diff options
Diffstat (limited to 'megapixels/app')
| -rw-r--r-- | megapixels/app/models/data_store.py | 2 | ||||
| -rw-r--r-- | megapixels/app/processors/face_detector.py | 8 | ||||
| -rw-r--r-- | megapixels/app/processors/face_pose.py | 42 | ||||
| -rw-r--r-- | megapixels/app/utils/im_utils.py | 6 |
4 files changed, 39 insertions, 19 deletions
diff --git a/megapixels/app/models/data_store.py b/megapixels/app/models/data_store.py index 7b6bef21..626c9da4 100644 --- a/megapixels/app/models/data_store.py +++ b/megapixels/app/models/data_store.py @@ -28,6 +28,8 @@ class DataStore: return join(self.dir_media, 'original') def face(self, subdir, fn, ext): + if subdir == '' or subdir is None: + subdir = '.' return join(self.dir_media, 'original', subdir, f'{fn}.{ext}') def face_crop(self, subdir, fn, ext): diff --git a/megapixels/app/processors/face_detector.py b/megapixels/app/processors/face_detector.py index 3a90c557..75ba54d4 100644 --- a/megapixels/app/processors/face_detector.py +++ b/megapixels/app/processors/face_detector.py @@ -24,7 +24,7 @@ class DetectorMTCNN: from mtcnn.mtcnn import MTCNN self.detector = MTCNN() - def detect(self, im, size=(400,400), conf_thresh=None, pyramids=None, largest=False): + def detect(self, im, size=(400,400), conf_thresh=None, pyramids=None, largest=False, zone=None): '''Detects face using MTCNN and returns (list) of BBox :param im: (numpy.ndarray) image :returns list of BBox @@ -79,7 +79,7 @@ class DetectorDLIBCNN: self.detector = dlib.cnn_face_detection_model_v1(cfg.DIR_MODELS_DLIB_CNN) os.environ['CUDA_VISIBLE_DEVICES'] = cuda_visible_devices # reset - def detect(self, im, size=None, conf_thresh=None, pyramids=None, largest=False): + def detect(self, im, size=None, conf_thresh=None, pyramids=None, largest=False, zone=None): bboxes = [] conf_thresh = self.conf_thresh if conf_thresh is None else conf_thresh pyramids = self.pyramids if pyramids is None else pyramids @@ -96,6 +96,10 @@ class DetectorDLIBCNN: bbox = BBox.from_dlib_dim(mmod_rect.rect, dim) bboxes.append(bbox) + if zone: + bboxes = [b for b in bboxes if b.cx > zone[0] and b.cx < 1.0 - zone[0] \ + and b.cy > zone[1] and b.cy < 1.0 - zone[1]] + if largest and len(bboxes) > 1: # only keep largest bboxes.sort(key=operator.attrgetter('area'), reverse=True) diff --git a/megapixels/app/processors/face_pose.py b/megapixels/app/processors/face_pose.py index f2548b32..96281637 100644 --- a/megapixels/app/processors/face_pose.py +++ b/megapixels/app/processors/face_pose.py @@ -18,12 +18,13 @@ class FacePoseDLIB: dnn_size = (400, 400) + pose_types = {'pitch': (0,0,255), 'roll': (255,0,0), 'yaw': (0,255,0)} def __init__(self): pass - def pose(self, landmarks, dim, project_points=False): + def pose(self, landmarks, dim): # computes pose using 6 / 68 points from dlib face landmarks # based on learnopencv.com and # https://github.com/jerryhouuu/Face-Yaw-Roll-Pitch-from-Pose-Estimation-using-OpenCV/ @@ -68,12 +69,17 @@ class FacePoseDLIB: result = {} # project points - if project_points: - pts_im, jac = cv.projectPoints(axis, rot_vec, tran_vec, cam_mat, dist_coeffs) - pts_model, jac2 = cv.projectPoints(model_points, rot_vec, tran_vec, cam_mat, dist_coeffs) - result['points_model'] = pts_model - result['points_image'] = pts_im - result['point_nose'] = tuple(landmarks[pose_points_idx[0]]) + #if project_points: + pts_im, jac = cv.projectPoints(axis, rot_vec, tran_vec, cam_mat, dist_coeffs) + pts_model, jac2 = cv.projectPoints(model_points, rot_vec, tran_vec, cam_mat, dist_coeffs) + #result['points_model'] = pts_model + #result['points_image'] = pts_im + result['points'] = { + 'pitch': pts_im[0], + 'roll': pts_im[2], + 'yaw': pts_im[1] + } + result['point_nose'] = tuple(landmarks[pose_points_idx[0]]) rvec_matrix = cv.Rodrigues(rot_vec)[0] @@ -84,21 +90,23 @@ class FacePoseDLIB: pitch = math.degrees(math.asin(math.sin(pitch))) roll = -math.degrees(math.asin(math.sin(roll))) yaw = math.degrees(math.asin(math.sin(yaw))) - degrees = {'pitch': pitch, 'roll': roll, 'yaw': yaw} - result['degrees'] = degrees + result['pitch'] = pitch + result['roll'] = roll + result['yaw'] = yaw return result - def draw_pose(self, im, pts_im, pts_model, pt_nose): - cv.line(im, pt_nose, tuple(pts_im[1].ravel()), (0,255,0), 3) #GREEN - cv.line(im, pt_nose, tuple(pts_im[0].ravel()), (255,0,), 3) #BLUE - cv.line(im, pt_nose, tuple(pts_im[2].ravel()), (0,0,255), 3) #RED + def draw_pose(self, im, pt_nose, image_pts): + cv.line(im, pt_nose, tuple(image_pts['pitch'].ravel()), self.pose_types['pitch'], 3) + cv.line(im, pt_nose, tuple(image_pts['yaw'].ravel()), self.pose_types['yaw'], 3) + cv.line(im, pt_nose, tuple(image_pts['roll'].ravel()), self.pose_types['roll'], 3) - def draw_degrees(self, im, degrees, color=(0,255,0)): - for i, item in enumerate(degrees.items()): - k, v = item + def draw_degrees(self, im, pose_data, color=(0,255,0)): + for i, pose_type in enumerate(self.pose_types.items()): + k, clr = pose_type + v = pose_data[k] t = '{}: {:.2f}'.format(k, v) origin = (10, 30 + (25 * i)) - cv.putText(im, t, origin, cv.FONT_HERSHEY_SIMPLEX, 0.5, color, thickness=2, lineType=2)
\ No newline at end of file + cv.putText(im, t, origin, cv.FONT_HERSHEY_SIMPLEX, 0.5, clr, thickness=2, lineType=2)
\ No newline at end of file diff --git a/megapixels/app/utils/im_utils.py b/megapixels/app/utils/im_utils.py index d5e92aa3..e882c67f 100644 --- a/megapixels/app/utils/im_utils.py +++ b/megapixels/app/utils/im_utils.py @@ -21,6 +21,12 @@ import datetime +def num_channels(im): + '''Returns number of channels in numpy.ndarray image''' + if len(im.shape) > 2: + return im.shape[2] + else: + return 1 def is_grayscale(im, threshold=5): """Returns True if image is grayscale |