Bounding box doubling as redaction boundary
Methods, systems, and techniques for redacted video exports are disclosed. Consistent with example embodiments, a bounding box may double as a redaction boundary.
1. A method comprising:
persistently storing surveillance video in an unredacted format within a system;
accessing, from within the system, the surveillance video and metadata defining a plurality of moving bounding boxes that:
designate a respective plurality of identified foreground objects within the surveillance video; and
follow movement thereof; and
generating, from the surveillance video, at least one redacted video clip formatted to include at least a subset of the moving bounding boxes, the subset of the moving bounding boxes overlaying video image frames of the redacted video clip, each bounding box of the subset delineating a boundary inside of which a revealed object area and outside of which an outside area appear in the redacted video clip as an unredacted part and a redacted part respectively.
2. The method of claim 1 wherein the moving bounding boxes are rectangular in shape.
3. The method of claim 2 wherein dimensions of each of the moving bounding boxes vary as a function of time.
4. The method of claim 1 further comprising transmitting the redacted video clip over at least one network from a first computing device to a second computing device.
5. The method of claim 4 wherein the second computing device is a mobile device.
6. The method of claim 1 wherein at least one of the identified foreground objects has visibly identifiable human traits.
7. The method of claim 6 wherein the visibly identifiable human traits include at least one of a physical appearance and a facial features.
8. The method of claim 1 wherein at least one of the identified foreground objects has visibly identifiable non-human traits.
9. The method of claim 8 wherein the visibly identifiable non-human traits include characters on a license plate.
10. The method of claim 1 wherein at least one of the identified foreground objects is a human face.
11. Apparatus comprising:
a display;
an input device;
at least one processor communicatively coupled to the display and the input device; and
a memory communicatively coupled to the processor and having stored thereon computer program code that is executable by the processor, wherein the computer program code, when executed by the processor, causes the processor to perform a method comprising:
retrieving, via a request to a server, surveillance video and metadata defining a plurality of moving bounding boxes that:
designate a respective plurality of identified foreground objects within the surveillance video; and
follow movement thereof; and
generating, from the surveillance video, at least one redacted video clip formatted to include at least a subset of the moving bounding boxes, the subset of the moving bounding boxes overlaying video image frames of the redacted video clip, each bounding box of the subset delineating a boundary inside of which a revealed object area and outside of which an outside area appear in the redacted video clip as an unredacted part and a redacted part respectively.
12. The apparatus of claim 11 wherein the moving bounding boxes are rectangular in shape.
13. The apparatus of claim 12 wherein dimensions of each of the moving bounding boxes vary as a function of time.
14. The apparatus of claim 11 wherein at east one of the identified foreground objects has visibly identifiable human traits.
15. The apparatus of claim 14 wherein the visibly identifiable human traits include at least one of a physical appearance and a facial features.
16. The apparatus of claim 11 wherein at least one of the identified foreground objects has visibly identifiable non-human traits.
17. The apparatus of claim 16 wherein the visibly identifiable non-human traits include characters on a license plate.
18. The apparatus of claim 11 wherein at least one of the identified foreground objects is a human face.
19. The apparatus of claim 11 wherein the apparatus is a computer terminal.
20. A tangible, non-transitory, computer-readable storage medium having instructions encoded therein, wherein the instructions, when executed by at least one processor, causes a carrying out of a method comprising:
retrieving, via a request to a server, surveillance video and metadata defining a plurality of moving bounding boxes that:
designate a respective plurality of identified foreground objects within the surveillance video; and
follow movement thereof; and
generating, from the surveillance video, at least one redacted video clip formatted to include at least a subset of the moving bounding boxes; the subset of the moving bounding boxes overlaying video image frames of the redacted video dip, each bounding box of the subset delineating a boundary inside of which a revealed object area and outside of which an outside area appear in the redacted video clip as an unredacted part and a redacted part respectively.