From 8032dc798287b0ae26342063c3016858f2b44974 Mon Sep 17 00:00:00 2001 From: adamhrv Date: Wed, 10 Apr 2019 23:04:29 +0200 Subject: add body detector, mod pull sheet --- megapixels/app/processors/person_detector.py | 65 ++++++++++++++++++++++++++++ megapixels/app/settings/app_cfg.py | 5 +++ megapixels/app/settings/types.py | 3 ++ megapixels/app/utils/display_utils.py | 7 +++ megapixels/app/utils/identity_utils.py | 19 ++++++-- 5 files changed, 96 insertions(+), 3 deletions(-) create mode 100644 megapixels/app/processors/person_detector.py (limited to 'megapixels/app') diff --git a/megapixels/app/processors/person_detector.py b/megapixels/app/processors/person_detector.py new file mode 100644 index 00000000..6daa8c40 --- /dev/null +++ b/megapixels/app/processors/person_detector.py @@ -0,0 +1,65 @@ +import sys +import os +from os.path import join +from pathlib import Path + +import cv2 as cv +import numpy as np +import imutils +import operator + +from app.utils import im_utils, logger_utils +from app.models.bbox import BBox +from app.settings import app_cfg as cfg +from app.settings import types + + +class DetectorCVDNN: + + # MobileNet SSD + dnn_scale = 0.007843 # fixed + dnn_mean = (127.5, 127.5, 127.5) # fixed + dnn_crop = False # crop or force resize + blob_size = (300, 300) + conf = 0.95 + + # detect + CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat", + "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", + "dog", "horse", "motorbike", "person", "pottedplant", "sheep", + "sofa", "train", "tvmonitor"] + + def __init__(self): + self.log = logger_utils.Logger.getLogger() + fp_prototxt = join(cfg.DIR_MODELS_CAFFE, 'mobilenet_ssd', 'MobileNetSSD_deploy.prototxt') + fp_model = join(cfg.DIR_MODELS_CAFFE, 'mobilenet_ssd', 'MobileNetSSD_deploy.caffemodel') + self.net = cv.dnn.readNet(fp_prototxt, fp_model) + self.net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV) + self.net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU) + + def detect(self, im, conf=None, largest=False, pyramids=None, zone=False, blob_size=None): + """Detects bodies and returns (list) of (BBox)""" + conf = self.conf if conf is None else conf + blob_size = self.blob_size if blob_size is None else blob_size + im = cv.resize(im, blob_size) + dim = im.shape[:2][::-1] + blob = cv.dnn.blobFromImage(im, self.dnn_scale, dim, self.dnn_mean) + self.net.setInput(blob) + net_outputs = self.net.forward() + + bboxes = [] + for i in range(0, net_outputs.shape[2]): + det_conf = float(net_outputs[0, 0, i, 2]) + bounds = np.array(net_outputs[0, 0, i, 3:7]) # bug: ensure all x,y within 1.0 ? + if det_conf > conf and np.all(bounds < 1): + idx = int(net_outputs[0, 0, i, 1]) + if self.CLASSES[idx] == "person": + rect_norm = net_outputs[0, 0, i, 3:7] + bboxes.append(BBox(*rect_norm)) + + if largest and len(bboxes) > 1: + # only keep largest + bboxes.sort(key=operator.attrgetter('area'), reverse=True) + bboxes = [bboxes[0]] + + return bboxes \ No newline at end of file diff --git a/megapixels/app/settings/app_cfg.py b/megapixels/app/settings/app_cfg.py index 1eed1a41..98d36b5f 100644 --- a/megapixels/app/settings/app_cfg.py +++ b/megapixels/app/settings/app_cfg.py @@ -19,6 +19,7 @@ LogLevelVar = click_utils.ParamVar(types.LogLevel) MetadataVar = click_utils.ParamVar(types.Metadata) DatasetVar = click_utils.ParamVar(types.Dataset) DataStoreVar = click_utils.ParamVar(types.DataStore) + # Face analysis HaarCascadeVar = click_utils.ParamVar(types.HaarCascade) FaceDetectNetVar = click_utils.ParamVar(types.FaceDetectNet) @@ -27,6 +28,10 @@ FaceLandmark2D_5Var = click_utils.ParamVar(types.FaceLandmark2D_5) FaceLandmark2D_68Var = click_utils.ParamVar(types.FaceLandmark2D_68) FaceLandmark3D_68Var = click_utils.ParamVar(types.FaceLandmark3D_68) +# Person/Body detector +BodyDetectNetVar = click_utils.ParamVar(types.BodyDetectNet) + + # base path DIR_SELF = os.path.dirname(os.path.realpath(__file__)) DIR_ROOT = Path(DIR_SELF).parent.parent.parent diff --git a/megapixels/app/settings/types.py b/megapixels/app/settings/types.py index 3d7e96c0..2609ece7 100644 --- a/megapixels/app/settings/types.py +++ b/megapixels/app/settings/types.py @@ -59,6 +59,9 @@ class FaceDetectNet(Enum): """Scene text detector networks""" HAAR, DLIB_CNN, DLIB_HOG, CVDNN, MTCNN_TF, MTCNN_PT, MTCNN_CAFFE = range(7) +class BodyDetectNet(Enum): + CVDNN = range(1) + class FaceExtractor(Enum): """Type of face recognition feature extractor""" # TODO deprecate DLIB resnet and use only CVDNN Caffe models diff --git a/megapixels/app/utils/display_utils.py b/megapixels/app/utils/display_utils.py index 43328ae9..8e265ae7 100644 --- a/megapixels/app/utils/display_utils.py +++ b/megapixels/app/utils/display_utils.py @@ -19,3 +19,10 @@ def handle_keyboard(delay_amt=1): break elif k != 255: log.debug(f'k: {k}') + +def handle_keyboard_video(delay_amt=1): + key = cv.waitKey(1) & 0xFF + # if the `q` key was pressed, break from the loop + if key == ord("q"): + cv.destroyAllWindows() + sys.exit() diff --git a/megapixels/app/utils/identity_utils.py b/megapixels/app/utils/identity_utils.py index 775652dc..5855fbbd 100644 --- a/megapixels/app/utils/identity_utils.py +++ b/megapixels/app/utils/identity_utils.py @@ -29,6 +29,13 @@ def names_match_strict(a, b): return len(clean_a) == len(clean_b) and letter_match(clean_a, clean_b) and letter_match(clean_b, clean_a) +def sanitize_name(name, as_str=False): + splits = [unidecode.unidecode(x.strip().lower()) for x in name.strip().split(' ')] + if as_str: + return ' '.join(splits) + else: + return splits + ''' class Dataset(Enum): LFW, VGG_FACE, VGG_FACE2, MSCELEB, UCCS, UMD_FACES, SCUT_FBP, UCF_SELFIE, UTK, \ @@ -106,12 +113,18 @@ def get_names(opt_dataset, opt_data_store=types.DataStore.HDD): def similarity(a, b): return difflib.SequenceMatcher(a=a.lower(), b=b.lower()).ratio() -def names_match(name_a, name_b, threshold=0.9, as_float=False, compound_score=False): +def names_match(name_a, name_b, threshold=0.9, as_float=False, compound_score=False, name_a_pre=False, name_b_pre=False): '''Returns boolean if names are similar enough ''' # strip spaces and split names into list of plain text words - name_a_clean = [unidecode.unidecode(x.strip().lower()) for x in name_a.strip().split(' ')] - name_b_clean = [unidecode.unidecode(x.strip().lower()) for x in name_b.strip().split(' ')] + if name_a_pre: + name_a_clean = name_a + else: + name_a_clean = [unidecode.unidecode(x.strip().lower()) for x in name_a.strip().split(' ')] + if name_b_pre: + name_b_clean = name_b + else: + name_b_clean = [unidecode.unidecode(x.strip().lower()) for x in name_b.strip().split(' ')] # assign short long vars len_a = len(name_a_clean) -- cgit v1.2.3-70-g09d2 From 9b1e2709cbdb40eabb34d379df18e61c10e3737c Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Thu, 11 Apr 2019 18:44:21 +0200 Subject: add h3 --- megapixels/app/site/parser.py | 7 +++-- .../datasets/50_people_one_question/index.html | 2 +- site/public/datasets/brainwash/index.html | 4 +-- site/public/datasets/duke_mtmc/index.html | 8 ++--- site/public/datasets/hrt_transgender/index.html | 2 +- site/public/datasets/index.html | 36 ---------------------- site/public/datasets/lfw/index.html | 4 +-- site/public/datasets/msceleb/index.html | 4 +-- site/public/datasets/oxford_town_centre/index.html | 11 ++++--- site/public/datasets/uccs/index.html | 6 ++-- 10 files changed, 27 insertions(+), 57 deletions(-) (limited to 'megapixels/app') diff --git a/megapixels/app/site/parser.py b/megapixels/app/site/parser.py index dc2a09f2..6b71e041 100644 --- a/megapixels/app/site/parser.py +++ b/megapixels/app/site/parser.py @@ -145,8 +145,11 @@ def parse_markdown(metadata, sections, s3_path, skip_h1=False): return ' {}'.format(key, footnote_count, key, index, index) key_regex = re.compile(key.replace('[', '\\[').replace('^', '\\^').replace(']', '\\]')) content = key_regex.sub(footnote_tag, content) - footnote_txt = footnote_txt.replace("{}_BACKLINKS".format(index), "".join(footnote_backlinks)) + footnote_txt = footnote_txt.replace("{}_BACKLINKS".format(key), "".join(footnote_backlinks)) + content += '
' + content += '

