Customized Object Detection MV72X

SOLVED
CSMax
Conversationalist

Customized Object Detection MV72X

Hi, my company is using MV72X and I like to know if we can deploy a customized deep learning model (other objects), other than the built-in people and object detection. 

 

Thanks!

1 ACCEPTED SOLUTION
PhilipDAth
Kind of a big deal
Kind of a big deal

No.  I've made this feature request before.  I don't think the security teams would allow it either.

 

You can use MQTT and the snapshot API to trigger when it sees motion, retrieve a snapshot, and then process that.  This can be done from the cloud.

https://developer.cisco.com/meraki/mv-sense/#!mqtt 

https://developer.cisco.com/meraki/api-v1/#!generate-device-camera-snapshot 

 

You can use the RTSP interface and process on-premise (I guess you could stream to the cloud if you didn't mind the bandwidth consumption).

https://documentation.meraki.com/MV/Advanced_Configuration/External_RTSP 

View solution in original post

2 REPLIES 2
PhilipDAth
Kind of a big deal
Kind of a big deal

No.  I've made this feature request before.  I don't think the security teams would allow it either.

 

You can use MQTT and the snapshot API to trigger when it sees motion, retrieve a snapshot, and then process that.  This can be done from the cloud.

https://developer.cisco.com/meraki/mv-sense/#!mqtt 

https://developer.cisco.com/meraki/api-v1/#!generate-device-camera-snapshot 

 

You can use the RTSP interface and process on-premise (I guess you could stream to the cloud if you didn't mind the bandwidth consumption).

https://documentation.meraki.com/MV/Advanced_Configuration/External_RTSP 

CSMax
Conversationalist

Thanks for the reply @PhilipDAth. And it makes sense from the security point of view. 

Get notified when there are additional replies to this discussion.
Welcome to the Meraki Community!
To start contributing, simply sign in with your Cisco account. If you don't yet have a Cisco account, you can sign up.