def filter_duplicate_candidates(self, data, image):
Params.box_size_factor = 0.5
Params.min_box_size = 5
Params.ellipsoid_thresh = 0.5
Params.min_k = 0
# TODO time optimization: split into initial clusters using gaussian information rather than heatmap contours
heat_map = numpy.zeros(shape=[image.shape[0], image.shape[1], 1], dtype=numpy.float64)
#检测出的框缩小后，按照iou分数求按照高斯分布的热图
original_detection_centers = self.shrink_boxes(data, heat_map)
cv2.normalize(heat_map, heat_map, 0, 255, cv2.NORM_MINMAX)
heat_map = cv2.convertScaleAbs(heat_map)
h2, heat_map = cv2.threshold(heat_map, 4, 255, cv2.THRESH_TOZERO)
#得到热图的轮廓
contours = cv2.findContours(numpy.ndarray.copy(heat_map), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
candidates = self.find_new_candidates(contours, heat_map, data, original_detection_centers, image)
candidates = self.map_original_boxes_to_new_boxes(candidates, original_detection_centers)
# TODO time optimization: parallelize contours/clusters resolvers.
# TODO time optimization: convert numpy to tensorflow/keras
best_detection_ids = {}
filtered_data = pandas.DataFrame(columns=data.columns)
for i, candidate in candidates.items():
label = candidate['original_detection_ids']
original_detections = data.ix[label]
original_detections[
'avg_score'] = 0.5 * original_detections.confidence + 0.5 * original_detections.hard_score
best_detection_id = original_detections.avg_score.argmax()
# best_detection_id = original_detections.confidence.argmax()
# best_detection_id = original_detections.hard_score.argmax()
best_detection = original_detections.ix[best_detection_id].copy()
# The following code creates the median bboxes
# original_detections = original_detections[original_detections.confidence > 0.5]
# if original_detections.shape[0] > 0:
# w = original_detections['x2'] - original_detections['x1']
# h = original_detections['y2'] - original_detections['y1']
# x = original_detections['x1'] + 0.5 * w
# y = original_detections['y1'] + 0.5 * h
#
# med_x = int(round(scipy.percentile(x, 50)))
# med_y = int(round(scipy.percentile(y, 50)))
# med_w = int(round(scipy.percentile(w, 50)))
# med_h = int(round(scipy.percentile(h, 50)))
# best_detection['x1'] = med_x - med_w / 2
# best_detection['y1'] = med_y - med_h / 2
# best_detection['x2'] = med_x + med_w / 2
# best_detection['y2'] = med_y + med_h / 2
best_detection_ids[best_detection_id] = best_detection
filtered_data = filtered_data.append(best_detection)
# to handle overlap between contour bboxes
filtered_data = perform_nms_on_image_dataframe(filtered_data, 0.3)
return filtered_data
def perform_nms(self, candidates, contour_i, curr_data):
nms_data = perform_nms_on_image_dataframe(curr_data, 0.3)
for sub_ind, row in nms_data.iterrows():
curr_box = numpy.asarray([row['x1'], row['y1'], row['x2'], row['y2']])
box_width = curr_box[BOX.X2] - curr_box[BOX.X1]
box_height = curr_box[BOX.Y2] - curr_box[BOX.Y1]
if box_width > Params.min_box_size and box_height > Params.min_box_size:
candidates.append({'box': curr_box, 'original_detection_ids': []})
