nabeelmsft

#pragma once

// Standard library includes
#include <string>
#include <vector>

// Third party includes
#include <opencv2/core.hpp>

nabeelmsft

// Copyright (c) Microsoft Corporation.
// Licensed under the MIT license.

// Standard library includes
#include <fstream>
#include <string>
#include <vector>
#include <stdio.h>
#include <curl/curl.h>
#include <iostream>

nabeelmsft

void ObjectDetector::preview(cv::Mat &rgb, const std::vector<cv::Rect> &boxes, const std::vector<int> &labels, const std::vector<float> &confidences) const
{
    // This method is responsible for marking up the raw BGR frames with the inferences from the
    // neural network. Since all of our object detector networks output bounding boxes, labels, and confidences,
    // let's mark up the frames with those items.
    std::string artext = std::string("");
    for (std::size_t i = 0; i < boxes.size(); i++)
    {
        // Draw a bounding box around the detected object. Use a new color each time
        // up to some point, at which point we wrap around and start reusing colors.

nabeelmsft

using Azure.Messaging.EventHubs;
using Microsoft.Azure.WebJobs;
using Microsoft.Extensions.Logging;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading.Tasks;
using TwinsUpdateBetaFunctionApp.Model;

namespace TwinsUpdateBetaFunctionApp

nabeelmsft

# Copyright (c) Microsoft. All rights reserved.
# Licensed under the MIT license. See LICENSE file in the project root for
# full license information.

import uuid
import re
import json
import time
import types
import os

nabeelmsft

#!/usr/bin/python

import jetson.inference
import jetson.utils

import argparse
import sys

import os
import asyncio

nabeelmsft

#!/usr/bin/python

import jetson.inference
import jetson.utils

import argparse
import sys

import os
import asyncio

nabeelmsft

#!/usr/bin/python

import jetson.inference
import jetson.utils

import argparse
import sys

import os
import asyncio