References

' content += footnote_txt + content += '
' return content @@ -254,7 +257,7 @@ def format_footnotes(footnotes, s3_path): continue key, note = footnote.split(': ', 1) footnote_index_lookup[key] = index - footnote_list.append('{}_BACKLINKS'.format(key, index) + markdown(note)) + footnote_list.append('{}_BACKLINKS'.format(key, key) + markdown(note)) index += 1 footnote_txt = '
  • ' + '
  • '.join(footnote_list) + '
' diff --git a/site/public/datasets/50_people_one_question/index.html b/site/public/datasets/50_people_one_question/index.html index b27fa3e5..3b33f530 100644 --- a/site/public/datasets/50_people_one_question/index.html +++ b/site/public/datasets/50_people_one_question/index.html @@ -35,7 +35,7 @@
33
Purpose
-
Facial landmark estimation in the wild
+
Facial landmark estimation
Website
caltech.edu
diff --git a/site/public/datasets/brainwash/index.html b/site/public/datasets/brainwash/index.html index 10ee577c..bd59f573 100644 --- a/site/public/datasets/brainwash/index.html +++ b/site/public/datasets/brainwash/index.html @@ -120,11 +120,11 @@
  • add ethics link to Stanford
  • add optout info
    • -

    References

    • a

      "readme.txt" https://exhibits.stanford.edu/data/catalog/sx925dc9385.

    • a

      Stewart, Russel. Andriluka, Mykhaylo. "End-to-end people detection in crowded scenes". 2016.

    • a

      Li, Y. and Dou, Y. and Liu, X. and Li, T. Localized Region Context and Object Feature Fusion for People Head Detection. ICIP16 Proceedings. 2016. Pages 594-598.

    • a

      Zhao. X, Wang Y, Dou, Y. A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering.

      -
    +