VideoAnnotation¶

class VideoAnnotation[source]¶

Bases: object

VideoAnnotation for a single video. VideoAnnotation object is immutable.

Parameters

img_size : Tuple[int, int] or List[int, int]

Size of the image (height, width).

frames_count : int

Number of frames in VideoAnnotation.

objects : VideoObjectCollection, optional

VideoObjectCollection object.

frames : FrameCollection, optional

FrameCollection object.

tags : VideoTagCollection, optional

VideoTagCollection object.

description : str, optional

Video description.

key : UUID, optional

UUID object.

Raises

TypeError, if img_size is not tuple or list

Usage example

import supervisely as sly

# Simple VideoAnnotation example
height, width = 500, 700
frames_count = 10
video_ann = sly.VideoAnnotation((height, width), frames_count)
print(video_ann.to_json())
# Output: {
#     "size": {
#         "height": 500,
#         "width": 700
#     },
#     "description": "",
#     "key": "abef780b01ad4063b4b961ab2ba2f410",
#     "tags": [],
#     "objects": [],
#     "frames": [],
#     "framesCount": 10
# }

# More complex VideoAnnotation example

height, width = 500, 700
frames_count = 1
# VideoObjectCollection
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
# FrameCollection
fr_index = 7
geometry = sly.Rectangle(0, 0, 100, 100)
video_figure_car = sly.VideoFigure(video_obj_car, geometry, fr_index)
frame = sly.Frame(fr_index, figures=[video_figure_car])
frames = sly.FrameCollection([frame])
# VideoTagCollection
meta_car = sly.TagMeta('car_tag', sly.TagValueType.ANY_STRING)
from supervisely.video_annotation.video_tag import VideoTag
vid_tag = VideoTag(meta_car, value='acura')
from supervisely.video_annotation.video_tag_collection import VideoTagCollection
video_tags = VideoTagCollection([vid_tag])
# Description
descr = 'car example'

video_ann = sly.VideoAnnotation((height, width), frames_count, objects, frames, video_tags, descr)
print(video_ann.to_json())
# Output: {
#     "size": {
#         "height": 500,
#         "width": 700
#     },
#     "description": "car example",
#     "key": "a85b282e5e174e7ebad6f878b6919244",
#     "tags": [
#         {
#             "name": "car_tag",
#             "value": "acura",
#             "key": "540a8212b0344788953996cea220ea8b"
#         }
#     ],
#     "objects": [
#         {
#             "key": "7c74b8a495044ea0ac127f32751c8f5c",
#             "classTitle": "car",
#             "tags": []
#         }
#     ],
#     "frames": [
#         {
#             "index": 7,
#             "figures": [
#                 {
#                     "key": "82dcbf2e3c5f42a99eeea2ad34173793",
#                     "objectKey": "7c74b8a495044ea0ac127f32751c8f5c",
#                     "geometryType": "rectangle",
#                     "geometry": {
#                         "points": {
#                             "exterior": [
#                                 [
#                                     0,
#                                     0
#                                 ],
#                                 [
#                                     100,
#                                     100
#                                 ]
#                             ],
#                             "interior": []
#                         }
#                     }
#                 }
#             ]
#         }
#     ],
#     "framesCount": 1
# }

Methods

clone	Makes a copy of VideoAnnotation with new fields, if fields are given, otherwise it will use fields of the original VideoAnnotation.
from_json	Convert a json dict to VideoAnnotation.
is_empty	Check whether video annotation contains objects or tags, or not.
key	Annotation key value.
load_json_file	Loads json file and converts it to VideoAnnotation.
to_json	Convert the VideoAnnotation to a json dict.
validate_figures_bounds	Checks if image contains figures from all frames in collection.

Attributes

description	Video description.
figures	VideoAnnotation figures.
frames	VideoAnnotation frames.
frames_count	Number of frames.
img_size	Size of the image (height, width).
objects	VideoAnnotation objects.
tags	VideoAnnotation tags.

clone(img_size=None, frames_count=None, objects=None, frames=None, tags=None, description=None)[source]¶

Makes a copy of VideoAnnotation with new fields, if fields are given, otherwise it will use fields of the original VideoAnnotation.

Parameters

img_size : Tuple[int, int], optional

Size of the image (height, width).

frames_count : int, optional

Number of frames in VideoAnnotation.

objects : VideoObjectCollection, optional

VideoObjectCollection object.

frames : FrameCollection, optional

FrameCollection object.

tags : VideoTagCollection, optional

VideoTagCollection object.

description : str, optional

Video description.

