orc.py

#!/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.
################################################################################

import sys
sys.path.append('../')
import gi
import configparser
gi.require_version('Gst', '1.0')
from gi.repository import GObject, Gst
from gi.repository import GLib
from ctypes import *
import time
import sys
import math
import platform
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
from common.FPS import GETFPS
import numpy as np
import pyds
import cv2
import os
import os.path
from os import path
fps_streams={}
frame_count={}
saved_count={}
global PGIE_CLASS_ID_VEHICLE
PGIE_CLASS_ID_VEHICLE=0
global PGIE_CLASS_ID_PERSON
PGIE_CLASS_ID_PERSON=2

MAX_DISPLAY_LEN=64
PGIE_CLASS_ID_VEHICLE = 0
PGIE_CLASS_ID_BICYCLE = 1
PGIE_CLASS_ID_PERSON = 2
PGIE_CLASS_ID_ROADSIGN = 3
MUXER_OUTPUT_WIDTH=1920
MUXER_OUTPUT_HEIGHT=1080
MUXER_BATCH_TIMEOUT_USEC=4000000
TILED_OUTPUT_WIDTH=1920
TILED_OUTPUT_HEIGHT=1080
GST_CAPS_FEATURES_NVMM="memory:NVMM"
pgie_classes_str= ["Vehicle", "TwoWheeler", "Person","RoadSign"]

vehicle_list = []   # vehicle metadata list

########## Vehicle Class ##########     # vehicle metadata class; described by tracking id, list of frames it is tracked for and the coordinates of bounding boxes in the tracking instances

class Vehicle:
    def __init__(self, vehicle_id, frames_list=[], x_list=[], y_list=[], xc_list=[], yc_list=[], width_list=[], height_list=[], lane_list=[]):
        self.vehicle_id = vehicle_id
        self.frames_list = frames_list
        self.x_list = x_list
        self.y_list = y_list
        self.xc_list = xc_list
        self.yc_list = yc_list

########## Vehicle Class ##########

# tiler_sink_pad_buffer_probe  will extract metadata received on tiler src pad
# and update params for drawing rectangle, object information etc.
def tiler_sink_pad_buffer_probe(pad,info,u_data):
    frame_number=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

        frame_number=frame_meta.frame_num
        l_obj=frame_meta.obj_meta_list
        num_rects = frame_meta.num_obj_meta
        obj_counter = {
        PGIE_CLASS_ID_VEHICLE:0,
        PGIE_CLASS_ID_PERSON:0,
        PGIE_CLASS_ID_BICYCLE:0,
        PGIE_CLASS_ID_ROADSIGN:0
        }
        while l_obj is not None:
            try: 
                # Casting l_obj.data to pyds.NvDsObjectMeta
                obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
                if obj_meta.class_id == PGIE_CLASS_ID_VEHICLE:  # vehicle detected
                    if obj_meta.rect_params.top > (0.25 * 1080):    # discard detection instances for vehicles too far from the camera
                        car_found = 0   # vehicle id flag
                        for x in vehicle_list:
                            if x.vehicle_id == obj_meta.object_id:  # vehicle id found in the list of vehicle metadata
                                x.frames_list.append(frame_number)
                                x.x_list.append(int(obj_meta.rect_params.left))
                                x.y_list.append(int(obj_meta.rect_params.top))
                                x.xc_list.append(int(obj_meta.rect_params.left + (obj_meta.rect_params.width / 2)))
                                x.yc_list.append(int(obj_meta.rect_params.top + (obj_meta.rect_params.height / 2)))
                                car_found = 1   # vehicle metadata was already initialized 
                                break
                            
                        if car_found == 0:      # vehicle metadata was not initialized in the list
                            frames_temp_list = []
                            frames_temp_list.append(frame_number)
                            x_temp_list = []
                            x_temp_list.append(int(obj_meta.rect_params.left))
                            y_temp_list = []
                            y_temp_list.append(int(obj_meta.rect_params.top))
                            xc_temp_list = []
                            xc_temp_list.append(int(obj_meta.rect_params.left + (obj_meta.rect_params.width / 2)))
                            yc_temp_list = []
                            yc_temp_list.append(int(obj_meta.rect_params.top + (obj_meta.rect_params.height / 2)))
                            vehicle_list.append(Vehicle(obj_meta.object_id, frames_temp_list, x_temp_list, y_temp_list, xc_temp_list, yc_temp_list))
                            
                        print('Vehicle ID = ', obj_meta.object_id, ', Frame Number = ', frame_number, ', Top X = ', obj_meta.rect_params.left,', Top Y = ', obj_meta.rect_params.top, ', Width = ', obj_meta.rect_params.width, ', Height = ', obj_meta.rect_params.height)     # initialize vehicle metadata
                        
            except StopIteration:
                break
            obj_counter[obj_meta.class_id] += 1
            
            try: 
                l_obj=l_obj.next
            except StopIteration:
                break

        print("Frame Number =", frame_number, "Number of Objects in frame =",num_rects,"Vehicles in frame =",obj_counter[PGIE_CLASS_ID_VEHICLE])    # object bounding box metadata overlay
        # Get frame rate through this probe
        fps_streams["stream{0}".format(frame_meta.pad_index)].get_fps()
        
