AXIS Audio Analytics - User manual

AXIS Audio Analytics detects sudden increases in sound volume and specific types of sounds such as screams or shouts within range of the device it’s installed on. These detections can be configured to trigger a response, such as recording video, playing an audio message, or alerting security staff.

Consider the following when setting up a device that will use AXIS Audio Analytics:

• The application is optimized to detect sounds up to a distance of 10 meters from the device it’s installed on.

• A high level of background noise in busy environments and heavy traffic can impact performance.

• Avoid placing the microphone next to a source of direct noise, such as a fan.

For product-specific considerations, see the user manual for your product at help.axis.com.

1. Log in to the device interface as an administrator and go to Analytics > Audio analytics.

2. Turn on Adaptive audio detection if you want the device to monitor the sound level in its immediate vicinity and detect sudden increases in sound volume.

3. 1. In Adaptive audio detection > Advanced settings, you can move the Threshold slider to raise or lower the detection threshold. Only sounds that pass the threshold trigger a detection.

   2. In Adaptive audio detection > Test alarms, click Test to trigger a detection. Use this to check whether you have set up your rules for events correctly.

4. Note

   The Threshold slider allows you to adjust how significant an increase in sound volume is required to trigger a detection. Adjust the slider according to where the device is installed and what the device is intended to detect.

5. Turn on Audio classification if you want to detect specific types of sounds, such as screams or shouts, in the device’s immediate vicinity.

6. 1. In Audio classification > Advanced settings, choose what types of sounds you want the device to detect.

   2. In Audio classification > Test alarms, select an option from the drop-down list and click Test to trigger a detection. Use this to check whether you have set up your rules for events correctly.

7. Note

   Adaptive audio detection and Audio classification work independently of each other. If you only need one of the two features, you can leave the other turned off.

To learn more, check out our guide Get started with rules for events.

This example explains how to set up the Axis device to record video to an SD card as soon as a sound triggers a detection.

1. In the device’s web interface, go to Analytics > Audio analytics and make sure that Adaptive audio detection is on.

2. To check that the SD card is mounted, go to System > Storage.

3. Go to System > Events and add a rule.

4. Enter a name for the rule.

5. In the list of conditions, under Audio analytics, select Audio level above threshold.

6. In the list of actions, under Recordings, select Record video.

7. In the list of storage options, select SD-DISK.

8. Select a Camera and a Stream profile.

9. If you want to start the recording before the sound was detected, enter a Prebuffer time.

10. Click Save.

11. To test the rule, go to Analytics > Audio analytics. In Adaptive audio detection > Advanced settings, click Test alarms to generate a false detection event.

You can use an Axis strobe siren to let intruders know that the area is under surveillance.

This example explains how to activate a profile in the strobe siren whenever AXIS Audio Analytics detects a sudden increase in sound volume.

Before you start:

• Create a new user with the role Operator or Administrator in the strobe siren.

• Create a profile in the strobe siren called: “Strobe siren profile”.

• In the device’s web interface, go to Analytics > Audio analytics and make sure that Adaptive audio detection is on.

Create a recipient in the camera:

1. In the camera’s device interface, go to System > Events > Recipients and add a recipient.

2. Enter the following information:

3. • Name: Strobe siren

   • Type: HTTP

   • URL: http://<IPaddress>/axis-cgi/siren_and_light.cgi

     Replace <IPaddress> with the address of the strobe siren.

   • The Account name and password of the newly created strobe siren user.

4. Click Test to make sure all data is valid.

5. Click Save.

Create two rules in the camera:

1. Go to Rules and add a rule to activate the strobe siren once AXIS Audio Analytics makes a detection.

2. Enter the following information:

3. • Name: Activate strobe siren on detection

   • Condition: Audio analytics > Audio level above threshold

   • Action: Notifications > Send notification through HTTP

   • Recipient: Strobe siren.

     The information must be the same as you previously entered under Events > Recipients > Name.

   • Method: Post

   • Body: 

   {
       "apiVersion": "1.0",
       "method": "start",
       "params": {
           "profile" : "Strobe siren profile"
       }
   }

4. Make sure to enter the same information under ‘"profile" : <>’ as you did when you created the profile in the strobe siren, in this case: “Strobe siren profile”.

5. Click Save.

6. Add another rule to deactivate the strobe siren after 15 seconds. Enter with the following information:

7. • Name: Deactivate strobe siren 15s after detection

   • Wait between actions: 00:00:15

   • Condition: Audio analytics > Audio level above threshold

   • Select Invert this condition.

