Method and system for detecting the owner of an abandoned object from a surveillance video
A video surveillance method and system involves transitioning pixel intensities in a region associated with a fixed location from background values to values representing an image of an object when the object is abandoned at a fixed location in a scene in a video, and identifying an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities.
1. A video surveillance method, comprising:
transitioning pixel intensities in a region associated with a fixed location from background values to values representing an image of an object, when the object is abandoned as shown at the fixed location in a scene in a video;
identifying an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities in the region associated with the fixed location from the background values to the values representing the image of the object; and
generating a first output comprising a video slip of a time before and after the transitioning, wherein the video slip displays an event of abandonment associated with the object, and a second output comprising an image constructed from a cross section in the constructed image intersecting the object and the transitioned pixel intensities in time, wherein at an instant of time in which there is a change in the pixel intensities, a representation in the image of a person associated with the object is confined to a localized region in a vicinity of the object in the image, wherein a search of this localized region results in an indication that the person shown in the localized region is an owner of the object that was abandoned.
2. The method of claim 1 wherein the cross section includes a horizontal cross section.
3. The method of claim 1 wherein the cross section includes a vertical cross section.
4. The method of claim 1 wherein the cross section includes at least one of a horizontal cross section and a vertical cross section.
5. The method of claim 1 wherein the region comprises a localized spatio-temporal region.
6. The method of claim 1 wherein the object comprises a piece of luggage.
7. The method of claim 1 wherein a performance of a data-processing system is improved by:
the transitioning of pixel intensities in a region associated with a fixed location from background values to values representing an image of the object;
the identifying of an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities in the region associated with the fixed location from the background values to the values representing the image of the object; and
the generating of the first output and the second output.
8. A video surveillance system, comprising:
at least one processor and a memory, the memory storing instructions to cause the at least one processor to perform:
when an object is abandoned at a fixed location in a scene in a video, transitioning pixel intensities in a region associated with the fixed location from background values to values representing an image of the object;
identifying an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities in the region associated with the fixed location from the background values to the values representing the image of the object; and
generating a first output comprising a video slip of a time before and after the transitioning, wherein the video slip displays an event of abandonment associated with the object, and a second output comprising an image constructed from a cross section in the constructed image intersecting the object and the transitioned pixel intensities in time, wherein at an instant of time in which there is a change in the pixel intensities, a representation in the image of a person associated with the object is confined to a localized region in a vicinity of the object in the image, wherein a search of this localized region results in an indication that the person shown in the localized region is an owner of the object that was abandoned.
9. The system of claim 8 wherein the cross section includes a horizontal cross section.
10. The system of claim 8 wherein the cross section includes a vertical cross section.
11. The system of claim 8 wherein the cross section includes at least one of a horizontal cross section and a vertical cross section.
12. The system of claim 8 wherein the region comprises a localized spatio-temporal region.
13. The system of claim 8 wherein the object comprises a piece of luggage.
14. The system of claim 8 further comprising a data-processing system comprising at least one of: the at least one processor and the memory, wherein a performance of a data-processing system is improved by:
the instructions for transitioning pixel intensities in a region associated with a fixed location from background values to values representing an image of the object;
the instructions for identifying of an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities in the region associated with the fixed location from the background values to the values representing the image of the object; and
the instructions for generating the first output and the second output.
15. A video surveillance system, comprising:
at least one surveillance camera that captures video of a scene, wherein when an object is abandoned at a fixed location in the scene in the video captured by the at least one surveillance camera, pixel intensities are transitioned by a processor in a region associated with the fixed location from background values to values representing an image of the object;
wherein the processor identifies an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities in the region associated with the fixed location from the background values to the values representing the image of the object; and
wherein the processor generates a first output comprising a video slip of a time before and after the transitioning, wherein the video slip displays an event of abandonment associated with the object, and a second output comprising an image constructed from a cross section in the constructed image intersecting the object and the transitioned pixel intensities in time, wherein at an instant of time in which there is a change in the pixel intensities, a representation in the image of a person associated with the object is confined to a localized region in a vicinity of the object in the image, wherein a search of this localized region results in an indication that the person shown in the localized region is an owner of the object that was abandoned.
16. The system of claim 15 wherein the cross section includes a horizontal cross section.
17. The system of claim 15 wherein the cross section includes a vertical cross section.
18. The system of claim 15 wherein the cross section includes at least one of a horizontal cross section and a vertical cross section.
19. The system of claim 15 wherein the region comprises a localized spatio-temporal region.
20. The system of claim 15 wherein the object comprises a piece of luggage.