Dynamic camera presets
A method implementing dynamic camera presets. An image is received. A list of bounding boxes and a list of classification values are generated from the image. A set of tags, for the image, are generated from the list of bounding boxes and the list of classification values. A tagged image incorporating the set of tags into the image is presented. In response to a user input, a tag selection identifying a tag of the set of tags is received. View settings are adjusted to focus on a bounding box, from the list of bounding boxes, corresponding to the tag selection. An adjusted image is presented using the view settings.
1. A computer implemented method comprising:
receiving an image;
generating, from the image, a list of bounding boxes and a list of classification values;
generating a set of tags, for the image, from the list of bounding boxes and the list of classification values;
presenting a tagged image comprising a tag from the set of tags overlayed onto the image;
receiving, in response to a user input, a tag selection identifying a tag of the set of tags;
adjusting view settings to focus on a bounding box, from the list of bounding boxes, corresponding to the tag selection; and
presenting an adjusted image using the view settings.
2. The computer implemented method of claim 1 , further comprising:
receiving the image as part of a real time stream from a camera; and
presenting the adjusted image as part of an adjusted stream.
3. The computer implemented method of claim 1 , further comprising:
presenting a tagged stream, comprising the tagged image, to a control device; and
presenting an adjusted stream, comprising the adjusted image, to a display device.
4. The computer implemented method of claim 1 , further comprising:
receiving sound source location data, wherein the sound source location data identifies a horizontal location in the image corresponding to a sound source.
5. The computer implemented method of claim 1 , further comprising:
updating a name of the tag from the set of tags using sound source location data.
6. The computer implemented method of claim 1 , further comprising:
combining at least two bounding boxes from the list of bounding boxes using a distance between the at least two bounding boxes and at least two classification values from the list of classification values.
7. The computer implemented method of claim 1 , further comprising:
combining at least two bounding boxes from the list of bounding boxes by determining an overlap between at least two bounding boxes.
8. The computer implemented method of claim 1 , further comprising:
combining at least two bounding boxes from the list of bounding boxes by prioritizing the at least two bounding boxes.
9. The computer implemented method of claim 1 , further comprising:
combining at least two bounding boxes from the list of bounding boxes by forming a combined box from the at least two bounding boxes.
10. The computer implemented method of claim 1 , wherein the tag, from the set of tags, corresponds to the bounding box, from the list of bounding boxes, in a one to one relationship.
11. The computer implemented method of claim 1 , wherein the bounding box, from the list of bounding boxes, comprises a set of coordinates that define a portion of the image within which an object in the image was detected.
12. The computer implemented method of claim 1 , wherein a classification value, from the list of classification values, identifies a classification for an object detected in the image.
13. The computer implemented method of claim 1 , further comprising:
generating, from the image, a list of confidence scores, wherein a confidence score, from the list of confidence scores, identifies an accuracy of a classification value, from the list of classification values, of an object detected in the image.
14. A system comprising:
a computing system; and
an application, executing on the computing system, configured for:
receiving an image;
generating, from the image, a list of bounding boxes and a list of classification values;
generating a set of tags, for the image, from the list of bounding boxes and the list of classification values;
presenting a tagged image comprising a tag from the set of tags overlayed onto the image;
receiving, in response to a user input, a tag selection identifying a tag of the set of tags;
adjusting view settings to focus on a bounding box, from the list of bounding boxes, corresponding to the tag selection; and
presenting an adjusted image using the view settings.
15. The system of claim 14 , wherein the application is further configured for:
receiving the image as part of a real time stream from a camera; and
presenting the adjusted image as part of an adjusted stream.
16. The system of claim 14 , wherein the application is further configured for:
presenting a tagged stream, comprising the tagged image, to a control device; and
presenting an adjusted stream, comprising the adjusted image, to a display device.
17. The system of claim 14 , wherein the application is further configured for:
receiving sound source location data, wherein the sound source location data identifies a horizontal location in the image corresponding to a sound source.
18. The system of claim 14 , wherein the application is further configured for:
updating a name of the tag from the set of tags using sound source location data.
19. The system of claim 14 , wherein the application is further configured for:
combining at least two bounding boxes from the list of bounding boxes using a distance between the at least two bounding boxes and at least two classification values from the list of classification values.
20. A system comprising:
a control device;
a display device;
a computing system connected to the control device and the display device; and
an application, executing on the computing system, configured for:
receiving an image;
generating, from the image, a list of bounding boxes and a list of classification values;
generating a set of tags, for the image, from the list of bounding boxes and the list of classification values;
presenting, to the control device, a tagged image comprising a tag from the set of tags overlayed onto the image;
receiving, in response to a user input, a tag selection identifying a tag of the set of tags;
adjusting view settings to focus on a bounding box, from the list of bounding boxes, corresponding to the tag selection; and
presenting, to the display device, an adjusted image using the view settings.