track-objects.py

#!/usr/bin/env python

import device_patches       # Device specific patches for Jetson Nano (needs to be before importing cv2)

# To run this example, you will need to install filterpy and lap via `pip install filterpy lap`
try:
    import cv2
except ImportError:
    print('Missing OpenCV, install via `pip3 install "opencv-python>=4.5.1.48,<5"`')
    exit(1)
import os
import sys, getopt
import signal
import time
from edge_impulse_linux.image import ImageImpulseRunner
from utils.sort_tracker import SORTTracker

runner = None
# if you don't want to see a camera preview, set this to False
show_camera = True
if (sys.platform == 'linux' and not os.environ.get('DISPLAY')):
    show_camera = False

def now():
    return round(time.time() * 1000)

def get_webcams():
    port_ids = []
    for port in range(5):
        print("Looking for a camera in port %s:" %port)
        camera = cv2.VideoCapture(port)
        if camera.isOpened():
            ret = camera.read()[0]
            if ret:
                backendName =camera.getBackendName()
                w = camera.get(3)
                h = camera.get(4)
                print("Camera %s (%s x %s) found in port %s " %(backendName,h,w, port))
                port_ids.append(port)
            camera.release()
    return port_ids

def sigint_handler(sig, frame):
    print('Interrupted')
    if (runner):
        runner.stop()
    sys.exit(0)

signal.signal(signal.SIGINT, sigint_handler)

def help():
    print('python classify.py <path_to_model.eim> <Camera port ID, only required when more than 1 camera is present>')

def main(argv):
    try:
        opts, args = getopt.getopt(argv, "h", ["--help"])
    except getopt.GetoptError:
        help()
        sys.exit(2)

    for opt, arg in opts:
        if opt in ('-h', '--help'):
            help()
            sys.exit()

    if len(args) == 0:
        help()
        sys.exit(2)

    model = args[0]

    dir_path = os.path.dirname(os.path.realpath(__file__))
    modelfile = os.path.join(dir_path, model)

    print('MODEL: ' + modelfile)

    with ImageImpulseRunner(modelfile) as runner:
        try:
            model_info = runner.init()
            # model_info = runner.init(debug=True, timeout=60) # to get debug print out and set longer timeout
            print('Loaded runner for "' + model_info['project']['owner'] + ' / ' + model_info['project']['name'] + '"')
            labels = model_info['model_parameters']['labels']
            if len(args)>= 2:
                videoCaptureDeviceId = int(args[1])
            else:
                port_ids = get_webcams()
                if len(port_ids) == 0:
                    raise Exception('Cannot find any webcams')
                if len(args)<= 1 and len(port_ids)> 1:
                    raise Exception("Multiple cameras found. Add the camera port ID as a second argument to use to this script")
                videoCaptureDeviceId = int(port_ids[0])

            camera = cv2.VideoCapture(videoCaptureDeviceId)
            ret = camera.read()[0]
            if ret:
                backendName = camera.getBackendName()
                w = camera.get(3)
                h = camera.get(4)
                print("Camera %s (%s x %s) in port %s selected." %(backendName,h,w, videoCaptureDeviceId))
                camera.release()
            else:
                raise Exception("Couldn't initialize selected camera.")

            next_frame = 0 # limit to ~10 fps here

            # Initialize tracker with your chosen parameters
            tracker = SORTTracker(
                max_age=5,
                min_hits=3,
                iou_threshold=0.01
            )
            
            for res, img in runner.classifier(videoCaptureDeviceId):
                if (next_frame > now()):
                    time.sleep((next_frame - now()) / 1000)

                if "bounding_boxes" in res["result"].keys():
                    detections = []
                    for bb in res["result"]["bounding_boxes"]:
                        x, y, w, h = bb['x'], bb['y'], bb['width'], bb['height']
                        img = cv2.rectangle(img, (bb['x'], bb['y']), (bb['x'] + bb['width'], bb['y'] + bb['height']), (255, 0, 0), 1)
                        detections.append([x + w/2, y + h/2, w, h]) # For FOMO, we might want to pass a larger box than the detected one

                    tracked_objects = tracker.update(detections)
                    for track_id, (x, y, w, h) in tracked_objects:
                        x1, y1 = int(x - w/2), int(y - h/2)
                        x2, y2 = int(x + w/2), int(y + h/2)
                        # cv2.rectangle(img, (x1, y1), (x2, y2), (255, 0, 0), 2)
                        cv2.putText(img, f"ID: {track_id}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 0, 0), 1)

                if (show_camera):
                    cv2.imshow('edgeimpulse', cv2.cvtColor(img, cv2.COLOR_RGB2BGR))
                    if cv2.waitKey(1) == ord('q'):
                        break

                next_frame = now() + 100
        finally:
            if (runner):
                runner.stop()

if __name__ == "__main__":
   main(sys.argv[1:])