Customized Object Detection MV72X

[CSMax]

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!

[PhilipDAth · Accepted solution]

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]

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