgomp.
# Add a reminder here in case the user forgets.
preload_reminder = "If the following error is encountered:\n" + \
"/usr/lib/aarch64-linux-gnu/libgomp.so.1: cannot allocate memory in static TLS block\n" + \
"Preload the offending library:\n" + \
"export LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libgomp.so.1\n"
encoder = make_elm_or_print_err("avenc_mpeg4", "encoder", "Encoder", preload_reminder)
encoder.set_property("bitrate", 2000000)
codeparser = make_elm_or_print_err("mpeg4videoparse", "mpeg4-parser", 'Code Parser')
container = make_elm_or_print_err("qtmux", "qtmux", "Container")
sink = make_elm_or_print_err("filesink", "filesink", "Sink")
video_base_path = os.path.basename(args.input_video)
output_video_path = args.out_dir + "/neuralet_deepstream_" + video_base_path
if not os.path.exists(args.out_dir):
os.makedirs(args.out_dir)
sink.set_property("location", output_video_path)
sink.set_property("sync", 0)
sink.set_property("async", 0)
print("Playing file %s " % args.input_video)
streammux.set_property("width", IMAGE_WIDTH)
streammux.set_property("height", IMAGE_HEIGHT)
streammux.set_property("batch-size", 1)
streammux.set_property("batched-push-timeout", 4000000)
pgie.set_property("config-file-path", args.config)
nvosd.set_property("display-text", False)
print("Adding elements to Pipeline \n")
pipeline.add(streammux)
pipeline.add(pgie)
pipeline.add(nvvidconv)
pipeline.add(nvosd)
pipeline.add(queue)
pipeline.add(nvvidconv2)
pipeline.add(capsfilter)
pipeline.add(encoder)
pipeline.add(codeparser)
pipeline.add(container)
pipeline.add(sink)
# we link the elements together
# file-source -> h264-parser -> nvh264-decoder ->
# nvinfer -> nvvidconv -> nvosd -> video-renderer
print("Linking elements in the Pipeline \n")
padname = "sink_0"
sinkpad = streammux.get_request_pad(padname)
if not sinkpad:
sys.stderr.write("Unable to create sink pad bin \n")
srcpad = source.get_static_pad("src")
if not srcpad:
sys.stderr.write("Unable to create src pad bin \n")
srcpad.link(sinkpad)
streammux.link(pgie)
pgie.link(nvvidconv)
nvvidconv.link(nvosd)
nvosd.link(queue)
queue.link(nvvidconv2)
nvvidconv2.link(capsfilter)
capsfilter.link(encoder)
encoder.link(codeparser)
codeparser.link(container)
container.link(sink)
# create an event loop and feed gstreamer bus mesages to it
loop = GObject.MainLoop()
bus = pipeline.get_bus()
bus.add_signal_watch()
bus.connect("message", bus_call, loop)
# Lets add probe to get informed of the meta data generated, we add probe to
# the sink pad of the osd element, since by that time, the buffer would have
# had got all the metadata.
osdsinkpad = nvosd.get_static_pad("sink")
if not osdsinkpad:
sys.stderr.write(" Unable to get sink pad of nvosd \n")
osd_sink_pad_buffer_probe_label = partial(osd_sink_pad_buffer_probe, label_path = args.label_path)
osdsinkpad.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe_label, 0)
# start play back and listen to events
print("Starting pipeline \n")
pipeline.set_state(Gst.State.PLAYING)
try:
loop.run()
except:
pass
# cleanup
pipeline.set_state(Gst.State.NULL)
if __name__ == "__main__":
sys.exit(main())