def crop_sample(sample, contextFactor=2):
"""
Given a sample image with bounding box, this method returns the image crop
at the bounding box location with twice the width and height for context.
"""
output_sample = {}
opts = {}
image, bb = sample['image'], sample['bb']
orig_bbox = BoundingBox(bb[0], bb[1], bb[2], bb[3])
orig_bbox.kContextFactor = contextFactor
(output_image, pad_image_location, edge_spacing_x,
edge_spacing_y) = cropPadImage(orig_bbox, image)
new_bbox = BoundingBox(0, 0, 0, 0)
new_bbox.kContextFactor = contextFactor
new_bbox = new_bbox.recenter(pad_image_location, edge_spacing_x,
edge_spacing_y, new_bbox)
output_sample['image'] = output_image
output_sample['bb'] = new_bbox.get_bb_list()
# additional options for visualization
opts['edge_spacing_x'] = edge_spacing_x
opts['edge_spacing_y'] = edge_spacing_y
opts['search_location'] = pad_image_location
opts['search_region'] = output_image
return output_sample, opts
def shift_crop_training_sample(sample, bb_params):
"""
Given an image with bounding box, this method randomly shifts the box and
generates a training example. It returns current image crop with shifted
box (with respect to current image).
"""
output_sample = {}
opts = {}
currimg = sample['image']
currimg_x2 = sample['image']
currbb = sample['bb']
bbox_curr_gt = BoundingBox(currbb[0], currbb[1], currbb[2], currbb[3])
bbox_curr_shift = BoundingBox(0, 0, 0, 0)
bbox_curr_shift = bbox_curr_gt.shift(currimg,
bb_params['lambda_scale_frac'],
bb_params['lambda_shift_frac'],
bb_params['min_scale'],
bb_params['max_scale'], True,
bbox_curr_shift)
(rand_search_region, rand_search_location, edge_spacing_x,
edge_spacing_y) = cropPadImage(bbox_curr_shift, currimg)
bbox_curr_shift.kContextFactor = 4
(rand_search_region_x2, rand_search_location_x2, edge_spacing_x_x2,
edge_spacing_y_x2) = cropPadImage(bbox_curr_shift, currimg_x2)
bbox_curr_shift.kContextFactor = 2
bbox_curr_gt = BoundingBox(currbb[0], currbb[1], currbb[2], currbb[3])
bbox_gt_recentered = BoundingBox(0, 0, 0, 0)
bbox_gt_recentered = bbox_curr_gt.recenter(rand_search_location,
edge_spacing_x, edge_spacing_y,
bbox_gt_recentered)
output_sample['image'] = rand_search_region
output_sample['image_x2'] = rand_search_region_x2
output_sample['bb'] = bbox_gt_recentered.get_bb_list()
# additional options for visualization
opts['edge_spacing_x'] = edge_spacing_x
opts['edge_spacing_y'] = edge_spacing_y
opts['search_location'] = rand_search_location
opts['search_region'] = rand_search_region
return output_sample, opts