Raises

TypeError, if img_size is not tuple or list

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
video_ann = sly.VideoAnnotation((height, width), frames_count)

obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
new_objects = sly.VideoObjectCollection([video_obj_car])
new_video_ann = video_ann.clone(objects=new_objects)
print(new_video_ann.to_json())
# Output: {
#     "size": {
#         "height": 500,
#         "width": 700
#     },
#     "description": "",
#     "key": "37f7d267864c4fd8b1a1a32f67e37f7d",
#     "tags": [],
#     "objects": [
#         {
#             "key": "27d4ba1aaee64930b2d0bfb7e8b53493",
#             "classTitle": "car",
#             "tags": []
#         }
#     ],
#     "frames": [],
#     "framesCount": 1
# }

Return type

VideoAnnotation

classmethod from_json(data, project_meta, key_id_map=None, skip_corrupted=False)[source]¶

Convert a json dict to VideoAnnotation. Read more about Supervisely format.

Parameters

data : dict

Dict in json format.

project_meta : ProjectMeta

Input ProjectMeta.

key_id_map : Union[KeyIdMap, None]

KeyIdMap object.

skip_corrupted : bool, optional

Skip corrupted items (currently only frames) during conversion.

Returns

VideoAnnotation object

Return type

VideoAnnotation

Usage example

import supervisely as sly

video_ann_json = {
    "size": {
        "height": 500,
        "width": 700
    },
    "tags": [],
    "objects": [],
    "frames": [],
    "framesCount": 1
}
key_id_map = sly.KeyIdMap()
meta = sly.ProjectMeta()

video_ann = sly.VideoAnnotation.from_json(video_ann_json, meta, key_id_map)

is_empty()[source]¶

Check whether video annotation contains objects or tags, or not.

Returns

True if video annotation is empty, False otherwise.

Return type

bool

Usage example

import supervisely as sly
from supervisely.video_annotation.key_id_map import KeyIdMap

address = 'https://app.supervise.ly/'
token = 'Your Supervisely API Token'
api = sly.Api(address, token)

project_id = 17208
video_id = 19371139
key_id_map = KeyIdMap()
meta_json = api.project.get_meta(project_id)
meta = sly.ProjectMeta.from_json(meta_json)

ann_json = api.video.annotation.download(video_id)
ann = sly.VideoAnnotation.from_json(ann_json, meta, key_id_map)

print(ann.is_empty()) # False

key()[source]¶

Annotation key value.

Returns

Key value of annotation object.

Return type

str

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
# VideoObjectCollection
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
video_ann = sly.VideoAnnotation((height, width), frames_count, objects)

print(video_ann.key())
# Output: 6e5bd622-4d7b-45ee-8bc5-807d5a5e2134

classmethod load_json_file(path, project_meta, key_id_map=None)[source]¶

Loads json file and converts it to VideoAnnotation.

Parameters

path : str

Path to the json file.

project_meta : ProjectMeta

Input ProjectMeta.

key_id_map : KeyIdMap, optional

KeyIdMap object.

Returns

VideoAnnotation object

Return type

VideoAnnotation

Usage example

import supervisely as sly

address = 'https://app.supervise.ly/'
token = 'Your Supervisely API Token'
api = sly.Api(address, token)

team_name = 'Vehicle Detection'
workspace_name = 'Cities'
project_name =  'London'

team = api.team.get_info_by_name(team_name)
workspace = api.workspace.get_info_by_name(team.id, workspace_name)
project = api.project.get_info_by_name(workspace.id, project_name)

meta_json = api.project.get_meta(project.id)
meta = sly.ProjectMeta.from_json(meta_json)


# Load json file
path = "/home/admin/work/docs/my_dataset/ann/annotation.json"
ann = sly.VideoAnnotation.load_json_file(path, meta)

to_json(key_id_map=None)[source]¶

Convert the VideoAnnotation to a json dict. Read more about Supervisely format.

Parameters

key_id_map : KeyIdMap, optional

KeyIdMap object.

Returns

Json format as a dict

Return type

dict

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 10
video_ann = sly.VideoAnnotation((height, width), frames_count)
print(video_ann.to_json())
# Output: {
#     "size": {
#         "height": 500,
#         "width": 700
#     },
#     "description": "",
#     "key": "abef780b01ad4063b4b961ab2ba2f410",
#     "tags": [],
#     "objects": [],
#     "frames": [],
#     "framesCount": 10
# }

validate_figures_bounds()[source]¶

Checks if image contains figures from all frames in collection.

