• Hardware Platform (Jetson / GPU)
Jetson Xavier NX
• DeepStream Version
DeepStream 6.0
• JetPack Version (valid for Jetson only)
4.6.1-b110
• TensorRT Version
8.2.1.8
Hi, I am trying to implement people counter by combining centroid tracker to deepstream with python binding (based on deepstream_test_1_usb.py).
However, it is likely every frame starts from the beginning of the function osd_sink_pad_buffer_probe and variables of the previous frame are not passed. I am glad if you can tell how to pass the variables to next frame. Here is the code(I am modifying osd_sink_pad_buffer_probe function):
#!/usr/bin/env python3
################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2020-2021 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################
import sys
from tkinter import W
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
import pyds
import cv2, dlib
import numpy as np
from mylib.centroidtracker import CentroidTracker
from mylib.trackableobject import TrackableObject
PGIE_CLASS_ID_VEHICLE = 0
PGIE_CLASS_ID_BICYCLE = 1
PGIE_CLASS_ID_PERSON = 2
PGIE_CLASS_ID_FACE = 3
def osd_sink_pad_buffer_probe(pad,info,u_data):
####################
# counter preparation
####################
# instantiate our centroid tracker, then initialize a list to store
# each of our dlib correlation trackers, followed by a dictionary to
# map each unique object ID to a TrackableObject
ct = CentroidTracker(maxDisappeared=40, maxDistance=20)
trackers = []
trackableObjects = {}
rects = []
# initialize the total number of frames processed thus far, along
# with the total number of objects that have moved either up or down
totalDown = 0
totalUp = 0
x = []
empty=[]
empty1=[]
check = False
frame_number=0
#Intiallizing object counter with 0.
obj_counter = {
PGIE_CLASS_ID_VEHICLE:0,
PGIE_CLASS_ID_PERSON:0,
PGIE_CLASS_ID_BICYCLE:0,
PGIE_CLASS_ID_FACE:0
}
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 is done by pyds.NvDsFrameMeta.cast()
# 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
print(check)
if check == True:
print(to)
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
################################
# counting and face recognizing
################################
obj_ucid = obj_meta.unique_component_id
obj_id = obj_meta.class_id
obj_label = obj_meta.obj_label
confidence = obj_meta.confidence
x_left = int(obj_meta.rect_params.left)
x_right = int(obj_meta.rect_params.left + obj_meta.rect_params.width)
y_top = int(obj_meta.rect_params.top)
y_bottom = int(obj_meta.rect_params.top + obj_meta.rect_params.height)
coordinates = (y_top, x_right, y_bottom, x_left)
if obj_label == "Person":
rects.append(coordinates)
obj_counter[obj_meta.class_id] += 1
try:
l_obj=l_obj.next
except StopIteration:
break
# initialize the frame dimensions (we'll set them as soon as we read
# the first frame from the video)
display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
l_frame = batch_meta.frame_meta_list
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
W = frame_meta.source_frame_width
H = frame_meta.source_frame_height
# use the centroid tracker to associate the (1) old object
# centroids with (2) the newly computed object centroids
objects = ct.update(rects)
print("rects", rects)
print("objects", objects)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
print("objectID", objectID, "cntroid", centroid)
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
print("to0", to) #Why none?
if to is None:
to = TrackableObject(objectID, centroid)
print("to1", to)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
print("to.continued", to.counted)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
empty.append(totalUp)
to.counted = True
print("totalUp", totalUp)
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
elif direction > 0 and centroid[1] > H // 2:
totalDown += 1
print("totalDown", totalDown)
empty1.append(totalDown)
to.counted = True
x = []
# compute the sum of total people inside
x.append(len(empty1)-len(empty))
print("Total people inside:", x)
# store the trackable object in our dictionary
print("trackableObjectID", objectID)
print(trackableObjects)
trackableObjects[objectID] = to
print("to2", to)
print("\n")
# # draw both the ID of the object and the centroid of the
# # object on the output frame
# 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.num_circles = 1
py_nvosd_circle_params = display_meta.circle_params[display_meta.num_circles-1]
py_nvosd_circle_params.xc = centroid[1]
py_nvosd_circle_params.yc = centroid[0]
py_nvosd_circle_params.radius = 10
py_nvosd_circle_params.bg_color.set(1.0, 0.0, 0.0, 1.0)
py_nvosd_circle_params.circle_color.set(1.0, 1.0, 1.0, 1.0)
display_meta.num_labels = 1
py_nvosd_text_params = display_meta.text_params[0]
py_nvosd_text_params.display_text = "ID {}".format(objectID)
py_nvosd_text_params.x_offset = centroid[1]
py_nvosd_text_params.y_offset = centroid[0]
# Font , font-color and font-size
py_nvosd_text_params.font_params.font_name = "Serif"