        # 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.
        py_nvosd_text_params.display_text = "Frame Number={} Number of Objects={} Vehicle_count={}".format(frame_number, num_rects, obj_counter[PGIE_CLASS_ID_VEHICLE])

        # 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)
        
        if frame_number == 500:     # when the stream should stop; increase this value to extend the life of video stream
            y_min_list = []
            y_max_list = []
            for car_object in vehicle_list:
                if len(car_object.frames_list) > 10:    # ignore tracking instances with a life of less than ten frames
                    print(car_object.vehicle_id, car_object.frames_list, car_object.y_list, len(car_object.frames_list), '\n', sep=' ')
                    y_min_list.append(min(car_object.y_list))
                    y_max_list.append(max(car_object.y_list))
            y_min_list.sort()
            y_max_list.sort()
            print('y_min:', y_min_list, len(y_min_list), '\n')
            print('y_max:', y_max_list, len(y_max_list), '\n')
            print('Optimal Frame Range:')
            print('y:', min(y_max_list)-100, max(y_min_list))
            
            with open('/opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/optimal_frame_extractor/road.txt', 'r') as file:   # input file of the frame extractor application
                data = file.readlines()    
            data[10] = str('y1 ') + str(min(y_max_list)-100) + str(' #opt_frm_inf_start') + str('\n')
            data[11] = str('y2 ') + str(max(y_min_list)) + str(' #opt_frm_inf_end')
            with open('/opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/optimal_frame_extractor/road.txt', 'w') as file:
                file.writelines(data)
            
            sys.exit()
        
        try:
            l_frame=l_frame.next
        except StopIteration:
            break

    return Gst.PadProbeReturn.OK

def draw_bounding_boxes(image,obj_meta,confidence):
    confidence='{0:.2f}'.format(confidence)
    rect_params=obj_meta.rect_params
    top=int(rect_params.top)
    left=int(rect_params.left)
    width=int(rect_params.width)
    height=int(rect_params.height)
    obj_name=pgie_classes_str[obj_meta.class_id]
    image=cv2.rectangle(image,(left,top),(left+width,top+height),(0,0,255,0),2)
    # Note that on some systems cv2.putText erroneously draws horizontal lines across the image
    image=cv2.putText(image,obj_name+',C='+str(confidence),(left-10,top-10),cv2.FONT_HERSHEY_SIMPLEX,0.5,(0,0,255,0),2)
    return image

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.
    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.
        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)   
    if(is_aarch64() and name.find("nvv4l2decoder") != -1):
        print("Seting bufapi_version\n")
        Object.set_property("bufapi-version",True)

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(args):
    
    # Check input arguments
    if len(args) < 2:
        sys.stderr.write("usage: %s <uri1> [uri2] ... [uriN] <folder to save frames>\n" % args[0])
        sys.exit(1)

    for i in range(0,len(args)-1):
        fps_streams["stream{0}".format(i)]=GETFPS(i)
    number_sources=len(args)-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()
    is_live = False

    if not pipeline:
        sys.stderr.write(" Unable to create Pipeline \n")
    print("Creating streamux \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")

    pipeline.add(streammux)
    for i in range(number_sources):
        frame_count["stream_"+str(i)]=0
        saved_count["stream_"+str(i)]=0
        print("Creating source_bin ",i," \n ")
        uri_name=args[i+1]
        if uri_name.find("rtsp://") == 0 :
            is_live = True
        source_bin=create_source_bin(i, uri_name)
        if not source_bin:
            sys.stderr.write("Unable to create source bin \n")
        pipeline.add(source_bin)
        padname="sink_%u" %i
        sinkpad= streammux.get_request_pad(padname) 
        if not sinkpad:
            sys.stderr.write("Unable to create sink pad bin \n")
        srcpad=source_bin.get_static_pad("src")
        if not srcpad:
            sys.stderr.write("Unable to create src pad bin \n")
        srcpad.link(sinkpad)
    print("Creating Pgie \n ")
    pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
    if not pgie:
        sys.stderr.write(" Unable to create pgie \n")
        
    tracker = Gst.ElementFactory.make("nvtracker", "tracker")       # tracker to assign unique ids to objects
    if not tracker:
        sys.stderr.write(" Unable to create tracker \n")
    
