Method, apparatus, computing device and computer-readable storage medium for correcting pedestrian trajectory
US-12062192-B2 · Aug 13, 2024 · US
US2018081908A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2018081908-A1 |
| Application number | US-201515564649-A |
| Country | US |
| Kind code | A1 |
| Filing date | Apr 8, 2015 |
| Priority date | Apr 8, 2015 |
| Publication date | Mar 22, 2018 |
| 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 image search apparatus including: an accumulation unit that accumulates search target images; an area detector that learns search priority by analyzing first information extracted from a plurality of first areas included in a plurality of the search target images, analyzes second information extracted from a plurality of second areas included in a query image, and detects the second areas, the search priority of which is high, as conspicuous areas by using the second information; and an image search unit that searches for the search target images by using an image feature extracted from the conspicuous areas.
Opening claim text (preview).
1 . An image search apparatus comprising: an accumulation unit that accumulates search target images; an area detector that learns search priority by analyzing first information extracted from a plurality of first areas included in a plurality of the search target images, analyzes second information extracted from a plurality of second areas included in a query image, and detects the second areas, the search priority of which is high, as conspicuous areas by using the second information; and an image search unit that searches for the search target images by using an image feature extracted from the conspicuous areas. 2 . The image search apparatus according to claim 1 , wherein the area detector analyzes a plurality of pieces of the first information, learns the first information with lowest appearance frequency as conspicuity information the search priority of which is the highest, and detects the conspicuous areas on the basis of a distance between the second information and the conspicuity information. 3 . The image search apparatus according to claim 2 , further comprising a moving object judgment unit that determines that the moving object is captured in the first areas through a plurality of frames when similarity with the first areas in an immediately preceding frame or an immediately following frame from among the first areas is higher than a threshold value, wherein the accumulation unit further accumulates moving object identification information indicating the moving object with respect to the plurality of first areas. 4 . The image search apparatus according to claim 2 , wherein the accumulation unit accumulates the search target images for each camera which captures the search target images; and wherein the area detector learns the search priority with respect to each camera. 5 . An image search system comprising an image search apparatus and an authentication device, wherein the image search apparatus includes: an accumulation unit that accumulates search target images and moving object identification information indicative of a moving object; an area detector that learns search priority by analyzing first information extracted from a plurality of first areas included in a plurality of the search target images, analyzes second information extracted from a plurality of second areas included in a query image, and detects the second areas, the search priority of which is high, as conspicuous areas by using the second information; an image search unit that searches for the search target images by using an image feature extracted from the conspicuous areas; and a moving object judgment unit that determines that the moving object is captured in the first areas through a plurality of frames when similarity with the first areas in an immediately preceding frame or an immediately following frame from among the first areas is higher than a threshold value; wherein the authentication device includes: a registration information storage unit that stores registration information of a plurality of users; a check unit that checks newly acquired user information against the registration information; an output unit that outputs first registration information, which is the registration information judged by the check unit that it matches the user information, to the image search apparatus; and wherein the accumulation unit further associates the first registration information with the moving object identification information and accumulates them. 6 . An image search method comprising: a first step of accumulating search target images in an accumulation unit; a second step of learning search priority by analyzing first information extracted from a plurality of first areas included in a plurality of the search target images, analyzing second information extracted from a plurality of second areas included in a query image, and detecting the second areas, the search priority of which is high, as conspicuous areas by using the second information; and a third step of searching for the search target images by using an image feature extracted from the conspicuous areas. 7 . The image search method according to claim 6 , wherein in the second step, a plurality of pieces of the first information is analyzed, the first information with lowest appearance frequency is learned as conspicuity information the search priority of which is the highest, and the conspicuous areas are detected on the basis of a distance between the second information and the conspicuity information. 8 . The image search method according to claim 7 , further comprising a fourth step of judging that the moving object is captured in the first areas through a plurality of frames when similarity with the first areas in an immediately preceding frame or an immediately following frame from among the first areas is higher than a threshold value, wherein in the first step, moving object identification information indicating the moving object with respect to the plurality of first areas is further accumulated in the accumulation unit. 9 . The image search method according to claim 7 , wherein in the first step, the search target images are accumulated for each camera which captures the search target images; and wherein in the second step, the search priority is learned with respect to each camera. 10 . The image search method according to claim 8 , further comprising: a fifth step of storing registration information of a plurality of users; a sixth step of acquiring the user information and checking the user information against the registration information; and a seventh step of outputting first registration information judged by the check unit that it matches the user information, wherein in the first step, the first registration information and the moving object identification information are associated with each other and accumulated.
involving reference images or patches · CPC title
using shape and object relationship · CPC title
Physics · mapped topic
Surveillance · CPC title
Video; Image sequence · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.