diff options
Diffstat (limited to 'megapixels/commands/processor/body_roi_video.py')
| -rw-r--r-- | megapixels/commands/processor/body_roi_video.py | 148 |
1 files changed, 148 insertions, 0 deletions
diff --git a/megapixels/commands/processor/body_roi_video.py b/megapixels/commands/processor/body_roi_video.py new file mode 100644 index 00000000..84bcebd2 --- /dev/null +++ b/megapixels/commands/processor/body_roi_video.py @@ -0,0 +1,148 @@ +""" +Crop images to prepare for training +""" + +import click +# from PIL import Image, ImageOps, ImageFilter, ImageDraw + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +color_filters = {'color': 1, 'gray': 2, 'all': 3} + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', required=True, + help='Override enum output filename CSV') +@click.option('--store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.HDD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--size', 'opt_size', + type=(int, int), default=(640, 480), + help='Input image size') +@click.option('-d', '--detector', 'opt_detector_type', + type=cfg.BodyDetectNetVar, + default=click_utils.get_default(types.BodyDetectNet.CVDNN), + help=click_utils.show_help(types.BodyDetectNet)) +@click.option('-g', '--gpu', 'opt_gpu', default=0, + help='GPU index') +@click.option('--conf', 'opt_conf_thresh', default=0.85, type=click.FloatRange(0,1), + help='Confidence minimum threshold') +@click.option('-p', '--pyramids', 'opt_pyramids', default=0, type=click.IntRange(0,4), + help='Number pyramids to upscale for DLIB detectors') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, + help='Display detections to debug') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('--color', 'opt_color_filter', + type=click.Choice(color_filters.keys()), default='color', + help='Filter to keep color or grayscale images (color = keep color') +@click.option('--keep', 'opt_largest', type=click.Choice(['largest', 'all']), default='largest', + help='Only keep largest face') +@click.option('--zone', 'opt_zone', default=(0.0, 0.0), type=(float, float), + help='Face center must be located within zone region (0.5 = half width/height)') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_size, opt_detector_type, + opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_force, opt_color_filter, + opt_largest, opt_zone): + """Converts frames with faces to CSV of ROIs""" + + import sys + import os + from os.path import join + from pathlib import Path + from glob import glob + + from tqdm import tqdm + import numpy as np + import dlib # must keep a local reference for dlib + import cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils, display_utils, draw_utils + from app.processors import person_detector + from app.models.data_store import DataStore + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + + opt_fp_out = opt_fp_out + if not opt_force and Path(opt_fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # set detector + if opt_detector_type == types.BodyDetectNet.CVDNN: + detector = person_detector.DetectorCVDNN() + else: + log.error('{} not yet implemented'.format(opt_detector_type.name)) + return + + # set largest flag, to keep all or only largest + opt_largest = (opt_largest == 'largest') + + # process video + cap = cv.VideoCapture(opt_fp_in) + + bboxes_all = [] + data_out = [] + frame_index = 0 + + while cap.isOpened(): + # get video frame + readable, im = cap.read() + if not readable: + break + + im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + + try: + bboxes_norm = detector.detect(im_resized, pyramids=opt_pyramids, largest=opt_largest, + zone=opt_zone, conf=opt_conf_thresh, blob_size=opt_size) + except Exception as e: + log.error('could not detect: {}'.format(frame_index)) + log.error('{}'.format(e)) + continue + + for bbox in bboxes_norm: + roi = { + 'record_index': frame_index, + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h + } + data_out.append(roi) + + if opt_display and len(bboxes_norm): + # draw each box + for bbox_norm in bboxes_norm: + dim = im_resized.shape[:2][::-1] + bbox_dim = bbox.to_dim(dim) + # if dim[0] > 1000: + # im_resized = im_utils.resize(im_resized, width=1000) + im_resized = draw_utils.draw_bbox(im_resized, bbox_norm) + + # display and wait + cv.imshow('', im_resized) + display_utils.handle_keyboard_video() + + frame_index += 1 + + + # create DataFrame and save to CSV + file_utils.mkdirs(opt_fp_out) + df = pd.DataFrame.from_dict(data_out) + df.index.name = 'index' + df.to_csv(opt_fp_out) + + # save script + file_utils.write_text(' '.join(sys.argv), '{}.sh'.format(opt_fp_out))
\ No newline at end of file |