modified_webcam.py

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import argparse
import cv2

import numpy as np
import glob

from maskrcnn_benchmark.config import cfg
from predictor import COCODemo

import time


 
 
def main():
    parser = argparse.ArgumentParser(description="PyTorch Object Detection Webcam Demo")
    parser.add_argument(
        "--config-file",
        default="../configs/caffe2/e2e_mask_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml",
        metavar="FILE",
        help="path to config file",
    )
    parser.add_argument(
        "--confidence-threshold",
        type=float,
        default=0.7,
        help="Minimum score for the prediction to be shown",
    )
    parser.add_argument(
        "--min-image-size",
        type=int,
        default=224,
        help="Smallest size of the image to feed to the model. "
            "Model was trained with 800, which gives best results",
    )
    parser.add_argument(
        "--show-mask-heatmaps",
        dest="show_mask_heatmaps",
        help="Show a heatmap probability for the top masks-per-dim masks",
        action="store_true",
    )
    parser.add_argument(
        "--masks-per-dim",
        type=int,
        default=2,
        help="Number of heatmaps per dimension to show",
    )
    parser.add_argument(
        "opts",
        help="Modify model config options using the command-line",
        default=None,
        nargs=argparse.REMAINDER,
    )

    args = parser.parse_args()

    # load config from file and command-line arguments
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()

    # prepare object that handles inference plus adds predictions on top of image
    coco_demo = COCODemo(
        cfg,
        confidence_threshold=args.confidence_threshold,
        show_mask_heatmaps=args.show_mask_heatmaps,
        masks_per_dim=args.masks_per_dim,
        min_image_size=args.min_image_size,
    )
    
    number_of_images = 1
    for i in range(number_of_images):

        img =  cv2.imread('/home/atas/kitti_data/2011_09_26/2011_10_03_drive_0042_sync/image_02/data/'+str(i).zfill(10)+'.png') 
        start_time = time.time()

        #scale_percent = 200 # percent of original size
        #width = int(img.shape[1] * scale_percent / 100)
        #height = int(img.shape[0] * scale_percent / 100)
        #dim = (width, height)
        # resize image
        #resized = cv2.resize(img, dim, interpolation = cv2.INTER_AREA) 
 
        composite, top_predictions = coco_demo.run_on_opencv_image(img)
        labels = top_predictions.get_field("labels")
        bbox = top_predictions.bbox
        print(labels, bbox)
        
        cv2.imwrite('/home/atas/kitti_data/2011_09_26/2011_10_03_drive_0042_sync/maskrcnn_detections/detection_image_02/'+str(i).zfill(10)+'.png',composite) 

        output = open(output_file, 'w')
        for i in range(len(labels)):
            full_label_bbox = str(labels.data.cpu().numpy()[i]) + ' ' + str(bbox.cpu().numpy()[i][0]) + ' ' + str(bbox.cpu().numpy()[i][1]) + ' ' + str(bbox.cpu().numpy()[i][2]) + ' ' + str(bbox.cpu().numpy()[i][3]) + '\n'

            output.write(full_label_bbox)
        output.close() 


        print("Time: {:.2f} s / img".format(time.time() - start_time))
        cv2.imshow("COCO detections", composite)
        if cv2.waitKey(1) == 27:
            break  # esc to quit
    cv2.destroyAllWindows()


if __name__ == "__main__":
    main()