Information processing system, information processing method and program
US-9292939-B2 · Mar 22, 2016 · US
US2016104357A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016104357-A1 |
| Application number | US-201414786945-A |
| Country | US |
| Kind code | A1 |
| Filing date | Apr 23, 2014 |
| Priority date | Apr 26, 2013 |
| Publication date | Apr 14, 2016 |
| Grant date | — |
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.
An information processing system includes an input unit which receives inputs of videos captured by a plurality of imaging apparatuses, a detection unit which detects a moving body appearing in a first video captured by a first imaging apparatus among the plurality of imaging apparatuses and a moving body appearing in a second video captured by a second imaging apparatus among the plurality of imaging apparatuses, a first computation unit which derives, on the basis of similarity between a feature value of the moving body appearing in the first video and a feature value of the moving body appearing in the second video, a first probability indicating a probability that both moving bodies are the same, a second computation unit which derives a second probability indicating a probability that the moving body appearing in the first video does not appear in the second video on the basis of an elapsed time after the moving body exits and disappears from the first video, and a determination unit which determines whether or not the moving body appearing in the first video and the moving body appearing in the second video are the same on the basis of a comparison between the first probability and the second probability.
Opening claim text (preview).
1 . An information processing system comprising: an input unit which receives inputs of videos captured by a plurality of imaging apparatuses; a detection unit which detects a moving body appearing in a first video captured by a first imaging apparatus among the plurality of imaging apparatuses and a moving body appearing in a second video captured by a second imaging apparatus among the plurality of imaging apparatuses; a first computation unit which derives, on the basis of similarity between a feature value of the moving body appearing in the first video and a feature value of the moving body appearing in the second video, a first probability indicating a probability that both moving bodies are the same; a second computation unit which derives a second probability indicating a probability that the moving body appearing in the first video does not appear in the second video on the basis of an elapsed time after the moving body exits and disappears from the first video; and a determination unit which determines whether or not the moving body appearing in the first video and the moving body appearing in the second video are the same on the basis of a comparison between the first probability and the second probability. 2 . The information processing system according to claim 1 , wherein the determination unit determines that the moving body appearing in the first video and the moving body appearing in the second video are the same when the first probability is larger than the second probability. 3 . The information processing system according to claim 1 , wherein the second probability is monotonously non-increasing with respect to an elapsed time after the moving body exits and disappears from the first video. 4 . The information processing system according to claim 3 , wherein the second probability exhibits a less decreased width with respect to an elapsed time when a distance from a imaging range of the first imaging apparatus to a imaging range of the second imaging apparatus is long than when the distance from the imaging range of the first imaging apparatus to the imaging range of the second imaging apparatus is short. 5 . The information processing system according to claim 1 , the system further comprising a display control unit which displays the second video on a display device, the display control units changing a display method, when the moving body appearing in the second video is the same as the moving body appearing in the first video, into a different display method from a display method used before the moving bodies are determined to be the same moving body. 6 . The information processing system according to claim 1 , wherein the determination unit determines whether or not any one of a plurality of moving bodies appearing in the first video at the same time is the same as a part of moving bodies appearing in the second video, and the second computation units lowers the second probability for a moving body that is not associated with the moving body appearing in the second video among the plurality of moving bodies when there is a moving body determined to be the same as the moving body appearing in the second video among the plurality of moving bodies. 7 . An information processing method comprising: receiving inputs of videos captured by a plurality of imaging apparatuses; detecting a moving body appearing in a first video captured by a first imaging apparatus among the plurality of imaging apparatuses and a moving body appearing in a second video captured by a second imaging apparatus among the plurality of imaging apparatuses; deriving, on the basis of similarity between a feature value of the moving body appearing in the first video and a feature value of the moving body appearing in the second video, a first probability in which both moving bodies are the same; deriving a second probability in which the moving body appearing in the first video does not appear in the second video on the basis of an elapsed time after the moving body exits and disappears from the first video; and determining whether or not the moving body appearing in the first video and the moving body appearing in the second video are the same on the basis of a comparison between the first probability and the second probability. 8 . A non-transitory computer readable storage medium recording thereon a program that causes a computer to execute: processing for receiving inputs of videos captured by a plurality of imaging apparatuses; processing for detecting a moving body appearing in a first video captured by a first imaging apparatus among the plurality of imaging apparatuses and a moving body appearing in a second video captured by a second imaging apparatus among the plurality of imaging apparatuses; processing for deriving, on the basis of similarity between a feature value of the moving body appearing in the first video and a feature value of the moving body appearing in the second video, a first probability in which both moving bodies are the same; processing for deriving a second probability in which the moving body appearing in the first video does not appear in the second video on the basis of an elapsed time after the moving body exits and disappears from the first video; and processing for determining whether or not the moving body appearing in the first video and the moving body appearing in the second video are the same on the basis of a comparison between the first probability and the second probability.
using television cameras · CPC title
Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over · CPC title
for receiving images from a plurality of remote sources · CPC title
in albums, collections or shared content, e.g. social network photos or video · CPC title
of traffic, e.g. cars on the road, trains or boats · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.