Inference engine for video analytics metadata-based event detection and forensic search
US-9226037-B2 · Dec 29, 2015 · US
US9514225B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9514225-B2 |
| Application number | US-201514823180-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 11, 2015 |
| Priority date | Dec 5, 2014 |
| Publication date | Dec 6, 2016 |
| Grant date | Dec 6, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A video recording apparatus includes: an object classifier configured to classify an object which is included in an input video and related to a detected event, according to a type of the object; an object color extractor configured to extract a representative color of the object; and a search color storage configured to transform the representative color into a search color and store the search color as color information to be used for searching the object or the detected event from the input video.
Opening claim text (preview).
What is claimed is: 1. A video recording apparatus comprising: an object classifier configured to classify an object which is included in an input video and related to a detected event, according to a type of the object; an object color extractor configured to extract a representative color of the object; and a search color storage configured to transform the representative color into a search color and store the search color as color information to be used for searching the object or the detected event from the input video. 2. The apparatus of claim 1 , further comprising an event information storage configured to store information about at least one of an area of the input video in which the event occurs, a time point when the event occurs, sensitivity about the event, and attribute of the object detected in the area in which the event occurs, wherein the information about the attribute comprises identification, size, and location of the object. 3. The apparatus of claim 1 , wherein the search color storage is configured to select, as the search color, a color of which differences between red, green and blue (RGB) values and RGB values of the representative color are minimum, among a plurality of predetermined colors. 4. The apparatus of claim 1 , further comprising a search interface configured to receive input of searching for the object or the event based on the search color. 5. The apparatus of claim 4 , wherein the search interface supports or provides for a search to be performed by additionally setting at least one among a sensitivity of the event, time information about a time point when the event occurs, and area information about an area in which the event occurs. 6. The apparatus of claim 1 , wherein each image frame of the input video comprises a predetermined number of blocks and the event is detected by determining the object in a unit of block. 7. The apparatus of claim 6 , further comprising a metadata storage configured to store information about at least one of an attribute, the representative color and the search color of the object, per block of the predetermined number of blocks. 8. The apparatus of claim 7 , wherein the attribute of the object comprises the type of the object indicating whether the object is at least one of a human and a vehicle. 9. The apparatus of claim 8 , wherein the search color storage is configured to select, as the search color, a color of which differences between red, green and blue (RGB) values and RGB values of the representative color are minimum, among a plurality of predetermined colors. 10. The apparatus of claim 1 , wherein the representative color is extracted based on a histogram generated based on colors of some or all pixels of the object or based on a line sampled from the object. 11. The apparatus of claim 1 , wherein the representative color is extracted based on a color of a representative pixel of the object, and wherein the representative pixel of the object comprises at least one of a corner pixel of the object, a central pixel of the object, and a pixel spaced a predetermined distance from a center of the object. 12. The apparatus of claim 1 , wherein the representative color is extracted based on a histogram generated with respect to a line sampled from the object. 13. The apparatus of claim 1 , wherein the search color storage is configured to select, as the search color, a color of which differences between red, green and blue (RGB) values and RGB values of the representative color are minimum, among a plurality of predetermined colors. 14. The apparatus of claim 13 , wherein the search color storage is further configured to generate a data structure from the input video based on a number of blocks constituting each image frame of the input video, the type of object related to the detected event, and a number of a predetermined colors from which the search color is selected. 15. A smart search method performed by a video recording apparatus, the method comprising: classifying, by an object classifier, an object which is included in an input video and related to a detected event, according to a type of the object; extracting, by an object color extractor, a representative color of the object; and transforming, by a search color storage, the representative color into a search color and storing the search color as color information to be used for searching the object or the detected event from the input video. 16. The method of claim 15 , further comprising selecting, as the search color, a color of which differences between red, green and blue (RGB) values and RGB values of the representative color are minimum, among a plurality of predetermined colors. 17. The method of claim 16 , further comprising storing information about at least one of an attribute, the representative color and the search color of the object, per block of the predetermined number of blocks. 18. The method of claim 17 , further comprising generating a data structure from the input video based on a number of blocks constituting each image frame of the input video, the type of object related to the detected event, and a number of a predetermined colors from which the search color is selected. 19. The method of claim 15 , further comprising storing information about at least one of an attribute, the representative color and the search color of the object, per block of the predetermined number of blocks. 20. The method of claim 15 , further comprising generating a data structure from the input video based on a number of blocks constituting each image frame of the input video, the type of object related to the detected event, and a number of a predetermined colors from which the search color is selected.
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Means responsive to presence or absence of recorded information signals · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.