Methods and apparatus to generate masked images based on selective privacy and/or location tracking
An example stationary tracker includes memory to store fixed geographic location information indicative of a fixed geographic location of the stationary tracker, and to store a reference feature image; and at least one processor to: determine a feature in an image is a non-displayable feature by comparing the feature to the reference feature image; and generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location of the stationary tracker, and the masked image to display a displayable feature in the image; and a wireless interface to detect a wireless tag located on a tag bearer, the at least one processor to determine the tag bearer is the displayable feature in the image based on the wireless tag.
1. A stationary tracker comprising:
memory to store fixed geographic location information indicative of a fixed geographic location of the stationary tracker, and to store a reference feature image; and
at least one processor to:
determine a feature in an image is a non-displayable feature by comparing the feature to the reference feature image; and
generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location of the stationary tracker, and the masked image to display a displayable feature in the image; and
a wireless interface to detect a wireless tag located on a tag bearer, the at least one processor to determine the tag bearer is the displayable feature in the image based on the wireless tag.
2. The stationary tracker of claim 1 , further including a first convolutional neural network to detect the non-displayable feature in the image.
3. The stationary tracker of claim 2 , further including a second convolutional neural network to detect the displayable feature in the image.
4. The stationary tracker of claim 1 , further including a camera to capture the image.
5. The stationary tracker of claim 1 , wherein the feature in the image is at least one of: (a) a face of a person, or (b) a vehicle.
6. The stationary tracker of claim 1 , further including a network interface to be in communication with a cloud service.
7. The stationary tracker of claim 6 , wherein the at least one processor is to determine the feature in the image is the non-displayable feature based on an instruction from the cloud service.
8. A stationary tracker comprising:
memory to store fixed geographic location information indicative of a fixed geographic location of the stationary tracker, and to store a reference feature image; and
programmable circuitry; and
instructions to cause the programmable circuitry to:
determine a feature in an image is a non-displayable feature based on: (a) an instruction from a cloud service, and (b) a comparison of the feature to the reference feature image; and
generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location of the stationary tracker, and the masked image to display a displayable feature in the image.
9. The stationary tracker of claim 8 , further including a first convolutional neural network to detect the non-displayable feature in the image.
10. The stationary tracker of claim 9 , further including a second convolutional neural network to detect the displayable feature in the image.
11. The stationary tracker of claim 8 , further including a camera to capture the image.
12. The stationary tracker of claim 8 , wherein the feature in the image is at least one of: (a) a face of a person, or (b) a vehicle.
13. The stationary tracker of claim 8 , further including a wireless interface to detect a wireless tag located on a tag bearer, the programmable circuitry to determine the tag bearer is the displayable feature in the image based on the wireless tag.
14. The stationary tracker of claim 13 , wherein the reference feature image is from the cloud service.
15. The stationary tracker of claim 8 , further including a network interface to be in communication with the cloud service.
16. A stationary tracker comprising:
means for storing to:
store geographic location information indicative of a fixed geographic location of the stationary tracker; and
store a reference feature image;
means for detecting a wireless tag located on a tag bearer; and
means for processing to, based on information from a cloud service:
determine a feature in an image is a non-displayable feature based on: (a) a comparison of the feature to the reference feature image, and (b) the geographic location information, wherein the non-displayable feature is not allowed to be displayed when captured from the fixed geographic location of the stationary tracker;
determine the tag bearer is a displayable feature in the image based on the wireless tag; and
generate a masked image, the masked image to mask the non-displayable feature, and the masked image to display the displayable feature in the image.
17. The stationary tracker of claim 16 , further including means for generating a probability value to detect the displayable feature in the image.
18. The stationary tracker of claim 16 , further including means for capturing the image.
19. The stationary tracker of claim 16 , wherein the feature in the image is at least one of: (a) a face of a person, or (b) a vehicle.
20. A non-transitory computer readable storage medium comprising computer readable instructions that, when executed, cause at least one processor to at least:
access an image captured by an image capture device of a stationary tracker, the stationary tracker located at a fixed geographic location;
access a reference feature image in a database, the reference feature image from a cloud service;
recognize a non-displayable feature in the image by comparing the non-displayable feature to the reference feature image; and
generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location, and the masked image to display a displayable feature in the image.
21. The non-transitory computer readable storage medium of claim 20 , wherein the instructions are to cause the at least one processor to execute a first convolutional neural network to detect the non-displayable feature in the image.
22. The non-transitory computer readable storage medium of claim 21 , wherein the instructions are to cause the at least one processor to execute a second convolutional neural network to detect the displayable feature in the image.
23. The non-transitory computer readable storage medium of claim 20 , wherein the non-displayable feature in the image is at least one of: (a) a face of a person, or (b) a vehicle.
24. The non-transitory computer readable storage medium of claim 20 , wherein the image capture device is a camera.
25. The non-transitory computer readable storage medium of claim 20 , wherein the instructions are to cause the at least one processor to execute a convolutional neural network to detect the non-displayable feature in the image before the at least one processor is to recognize the non-displayable feature.