IP Library › Granted Patent US 12,597,154
Granted Patent B2
US 12,597,154 · App. 18/220,284 · Granted Apr 7, 2026

Image analysis method without computation of an installation angle and related camera apparatus

Inventor: Chao-Tan Huang (New Taipei City, TW)
Assignee: VIVOTEK INC.
G06T7/60G06T7/11G06V10/761
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,597,154
App. No.
18/220,284
Granted
Apr 7, 2026
Kind
B2
Abstract

An image analysis method is applied to a camera apparatus and used to analyze the landform inside a detection image captured by the camera apparatus via a predefined installation angle. The image analysis method includes dividing the detection image into a plurality of first regions to acquire a plurality of first height, defining some first regions with the same height and adjacent to each other as a first reference plane area to acquire a first plane formula, selecting at least one first region adjacent to and outside the first reference plane area, applying the selected first region for the first plane formula to acquire a first planar height and comparing the first planar height with an initial first height of the at least one first region, and determining landform between the first reference plane area and the selected at least one first region in accordance with a comparison result.

Claims (41)

1 . An image analysis method applied to a camera apparatus having an operation processor and an image receiver, and adapted to analyze a landform inside a detection image captured by the image receiver via a predefined installation angle, the image analysis method comprising:

the operation processor dividing the detection image into a plurality of first regions to acquire a plurality of first heights of the plurality of first regions relative to the camera apparatus;

the operation processor defining some of the plurality of first regions having the same height and being adjacent to each other as a first reference plane area to acquire a first plane formula of the first reference plane area;

the operation processor selecting at least one of the plurality of first regions adjacent to and outside the first reference plane area, and applying the first plane formula for the selected at least one first region to acquire a first planar height of the selected at least one first region;

the operation processor comparing the first planar height with an initial first height of the selected at least one first region; and

the operation processor determining a landform relation between the first reference plane area and the selected at least one first region relative to the camera apparatus in accordance with a comparison result.

2 . The image analysis method of claim 1 , further comprising:

the operation processor dividing each first region into a plurality of second regions when a dispersion degree of the plurality of first heights conforms to a predefined condition;

the operation processor acquiring a plurality of second heights of the plurality of second regions relative to the camera apparatus;

the operation processor defining some of the plurality of second regions having the same height and being adjacent to each other as a third reference plane area to acquire a third plane formula of the third reference plane area;

the operation processor selecting at least one of the plurality of second regions adjacent to and outside the third reference plane area, and applying the third plane formula for the selected at least one second region to acquire a second planar height of the selected at least one second region;

the operation processor comparing the second planar height with an initial second height of the selected at least one second region; and

the operation processor determining a landform relation between the third reference plane area and the selected at least one second region relative to the camera apparatus in accordance with a comparison result.

3 . The image analysis method of claim 2 , further comprising:

the operation processor utilizing the predefined installation angle to compute the plurality of first heights of the plurality of first regions; and

the operation processor computing standard deviation of the plurality of first heights to acquire the dispersion degree.

4 . The image analysis method of claim 3 , wherein the operation processor utilizes the predefined installation angle to compute an average height of all objects inside the detection image, and compares the average height with an object mean height of a place where on the camera apparatus is located so as to calibrate the plurality of first heights.

5 . The image analysis method of claim 2 , further comprising:

the operation processor setting the plurality of first heights as a landform height inside the detection image when the dispersion degree of the plurality of first heights does not conform to the predefined condition.

6 . The image analysis method of claim 1 , further comprising:

the operation processor utilizing a two-dimensional regression algorithm to acquire the first plane formula.

7 . The image analysis method of claim 1 , further comprising:

the operation processor determining the at least one first region adjacent to and outside the first reference plane area is on the same plane as the first reference plane area when a difference between the first planar height of the selected at least one first region and the initial first height is lower than a predefined threshold.

8 . The image analysis method of claim 1 , further comprising:

the operation processor determining the at least one first region adjacent to and outside the first reference plane area has a height different from a height of the first reference plane area when a difference between the first planar height of the selected at least one first region and the initial first height is greater than or equal to a predefined threshold.

9 . The image analysis method of claim 8 , further comprising:

the operation processor deciding whether the plurality of first regions contains other first region having the same height and adjacent position.

10 . The image analysis method of claim 1 , further comprising:

the operation processor dividing the detection image into the plurality of first regions in a predefined grid arrangement manner to detect the plurality of first heights.