    # Add nvvidconv1 and filter1 to convert the frames to RGBA
    # which is easier to work with in Python.
    print("Creating nvvidconv1 \n ")
    nvvidconv1 = Gst.ElementFactory.make("nvvideoconvert", "convertor1")
    if not nvvidconv1:
        sys.stderr.write(" Unable to create nvvidconv1 \n")
    print("Creating filter1 \n ")
    caps1 = Gst.Caps.from_string("video/x-raw(memory:NVMM), format=RGBA")
    filter1 = Gst.ElementFactory.make("capsfilter", "filter1")
    if not filter1:
        sys.stderr.write(" Unable to get the caps filter1 \n")
    filter1.set_property("caps", caps1)
    print("Creating tiler \n ")
    tiler=Gst.ElementFactory.make("nvmultistreamtiler", "nvtiler")
    if not tiler:
        sys.stderr.write(" Unable to create tiler \n")
    print("Creating nvvidconv \n ")
    nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
    if not nvvidconv:
        sys.stderr.write(" Unable to create nvvidconv \n")
    print("Creating nvosd \n ")
    nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
    if not nvosd:
        sys.stderr.write(" Unable to create nvosd \n")
    if(is_aarch64()):
        print("Creating transform \n ")
        transform=Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
        if not transform:
            sys.stderr.write(" Unable to create transform \n")

    print("Creating EGLSink \n")
    sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
    if not sink:
        sys.stderr.write(" Unable to create egl sink \n")

    if is_live:
        print("Atleast one of the sources is live")
        streammux.set_property('live-source', 1)

    streammux.set_property('width', 1920)
    streammux.set_property('height', 1080)
    streammux.set_property('batch-size', number_sources)
    streammux.set_property('batched-push-timeout', 4000000)
    pgie.set_property('config-file-path', "dstest_imagedata_config.txt")
    pgie_batch_size=pgie.get_property("batch-size")
    if(pgie_batch_size != number_sources):
        print("WARNING: Overriding infer-config batch-size",pgie_batch_size," with number of sources ", number_sources," \n")
        pgie.set_property("batch-size",number_sources)
    tiler_rows=int(math.sqrt(number_sources))
    tiler_columns=int(math.ceil((1.0*number_sources)/tiler_rows))
    tiler.set_property("rows",tiler_rows)
    tiler.set_property("columns",tiler_columns)
    tiler.set_property("width", TILED_OUTPUT_WIDTH)
    tiler.set_property("height", TILED_OUTPUT_HEIGHT)

    sink.set_property("sync", 0)

    # Set properties of tracker
    config = configparser.ConfigParser()
    config.read('dstest2_tracker_config.txt')
    config.sections()

    for key in config['tracker']:
        if key == 'tracker-width' :
            tracker_width = config.getint('tracker', key)
            tracker.set_property('tracker-width', tracker_width)
        if key == 'tracker-height' :
            tracker_height = config.getint('tracker', key)
            tracker.set_property('tracker-height', tracker_height)
        if key == 'gpu-id' :
            tracker_gpu_id = config.getint('tracker', key)
            tracker.set_property('gpu_id', tracker_gpu_id)
        if key == 'll-lib-file' :
            tracker_ll_lib_file = config.get('tracker', key)
            tracker.set_property('ll-lib-file', tracker_ll_lib_file)
        if key == 'll-config-file' :
            tracker_ll_config_file = config.get('tracker', key)
            tracker.set_property('ll-config-file', tracker_ll_config_file)
        if key == 'enable-batch-process' :
            tracker_enable_batch_process = config.getint('tracker', key)
            tracker.set_property('enable_batch_process', tracker_enable_batch_process)

    if not is_aarch64():
        # Use CUDA unified memory in the pipeline so frames
        # can be easily accessed on CPU in Python.
        mem_type = int(pyds.NVBUF_MEM_CUDA_UNIFIED)
        streammux.set_property("nvbuf-memory-type", mem_type)
        nvvidconv.set_property("nvbuf-memory-type", mem_type)
        nvvidconv1.set_property("nvbuf-memory-type", mem_type)
        tiler.set_property("nvbuf-memory-type", mem_type)

    print("Adding elements to Pipeline \n")
    pipeline.add(pgie)
    pipeline.add(tracker)
    pipeline.add(tiler)
    pipeline.add(nvvidconv)
    pipeline.add(filter1)
    pipeline.add(nvvidconv1)
    pipeline.add(nvosd)
    if is_aarch64():
        pipeline.add(transform)
    pipeline.add(sink)

    print("Linking elements in the Pipeline \n")
    streammux.link(pgie)    
    pgie.link(tracker)
    tracker.link(nvvidconv1)
    nvvidconv1.link(filter1)
    filter1.link(tiler)
    tiler.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)

    tiler_sink_pad=tiler.get_static_pad("sink")
    if not tiler_sink_pad:
        sys.stderr.write(" Unable to get src pad \n")
    else:
        tiler_sink_pad.add_probe(Gst.PadProbeType.BUFFER, tiler_sink_pad_buffer_probe, 0)

    # List the sources
    print("Now playing...")
    for i, source in enumerate(args[:-1]):
        if (i != 0):
            print(i, ": ", source)

    print("Starting pipeline \n")
    # start play back and listed to events		
    pipeline.set_state(Gst.State.PLAYING)
    try:
        loop.run()
    except:
        pass
    
    def cleanup():
    # cleanup
        print("Exiting app\n")
        pipeline.set_state(Gst.State.NULL)

if __name__ == '__main__':
    sys.exit(main(sys.argv))