Raises

OutOfImageBoundsException, if figure is out of image bounds

Returns

None

Return type

NoneType

Usage Example

import supervisely as sly

height, width = 50, 700
frames_count = 1
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
fr_index = 7
geometry = sly.Rectangle(0, 0, 100, 100)
video_figure_car = sly.VideoFigure(video_obj_car, geometry, fr_index)
frame = sly.Frame(fr_index, figures=[video_figure_car])
frames = sly.FrameCollection([frame])

video_ann = sly.VideoAnnotation((height, width), frames_count, objects, frames)
video_ann.validate_figures_bounds()
# raise OutOfImageBoundsException("Figure is out of image bounds")

property description¶

Video description.

Returns

Video description

Return type

str

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
descr = 'example'
video_ann = sly.VideoAnnotation((height, width), frames_count, description=descr)
print(video_ann.description) # example

property figures¶

VideoAnnotation figures.

Returns

List of VideoFigures from all frames in VideoAnnotation

Return type

List[VideoFigure]

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
fr_index = 7
geometry = sly.Rectangle(0, 0, 100, 100)
video_figure_car = sly.VideoFigure(video_obj_car, geometry, fr_index)
frame = sly.Frame(fr_index, figures=[video_figure_car])
frames = sly.FrameCollection([frame])

video_ann = sly.VideoAnnotation((height, width), frames_count, objects, frames)
print(len(video_ann.figures)) # 1

property frames¶

VideoAnnotation frames.

Returns

FrameCollection object

Return type

FrameCollection

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
fr_index = 7
geometry = sly.Rectangle(0, 0, 100, 100)
video_figure_car = sly.VideoFigure(video_obj_car, geometry, fr_index)
frame = sly.Frame(fr_index, figures=[video_figure_car])
frames = sly.FrameCollection([frame])

video_ann = sly.VideoAnnotation((height, width), frames_count, objects, frames)
print(video_ann.frames.to_json())
# Output: [
#     {
#         "index": 7,
#         "figures": [
#             {
#                 "key": "2842f561b1924f6abd6ab6f696ed9b65",
#                 "objectKey": "7f30fa9b78444ad69e02b37edbf9a902",
#                 "geometryType": "rectangle",
#                 "geometry": {
#                     "points": {
#                         "exterior": [
#                             [
#                                 0,
#                                 0
#                             ],
#                             [
#                                 100,
#                                 100
#                             ]
#                         ],
#                         "interior": []
#                     }
#                 }
#             }
#         ]
#     }
# ]

property frames_count¶

Number of frames.

Returns

Frames count

Return type

int

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 15
video_ann = sly.VideoAnnotation((height, width), frames_count)
print(video_ann.frames_count)
# Output: 15

property img_size¶

Size of the image (height, width).

Returns

Image size

Return type

Tuple[int, int]

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
video_ann = sly.VideoAnnotation((height, width), frames_count)
print(video_ann.img_size)
# Output: (500, 700)

property objects¶

VideoAnnotation objects.

Returns

VideoObjectCollection object

Return type

VideoObjectCollection

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
# VideoObjectCollection
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
video_ann = sly.VideoAnnotation((height, width), frames_count, objects)
print(video_ann.objects.to_json())
# Output: [
#     {
#         "key": "79fc07a4a6ca4b2796279bc033b9ec9a",
#         "classTitle": "car",
#         "tags": []
#     }
# ]

property tags¶

VideoAnnotation tags.

Returns

VideoTagCollection object

Return type

VideoTagCollection

Usage example

import supervisely as sly

height, width = 500, 700
frames_count = 1
obj_class_car = sly.ObjClass('car', sly.Rectangle)
video_obj_car = sly.VideoObject(obj_class_car)
objects = sly.VideoObjectCollection([video_obj_car])
fr_index = 7
geometry = sly.Rectangle(0, 0, 100, 100)
video_figure_car = sly.VideoFigure(video_obj_car, geometry, fr_index)
frame = sly.Frame(fr_index, figures=[video_figure_car])
frames = sly.FrameCollection([frame])
meta_car = sly.TagMeta('car_tag', sly.TagValueType.ANY_STRING)
from supervisely.video_annotation.video_tag import VideoTag
vid_tag = VideoTag(meta_car, value='acura')
from supervisely.video_annotation.video_tag_collection import VideoTagCollection
tags = VideoTagCollection([vid_tag])

video_ann = sly.VideoAnnotation((height, width), frames_count, objects, frames, tags)
print(video_ann.tags.to_json())
# Output: [
#     {
#         "name": "car_tag",
#         "value": "acura",
#         "key": "c63e8259589a4fa5b4fb15a48c1f6a63"
#     }
# ]