demo.py

import argparse

import numpy as np
import cv2 as cv

from lpd_yunet import LPD_YuNet

def str2bool(v):
    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
        return True
    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
        return False
    else:
        raise NotImplementedError

backends = [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_BACKEND_CUDA]
targets = [cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_CUDA, cv.dnn.DNN_TARGET_CUDA_FP16]
help_msg_backends = "Choose one of the computation backends: {:d}: OpenCV implementation (default); {:d}: CUDA"
help_msg_targets = "Chose one of the target computation devices: {:d}: CPU (default); {:d}: CUDA; {:d}: CUDA fp16"
try:
    backends += [cv.dnn.DNN_BACKEND_TIMVX]
    targets += [cv.dnn.DNN_TARGET_NPU]
    help_msg_backends += "; {:d}: TIMVX"
    help_msg_targets += "; {:d}: NPU"
except:
    print('This version of OpenCV does not support TIM-VX and NPU. Visit https://gist.github.com/fengyuentau/5a7a5ba36328f2b763aea026c43fa45f for more information.')

parser = argparse.ArgumentParser(description='LPD-YuNet for License Plate Detection')
parser.add_argument('--input', '-i', type=str, help='Path to the input image. Omit for using default camera.')
parser.add_argument('--model', '-m', type=str, default='license_plate_detection_lpd_yunet_2022may.onnx', help='Path to the model.')
parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
parser.add_argument('--conf_threshold', type=float, default=0.9, help='Filter out faces of confidence < conf_threshold.')
parser.add_argument('--nms_threshold', type=float, default=0.3, help='Suppress bounding boxes of iou >= nms_threshold.')
parser.add_argument('--top_k', type=int, default=5000, help='Keep top_k bounding boxes before NMS.')
parser.add_argument('--keep_top_k', type=int, default=750, help='Keep keep_top_k bounding boxes after NMS.')
parser.add_argument('--save', '-s', type=str2bool, default=False, help='Set true to save results. This flag is invalid when using camera.')
parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
args = parser.parse_args()

def visualize(image, dets, line_color=(0, 255, 0), text_color=(0, 0, 255), fps=None):
    output = image.copy()

    if fps is not None:
        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, text_color)

    for det in dets:
        bbox = det[:-1].astype(np.int32)
        x1, y1, x2, y2, x3, y3, x4, y4 = bbox

        # Draw the border of license plate
        cv.line(output, (x1, y1), (x2, y2), line_color, 2)
        cv.line(output, (x2, y2), (x3, y3), line_color, 2)
        cv.line(output, (x3, y3), (x4, y4), line_color, 2)
        cv.line(output, (x4, y4), (x1, y1), line_color, 2)

    return output

if __name__ == '__main__':
    # Instantiate LPD-YuNet
    model = LPD_YuNet(modelPath=args.model,
                      confThreshold=args.conf_threshold,
                      nmsThreshold=args.nms_threshold,
                      topK=args.top_k,
                      keepTopK=args.keep_top_k,
                      backendId=args.backend,
                      targetId=args.target)

    # If input is an image
    if args.input is not None:
        image = cv.imread(args.input)
        h, w, _ = image.shape

        # Inference
        model.setInputSize([w, h])
        results = model.infer(image)

        # Print results
        print('{} license plates detected.'.format(results.shape[0]))

        # Draw results on the input image
        image = visualize(image, results)

        # Save results if save is true
        if args.save:
            print('Resutls saved to result.jpg')
            cv.imwrite('result.jpg', image)

        # Visualize results in a new window
        if args.vis:
            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
            cv.imshow(args.input, image)
            cv.waitKey(0)
    else: # Omit input to call default camera
        deviceId = 0
        cap = cv.VideoCapture(deviceId)
        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
        model.setInputSize([w, h])

        tm = cv.TickMeter()
        while cv.waitKey(1) < 0:
            hasFrame, frame = cap.read()
            if not hasFrame:
                print('No frames grabbed!')
                break

            # Inference
            tm.start()
            results = model.infer(frame) # results is a tuple
            tm.stop()

            # Draw results on the input image
            frame = visualize(frame, results, fps=tm.getFPS())

            # Visualize results in a new Window
            cv.imshow('LPD-YuNet Demo', frame)

            tm.reset()