Applications - Detections

The Application Detections endpoint returns the latest assertions on media from either a user or the application's current best model.

Application Detection Objects

Subject-Media Assertion Object

Retrieving Application Detections

The following query parameters are supported:

GET /1/applications/{application_id}/detections
Host: https://api.cogniac.io

Example: Retrieve Application Detections

curl -X GET https://api.cogniac.io/1/applications/di71rG94/detections?limit=10&reverse=true \
-H "Authorization: Bearer abcdefg.hijklmnop.qrstuvwxyz"

import cogniac

# connect to the tenant
cc = cogniac.CogniacConnection(username="test@cogniac.co", 
                               password="myPassword", 
                               tenant_id="63QhzFLc9tg4")

# get the app object
my_app = cc.get_application('di71rG94')

# the detections method returns an iterator of app detections
detections = app.detections(limit=10, reverse=True)
for d in detections:
  print d

import cogniac
from pprint import pprint

app_id = '0Am1V3kr'
# connect to the tenant
cc = cogniac.CogniacConnection(username="test@cogniac.co", 
                               password="abcdefghijk", 
                               tenant_id="skjdfh853k4jt")

# get the app object
my_app = cc.get_application(app_id)

# the detections method returns an iterator of app detections
detections = my_app.detections(limit=1, reverse=True)
for detection in detections:
  pprint(detection)

{
  "data": [
   {'detections': [{'app_data': None,
                 'app_data_type': None,
                 'app_id': 'yii3tm2g',
                 'assertion_prefix': 'RPSuDaRJOX5wi998cVxAmI9',
                 'created_at': 1693951026.527223,
                 'detection_id': 'RPSuDaRJOX5wi998cVxAmI9:0',
                 'focus': None,
                 'media_id': '2C9OUC8BEXURYEFMABYHGSWEUBIM',
                 'model_id': 'InitialModel_yii3tm2g_OxxbyP.tgz',
                 'model_image_id': 'InitialModel_yii3tm2g_OxxbyP.tgz:5431c7e',
                 'origin': None,
                 'prev_prob': 0.5000034855833563,
                 'probability': 0.5000034855833563,
                 'subject_uid': 'dog5333_6ggqjf',
                 'uncal_prob': 1.0,
                 'user_id': None}],
 'focus': None,
 'force_feedback': True,
 'force_review': False,
 'media': {'author': None,
           'author_profile_url': None,
           'bits_per_pixel': 8,
           'created_at': 1693950644.539737,
           'domain_unit': '39eece0dd462c4bd9545b995222046b4',
           'duration': None,
           'external_media_id': None,
           'filename': '174d2108eea9b488.jpg',
           'fps': None,
           'frame': None,
           'frame_durations': [],
           'frame_preview_map': {},
           'image_height': 737,
           'image_width': 1024,
           'license': None,
           'md5': '39eece0dd462c4bd9545b995222046b4',
           'media_format': 'JPEG',
           'media_id': '2C9OUC8BEXURYEFMABYHGSWEUBIM',
           'media_src': 'web_app',
           'media_timestamp': 1671569480.424,
           'media_url': 'https://api.cogniac.io/1/media/download/2C9OUC8BEXURYEFMABYHGSWEUBIM/2C9OUC8BEXURYEFMABYHGSWEUBIM',
           'meta_tags': None,
           'network_camera_id': None,
           'num_channels': 3,
           'num_frames': None,
           'original_landing_url': None,
           'original_url': None,
           'parent_media_id': None,
           'parent_media_ids': [],
           'preview_url': None,
           'resize_urls': {'454': 'https://api.cogniac.io/1/media/download/2C9OUC8BEXURYEFMABYHGSWEUBIM/2C9OUC8BEXURYEFMABYHGSWEUBIM_max_454'},
           'sequence_ix': None,
           'set_assignment': 'validation',
           'size': 172109.0,
           'source_url': None,
           'status': 'success',
           'tenant_id': 'd16jdqt1h71f',
           'time_base': None,
           'title': None,
           'trigger_id': None,
           'uploaded_by_user': 'user@cogniac.co',
           'video': False,
           'video_context': None},
 'media_list': [{'author': None,
                 'author_profile_url': None,
                 'bits_per_pixel': 8,
                 'created_at': 1693950644.539737,
                 'domain_unit': '39eece0dd462c4bd9545b995222046b4',
                 'duration': None,
                 'external_media_id': None,
                 'filename': '174d2108eea9b488.jpg',
                 'fps': None,
                 'frame': None,
                 'frame_durations': [],
                 'frame_preview_map': {},
                 'image_height': 737,
                 'image_width': 1024,
                 'license': None,
                 'md5': '39eece0dd462c4bd9545b995222046b4',
                 'media_format': 'JPEG',
                 'media_id': '2C9OUC8BEXURYEFMABYHGSWEUBIM',
                 'media_src': 'web_app',
                 'media_timestamp': 1671569480.424,
                 'media_url': 'https://api.cogniac.io/1/media/download/2C9OUC8BEXURYEFMABYHGSWEUBIM/2C9OUC8BEXURYEFMABYHGSWEUBIM',
                 'meta_tags': None,
                 'network_camera_id': None,
                 'num_channels': 3,
                 'num_frames': None,
                 'original_landing_url': None,
                 'original_url': None,
                 'parent_media_id': None,
                 'parent_media_ids': [],
                 'preview_url': None,
                 'resize_urls': {'454': 'https://api.cogniac.io/1/media/download/2C9OUC8BEXURYEFMABYHGSWEUBIM/2C9OUC8BEXURYEFMABYHGSWEUBIM_max_454'},
                 'sequence_ix': None,
                 'set_assignment': 'validation',
                 'size': 172109.0,
                 'source_url': None,
                 'status': 'success',
                 'tenant_id': 'd16jdqt1h71f',
                 'time_base': None,
                 'title': None,
                 'trigger_id': None,
                 'uploaded_by_user': 'user@cogniac.co',
                 'video': False,
                 'video_context': None}],
 'other_media': [],
 'updated_at': 1693951026.527223}

Detection Post URLs

In addition to polling for recent Application detections, you can also specify callback URLs to receive postback detections in realtime as they occur. Please enter your listening URL's in the detection_post_urls field of the Application object, for example "detection_post_urls":["http://127.0.0.1:9999/my_model_output.net", "https://product_model_detections.co"].

Posts are retried for thirty seconds, but URL's that fail retried posts after thirty seconds are blacklisted for five minutes.

The detection callback post will will only be sent if a subject probability is over the configured detection threshold (0.5 by default).

{
    "media": {"media_id": "dfc37db6723376ab953b10cd40097a68"
            "parent_media_ids": ['c8ee0f4f05f3fdcf36f69a3fd81fd84f'],
           },
  "focus":{
        "box": {"x0": 50, "x1": 275, "y0": 634, "y1": 870}
      },
  "subjects":[
    {
      "subject_uid":"dog",
      "probability":0.79,
      "updated_at": 1481857269.646634
      
    },
    {
      "subject_uid":"cat",
      "probability":0.49,
      "updated_at": 1481857269.646634      
    }  
  ]
}