py_nvosd_text_params.font_params.font_size = 30
# 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)
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
display_meta.num_lines = 1
py_nvosd_line_params = display_meta.line_params[0]
py_nvosd_line_params.line_width = 4
py_nvosd_line_params.line_color.set(0.0, 1.0, 0.0, 1.0)
py_nvosd_line_params.x1 = 0
py_nvosd_line_params.y1 = H // 2
py_nvosd_line_params.x2 = W
py_nvosd_line_params.y2 = H // 2
check = True
pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
try:
l_frame=l_frame.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def main(args):
# Check input arguments
if len(args) != 2:
sys.stderr.write("usage: %s <v4l2-device-path>\n" % args[0])
sys.exit(1)
# 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
print("Creating Source \n ")
source = Gst.ElementFactory.make("v4l2src", "usb-cam-source")
if not source:
sys.stderr.write(" Unable to create Source \n")
caps_v4l2src = Gst.ElementFactory.make("capsfilter", "v4l2src_caps")
if not caps_v4l2src:
sys.stderr.write(" Unable to create v4l2src capsfilter \n")
print("Creating Video Converter \n")
# Adding videoconvert -> nvvideoconvert as not all
# raw formats are supported by nvvideoconvert;
# Say YUYV is unsupported - which is the common
# raw format for many logi usb cams
# In case we have a camera with raw format supported in
# nvvideoconvert, GStreamer plugins' capability negotiation
# shall be intelligent enough to reduce compute by
# videoconvert doing passthrough (TODO we need to confirm this)
# videoconvert to make sure a superset of raw formats are supported
vidconvsrc = Gst.ElementFactory.make("videoconvert", "convertor_src1")
if not vidconvsrc:
sys.stderr.write(" Unable to create videoconvert \n")
# nvvideoconvert to convert incoming raw buffers to NVMM Mem (NvBufSurface API)
nvvidconvsrc = Gst.ElementFactory.make("nvvideoconvert", "convertor_src2")
if not nvvidconvsrc:
sys.stderr.write(" Unable to create Nvvideoconvert \n")
caps_vidconvsrc = Gst.ElementFactory.make("capsfilter", "nvmm_caps")
if not caps_vidconvsrc:
sys.stderr.write(" Unable to create capsfilter \n")
# Create nvstreammux instance to form batches from one or more sources.
streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
if not streammux:
sys.stderr.write(" Unable to create NvStreamMux \n")
# Use nvinfer to run inferencing on camera's output,
# behaviour of inferencing is set through config file
pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
if not pgie:
sys.stderr.write(" Unable to create pgie \n")
# Use convertor to convert from NV12 to RGBA as required by nvosd
nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
if not nvvidconv:
sys.stderr.write(" Unable to create nvvidconv \n")
# Create OSD to draw on the converted RGBA buffer
nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
if not nvosd:
sys.stderr.write(" Unable to create nvosd \n")
# Finally render the osd output
if is_aarch64():
transform = Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
print("Creating EGLSink \n")
sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
if not sink:
sys.stderr.write(" Unable to create egl sink \n")
print("Playing cam %s " %args[1])
caps_v4l2src.set_property('caps', Gst.Caps.from_string("video/x-raw, framerate=30/1"))
caps_vidconvsrc.set_property('caps', Gst.Caps.from_string("video/x-raw(memory:NVMM)"))
source.set_property('device', args[1])
streammux.set_property('width', 640)
streammux.set_property('height', 480)
streammux.set_property('batch-size', 1)
streammux.set_property('batched-push-timeout', 4000000)
pgie.set_property('config-file-path', "shelltus_edge_pgie_config.txt")
# Set sync = false to avoid late frame drops at the display-sink
sink.set_property('sync', False)
print("Adding elements to Pipeline \n")
pipeline.add(source)
pipeline.add(caps_v4l2src)
pipeline.add(vidconvsrc)
pipeline.add(nvvidconvsrc)
pipeline.add(caps_vidconvsrc)
pipeline.add(streammux)
pipeline.add(pgie)
pipeline.add(nvvidconv)
pipeline.add(nvosd)
pipeline.add(sink)
if is_aarch64():
pipeline.add(transform)
# we link the elements together
# v4l2src -> nvvideoconvert -> mux ->
# nvinfer -> nvvideoconvert -> nvosd -> video-renderer
print("Linking elements in the Pipeline \n")
source.link(caps_v4l2src)
caps_v4l2src.link(vidconvsrc)
vidconvsrc.link(nvvidconvsrc)
nvvidconvsrc.link(caps_vidconvsrc)
sinkpad = streammux.get_request_pad("sink_0")
if not sinkpad:
sys.stderr.write(" Unable to get the sink pad of streammux \n")
srcpad = caps_vidconvsrc.get_static_pad("src")
if not srcpad:
sys.stderr.write(" Unable to get source pad of caps_vidconvsrc \n")
srcpad.link(sinkpad)
streammux.link(pgie)
pgie.link(nvvidconv)
nvvidconv.link(nvosd)
if is_aarch64():
nvosd.link(transform)
transform.link(sink)
else:
nvosd.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")
osdsinkpad.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe, 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(sys.argv))