PETS-Jason format(annots)

trainning:
len(dataset['images'])=1696     =number of images

len(dataset['annotations'])=23107 = number of detections

##====================================================================
k: categories
v:
[{'id': 1, 'name': 'pedestrian', 'supercategory': 'pedestrian'}]

##------------------------------------------------------------------------------------------------------- ##

k: annotations
v:

dataset['annotations'][0]

{'id': 11, 'area': 4558.0, 'iscrowd': 0, 'bbox': [719.0, 296.0, 43.0, 106.0], 'category_id': 1, 'image_id': 1}

##-------------------------------------------------------------------------------------------------------- ##
k: info
v: {'description': 'PETS training set: seqences S1*, S2L1, S3MF1', 'year': 1745, 'version': '1.0'}

##---------------------------------------------------------------------------------------------------------- ##
k: images
v:

dataset['images'][0]

{'id': 0, 'height': 768, 'file_name': '/BS/databases05/multi-people-tracking/PETS09-S1L1/Time_13-57/View_001/frame_0000.jpg', 'width': 576}