11 . A camera apparatus comprising:

an image receiver adapted to capture a detection image via a predefined installation angle; and

an operation processor electrically connected to the image receiver in a wire manner or in a wireless manner, and adapted to divide the detection image into a plurality of first regions for acquiring a plurality of first heights of the plurality of first regions relative to the camera apparatus, to define some of the plurality of first regions having the same height and being adjacent to each other as a first reference plane area for acquiring a first plane formula of the first reference plane area, to select at least one of the plurality of first regions adjacent to and outside the first reference plane area and apply the first plane formula for the selected at least one first region to acquire a first planar height of the selected at least one first region, to compare the first planar height with an initial first height of the selected at least one first region, and to determine a landform relation between the first reference plane area and the selected at least one first region relative to the camera apparatus in accordance with a comparison result.

12 . The camera apparatus of claim 11 , wherein the operation processor is adapted to further divide each first region into a plurality of second regions when a dispersion degree of the plurality of first heights conforms to a predefined condition, to acquire a plurality of second heights of the plurality of second regions relative to the camera apparatus, to define some of the plurality of second regions having the same height and being adjacent to each other as a third reference plane area for acquiring a third plane formula of the third reference plane area, to select at least one of the plurality of second regions adjacent to and outside the third reference plane area and apply the third plane formula for the selected at least one second region to acquire a second planar height of the selected at least one second region, to compare the second planar height with an initial second height of the selected at least one second region, and to determine a landform relation between the third reference plane area and the selected at least one second region relative to the camera apparatus in accordance with a comparison result.

13 . The camera apparatus of claim 12 , wherein the operation processor is adapted to further utilize the predefined installation angle to compute the plurality of first heights of the plurality of first regions, and to compute standard deviation of the plurality of first heights for acquiring the dispersion degree.

14 . The camera apparatus of claim 13 , wherein the operation processor is adapted to further utilize the predefined installation angle to compute an average height of all objects inside the detection image, and compares the average height with an object mean height of a place where on the camera apparatus is located for calibrating the plurality of first heights.

15 . The camera apparatus of claim 12 , wherein the operation processor is adapted to further set the plurality of first heights as a landform height inside the detection image when the dispersion degree of the plurality of first heights does not conform to the predefined condition.

16 . The camera apparatus of claim 11 , wherein the operation processor is adapted to further utilize a two-dimensional regression algorithm to acquire the first plane formula.

17 . The camera apparatus of claim 11 , wherein the operation processor is adapted to further determine the at least one first region adjacent to and outside the first reference plane area is on the same plane as the first reference plane area when a difference between the first planar height of the selected at least one first region and the initial first height is lower than a predefined threshold.

18 . The camera apparatus of claim 11 , wherein the operation processor is adapted to further determine the at least one first region adjacent to and outside the first reference plane area has a height different from a height of the first reference plane area when a difference between the first planar height of the selected at least one first region and the initial first height is greater than or equal to a predefined threshold.

19 . The camera apparatus of claim 18 , wherein the operation processor is adapted to further decide whether the plurality of first regions contains other first region having the same height and adjacent position.

20 . The camera apparatus of claim 18 , wherein the operation processor is adapted to further divide the detection image into the plurality of first regions in a predefined grid arrangement manner for detection of the plurality of first heights.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2023
From: HUANG, CHAO-TAN
To: VIVOTEK INC.
Reel/Frame 064217/0786 →
Priority Claims (1)
TW 111129154 · Aug 3, 2022 · national
Continuity (1)
Related Publication 20240046497A1 · Feb 8, 2024
References Cited (13)
US 10089750B2 · Ho · 2018 [cited by examiner]
US 10176564B1 · El Dokor · 2019 [cited by examiner]
US 20030174880A1 · Sakamoto · 2003 [cited by applicant]
US 20140363073A1 · Shirakyan · 2014 [cited by examiner]
US 20150254830A1 · Shimodaira · 2015 [cited by examiner]
US 20170032194A1 · Yu · 2017 [cited by examiner]
US 20170039431A1 · Yu · 2017 [cited by examiner]
US 20170049366A1 · Matsumoto · 2017 [cited by examiner]
US 20180128602A1 · Morimoto · 2018 [cited by examiner]
US 20210209779A1 · Yeh · 2021 [cited by examiner]
CA 2726895A1 · 2009 [cited by examiner]
CN 104349136A · 2015 [cited by applicant]
CN 107504957A · 2017 [cited by applicant]