   • Action: Notifications > Send notification through HTTP

   • Recipient: Strobe siren

     The information must be the same as you previously entered under Events > Recipients > Name.

   • Method: Post

   • Body:

{
    "apiVersion": "1.0",
    "method": "stop",
    "params": {
        "profile" : "Strobe siren profile"
    }
}

8. Make sure to enter the same information under ‘"profile" : <>’ as you did when you created the profile in the strobe siren, in this case: “Strobe siren profile”.

9. Click Save.

This example explains how to set up the Axis device to record video to an SD card as soon as both the following conditions are met:

• AXIS Object Analytics detects a person.

• AXIS Audio Analytics detects a shout.

1. In the device’s web interface, go to Analytics > Audio analytics and make sure that Adaptive audio detection is on.

2. In the device’s web interface, go to Apps and make sure that Axis Object Analytics is on.

3. To check that the SD card is mounted, go to System > Storage.

4. In AXIS Object Analytics, click + New scenario.

5. Select Object in area and click Next.

6. Select Human and click Next.

7. Adjust the area of interest if necessary.

8. Click Finish.

9. Back in the device interface, go to System > Events and add a rule.

10. Enter a name for the rule.

11. For the first condition, select Shout detected under Audio analytics.

12. Add a second condition and select the AXIS Object Analytics scenario you created under Applications.

13. In the list of actions, under Recordings, select Record video.

14. In the list of storage options, select SD-DISK.

15. Select a Camera and a Stream profile.

16. If you want to start the recording before the sound was detected, enter a Prebuffer time.

17. Click Save.

The application is currently able to classify two types of distinct sounds from an audio stream: screams and shouts.

• A scream is characterized by a loud and high-pitched vocalization, often elicited to express fear or pain.

• A shout is characterized by a person speaking in a loud voice, often elicited in anger or to attract attention.

If the application is configured to detect either of these sounds, it will represent them as blue or red lines in the user interface. The output of the detection will consist of metadata.

For privacy considerations, audio streaming is turned off by default on all Axis devices. You do not need to enable audio streaming to use AXIS Audio Analytics, as the application can still visualize and generate metadata about captured audio without storing it anywhere.

This means that you only have to enable audio streaming if you want to configure the application to process and encode captured audio for storage.

Example

1. An Axis device with a microphone picks up the sound of a man shouting at someone.
2. Audio streaming is disabled on this device, which means that the man’s shouting is not recorded.
3. AXIS Audio Analytics detects a shout.
4. AXIS Audio Analytics generates metadata and an event associated with the shout.
5. A security staff member receives an alert about someone shouting, but no recording from the event.

This example explains how to set up a rule in AXIS Camera Station to alert the operator and record video when AXIS Audio Analytics detects a scream.

Before you start

• You need:

• an Axis network camera with AXIS Audio Analytics set up and running, see Get started

• a computer with AXIS Camera Station installed

1. Add the camera to AXIS Camera Station

2. In AXIS Camera Station, add the camera. See the user manual for AXIS Camera Station.

1. Create a device event trigger

2. Click and go to Configuration > Recording and events > Action rules and click New.

3. Click Add to add a trigger.

4. Select Device event from the list of triggers and click Ok.

5. In the Configure device event trigger section:

6. • In Device, select the camera.

   • In Event, select Scream detected from the options for AXIS Audio Analytics

   • In Trigger period, set an interval time between two successive triggers. Use this function to reduce the number of successive recordings. If an additional trigger occurs within this interval, the recording will continue and the trigger period starts over from that point in time.

7. In Filters, set active to Yes.

8. Click Ok.

1. Create actions to raise alarms and record video

2. Click Next.

3. Click Add to add an action.

4. Select Raise alarm from the list of actions and click Ok.

5. Note

   The alarm message is what the operator sees when an alarm is raised.

6. In the Alarm message section, enter an alarm title and description.

7. Click Ok.

8. Click Add to add another action.

9. Select Record from the list of actions and click Ok.

10. In the list of cameras, select the camera to use for recording.

11. Select a profile and set the prebuffer and postbuffer.

12. Click Ok.

1. Specify when the alarm is active

2. Click Next.

3. If you only want the alarm to be active during certain hours, select Custom schedule.

4. Select a schedule from the list.

5. Click Next.

6. Enter a name for the rule.

7. Click Finish.