Boundary line recognition apparatus and branch road determination apparatus
US-2015348275-A1 · Dec 3, 2015 · US
US9704259B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9704259-B2 |
| Application number | US-201414779044-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 14, 2014 |
| Priority date | Mar 26, 2013 |
| Publication date | Jul 11, 2017 |
| Grant date | Jul 11, 2017 |
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 people counting device includes an edge extracting unit configured to extract an edge from a planar image of a target area, and a circle candidate detecting unit configured to detect a circle candidate included in the planar image based on the edge extracted by the edge extracting unit. The people counting device further includes a person determining unit configured to calculate a brightness gradient for each edge pixel constituting an edge of each circle candidate detected by the circle candidate detecting unit and determine that a circle candidate whose uniformity of brightness gradients for the edge pixels of the circle candidate is higher than a reference is a person's head portion, and a people counting unit configured to count the number of circle candidates determined to be a person's head portion by the person determining unit.
Opening claim text (preview).
What is claimed is: 1. A people counting device comprising: an edge extracting unit configured to extract an edge from a planar image of a target area; a circle candidate detecting unit configured to detect a circle candidate included in the planar image based on the edge extracted by the edge extracting unit; a person determining unit configured to calculate a brightness gradient for each of a plurality of edge pixels constituting an edge of each circle candidate detected by the circle candidate detecting unit and determine that a circle candidate whose uniformity of brightness gradients for the edge pixels of the circle candidate is higher than a reference is a person's head portion; and a people counting unit configured to count a number of circle candidates determined to be a person's head portion by the person determining unit. 2. The people counting device of claim 1 , wherein the person determining unit calculates a degree of radial distribution of brightness gradients for each edge pixel from a center of the circle, as an indicator indicating the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate, and determines whether or not the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate is higher than the reference by comparing a result of the calculation with a predetermined threshold. 3. The people counting device of claim 1 , wherein the person determining unit calculates a degree of variation of magnitude of brightness gradients for each edge pixel, as an indicator indicating the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate, and determines whether or not the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate is higher than the reference by comparing a result of the calculation with a predetermined threshold. 4. A people counting method comprising: extracting an edge from a planar image of a target area; detecting a circle candidate included in the planar image based on the edge extracted by extracting the edge; calculating a brightness gradient for each of a plurality of edge pixels constituting an edge of each circle candidate detected by detecting the circle candidate and determining that a circle candidate whose uniformity of brightness gradients for the edge pixels of the circle candidate is higher than a reference is a person's head portion; and counting a number of circle candidates determined to be a person's head portion by the determining. 5. The people counting method of claim 4 , wherein the determining comprises calculating a degree of radial distribution of brightness gradients for each edge pixel from a center of the circle, as an indicator indicating the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate, and determining whether or not the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate is higher than the reference by comparing a result of the calculation with a predetermined threshold. 6. The people counting method of claim 4 , wherein the determining comprises calculating a degree of variation of magnitude of brightness gradients for each edge pixel, as an indicator indicating the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate, and determining whether or not the uniformity of brightness gradients for the edge pixels constituting the edge of the circle candidate is higher than the reference by comparing a result of the calculation with a predetermined threshold.
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Video; Image sequence · CPC title
Surveillance · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.