Im afraid I am no expert on AWS credentials, it is a puzzling topic
Anyone that got this setup, can you let me know how you set up the security in AWS?
Did you use the Access keys (access key ID and secret access key) from the home Security Credentials?
Did you create a new user and create specific access key for that user?
Did you add specific permissions, did you create a group with specific permissions?
Did you create HTTPS Git credentials for AWS CodeCommit?
Did you create SSH keys for AWS CodeCommit?
Is there any possibility to elaborate more on the automaton example, when using scan_interval: 10000? I am getting image recognition, if I am triggering the service from Developer Tools/Services, but I need to trigger it from automation of the camera.
I have example automationsin this article
@sleeepy2 you can just use your aws superuser profile. I did not create any additional users. I know this is not best practice
1 Like
FYI, if anyone was curious, I am stupid.
Don’t use capitals when setting secrets.
Got it working now.
@robmarkcole Thanks for your work.
1 Like
Latest release draws bounding boxes of detected objects, check it out!
1 Like
I’m getting this error when running the “Check Config” on hassio. Did the bounding boxes break this for hassio?
Platform error image_processing.amazon_rekognition - No module named 'homeassistant.util.pil'
Update HA to latest
I updated to the latest and added the save location to see the bounding box.
It saves the image but I don’t see any boxes anywhere…
I am I misunderstanding what it is supposed to show?
Boxes are added for the target object. If this is not happening please open an issue on the repo.
Sorry, my bad, it is working. The front end wasn’t updating correctly to show the correct picture.
Bounding boxes work great. This component is excellent. Thanks for the hard work @robmarkcole (and @ping-localhost)
1 Like
Is there a way to add a timestamp or something to the bounding box images? I would like to save them indefinitely so I can review the images and see what it was looking at when it detected/or didn’t detect something. I thought I did that when I tried tensorflow, but I can’t find anything.
In this repo we are doing something close, but saving the timestamp in the filename. To actually annotate the image with the timestamp is probably functionality I would want implemented in HA, probably in the pil utils. Suggest you open a feature request for that, and perhaps myself or other will pick it up
how do you set up multiple targets with this?
My mistake, it is deepstack object which supports multiple objects
@mathewtaylor2007 did you figure out how to get the list of detected objects? I can see them in the dev tools, but no idea how to get them out of there into a card or something.
Hi all, I have published a new release which fixes a bug and also adds a configurable save_timestamped_file option (CC @Bartem ), check it out
@kr_noob the list of objects is accessible from the entity attributes, I guess you would need a custom card to break them all out in a nice table
@mtweldon there is a feature request to configure multiple targets, I haven’t gotten around to it yet
3 Likes
@robmarkcole thanks for this job. Amazing. I have spends lot of hours playing with it. Just, awaiting the ‘multiple targets’ improvement, because setting multiple imaging_processing sensors doesn’t works properly (sometimes works one, and sometime otrhers ones). Probably by Amazon service limitation.
Edit: when they are triggering at same time (or near at least)
1 Like