Object detection with Amazon Rekognition

Share your Projects! Custom Integrations
75

You have configured target: Baby ?

76

Hi Rob,
Yes, exactly the same config as I did for person but with Baby as target:

  - platform: amazon_rekognition
    aws_access_key_id: xxx
    aws_secret_access_key: zzz
    region_name: eu-west-1 # optional region, default us-east-1
    target: Baby # Optional target object, default Person
    source:
      - entity_id: camera.nurserycam
77

I think there might be a bug on the image processing integration. Can you disable your person detector, leaving only the baby detector, and see if it works then?

78

Hey @robmarkcole I thought that would fix it but strangely it did not, I still get this

image
image1410×290 25 KB

79

That is strange, no idea

80

I guess I can work around it by just getting a list of the detected objects and ignore the state value. Has anyone done this?

81

Need some help with this please. I am not sure what I am missing. I get this error.
“An error occurred (UnrecognizedClientException) when calling the DetectLabels operation: The security token included in the request is invalid.”

configuration.yaml looks like this.

image_processing:
  - platform: amazon_rekognition
    aws_access_key_id: AWS_ACCESS_KEY_ID
    aws_secret_access_key: AWS_SECRET_ACCESS_KEY
    target: Car # Optional target object, default Person
    source:
      - entity_id: camera.front_door

To get the aws id and secret I logged into aws and go to the IAM dashboard. Added a user and added them to a group that has the AmazonRekognitionFullAccess and AmazonRekognitionServiceRole policeies. Then in that user on the Security credentials I created an access key. I use that access key id for the AWS_ACCESS_KEY_ID and key that gets generated from that as the AWS_SECRET_ACCESS_KEY.

I am obviously missing something. Can some one point me in the correct direction.

Thanks

82

Im afraid I am no expert on AWS credentials, it is a puzzling topic

83

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?

84

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.

85

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
86

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
87

Latest release draws bounding boxes of detected objects, check it out!

1 Like
88

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'
89

Update HA to latest

90

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?

91

Boxes are added for the target object. If this is not happening please open an issue on the repo.

92

Sorry, my bad, it is working. The front end wasn’t updating correctly to show the correct picture.

93

Bounding boxes work great. This component is excellent. Thanks for the hard work @robmarkcole (and @ping-localhost)

1 Like
94

Great work @robmarkcole!

1 Like