US 11,600,061 B1Granted

Method and system for maintaining bridge using bridge image data

AssigneeRainbowtech Co., Ltd.

InventorHan Kyu Jeong

Life of this patent

Estimating the term…

Abstract

Provided are a method and a system for analyzing image data obtained by photographing a bridge by a drone using artificial intelligence, rapidly and accurately finding a part that requires maintenance of the bridge, and calculating a maintenance solution and a maintenance estimate for the part. The system for maintaining a bridge by analyzing bridge image data received from a drone using artificial intelligence, includes: the drone that photographs the bridge to generate the bridge image data; and an artificial intelligence bridge maintenance apparatus that finds a part of the bridge requiring maintenance, and calculates an optimal maintenance solution and an optimal maintenance estimate necessary for the bridge maintenance.

Claims11

Dependent claims

A system for maintaining a bridge by analyzing bridge image data received from a drone using artificial intelligence, comprising:

the drone that photographs a bridge to generate the bridge image data;
and
an artificial intelligence bridge maintenance apparatus that finds a part of the bridge requiring maintenance, and calculates an optimal maintenance solution and an optimal maintenance estimate necessary for the bridge maintenance,
wherein the artificial intelligence bridge maintenance apparatus includes:
a communicating unit that communicates with the drone to receive the bridge image data and transmits a drone control signal;
a DB that stores bridge data and the bridge image data;
a primary bridge image data generating unit that controls the drone under the control of an artificial intelligence processing unit to perform drone photographing to generate primary bridge image data for a concerned area of the bridge;
and
the artificial intelligence processing unit that analyzes the bridge data and the bridge image data through big data and artificial intelligence to divide the bridge into drone photographing areas, analyzes the primary bridge image data to select a dangerous part that requires intensive photographing for the bridge maintenance, performs precise drone photographing for the dangerous part to generate secondary bridge image data including corrected features for cracks, and analyzes the secondary bridge image data to calculate a maintenance solution and a maintenance estimate for the bridge,
wherein the artificial intelligence processing unit includes:
a drone photographing area dividing unit that determines structural features of the bridge using at least one of the bridge data and the bridge image data to divide the bridge into the drone photographing areas according to priority;
a dangerous part selecting unit that analyzes the primary bridge image data through a dangerous part selecting artificial intelligence method to select the dangerous part that requires the intensive photographing for the bridge maintenance;
a secondary bridge image data generating unit that performs the precise drone photographing for the dangerous part through a precise crack photographing artificial intelligence method to generate the secondary bridge image data including the corrected features for the cracks;
and
a maintenance solution and estimate calculating unit that analyzes the secondary bridge image data using a bridge maintenance artificial intelligence method to calculate the maintenance solution and the maintenance estimate for the dangerous part, and
wherein the dangerous part selecting unit analyzes at least one of a photographing route of the drone and photographing information included in the primary bridge image data stored in the DB, performs drone photographing to match the photographing route of the drone, performs correction to be the same or similar to the photographing information to generate the primary bridge image data, and selects a part of the bridge in which a change of at least one of a shape, color, and features of cracks in the primary bridge image data is equal to or greater than a reference range as a dangerous part, using a CNN (Convolution Neural Network) method for optimally changing a filter and a channel according to features to be compared between the generated primary bridge image data and existing bridge image data.

13 more elements

A bridge maintaining method using bridge image data in a bridge maintaining system including a drone and an artificial intelligence bridge maintenance apparatus, the method comprising:

(a) a step of dividing a bridge into drone photographing areas using at least one of bridge data stored in a DB and existing bridge image data, by the artificial intelligence bridge maintenance apparatus;
(b) a step of performing drone photographing for the photographing areas of the drone according to priority, generating primary bridge image data for a concerned area including a photographing route of the drone and photographing information, and storing the generated primary bridge image data in the DB to update the existing bridge image data, by the artificial intelligence bridge maintenance apparatus;
(c) a step of analyzing the primary bridge image data using a dangerous part selecting artificial intelligence method to select a dangerous part that needs intensive photographing for bridge maintenance, by the artificial intelligence bridge maintenance apparatus;
(d) a step of performing precise drone photographing for the dangerous part using a precise crack photographing artificial intelligence method, generating secondary bridge image data including corrected features for cracks, and storing the generated secondary bridge image data in the DB, by the artificial intelligence bridge maintenance apparatus;
and
(e) a step of analyzing the secondary bridge image data using a bridge maintenance artificial intelligence method to calculate a maintenance solution and a maintenance estimate for the bridge, by the artificial intelligence bridge maintenance apparatus,
wherein the precise crack photographing artificial intelligence method determines a width, length, and depth of a crack by correcting the photographing route, a photographing position, and a photographing distance of the drone.

4 more elements

A bridge maintaining method using bridge image data in a bridge maintaining system including a drone and an artificial intelligence bridge maintenance apparatus, the method comprising:

(a) a step of dividing a bridge into drone photographing areas using at least one of bridge data stored in a DB and existing bridge image data, by the artificial intelligence bridge maintenance apparatus;
(b) a step of performing drone photographing for the photographing areas of the drone according to priority, generating primary bridge image data for a concerned area including a photographing route of the drone and photographing information, and storing the generated primary bridge image data in the DB to update the existing bridge image data, by the artificial intelligence bridge maintenance apparatus;
(c) a step of analyzing the primary bridge image data using a dangerous part selecting artificial intelligence method to select a dangerous part that needs intensive photographing for bridge maintenance, by the artificial intelligence bridge maintenance apparatus;
(d) a step of performing precise drone photographing for the dangerous part using a precise crack photographing artificial intelligence method, generating secondary bridge image data including corrected features for cracks, and storing the generated secondary bridge image data in the DB, by the artificial intelligence bridge maintenance apparatus;
and
(e) a step of analyzing the secondary bridge image data using a bridge maintenance artificial intelligence method to calculate a maintenance solution and a maintenance estimate for the bridge, by the artificial intelligence bridge maintenance apparatus,
wherein the bridge maintenance artificial intelligence method determines an optimal maintenance solution using a bridge design, a construction method, construction materials, and features of cracks of a part where the cracks occur, in the secondary bridge image data, and calculates an optimal maintenance estimate using the same.

4 more elements

Dependencies are inferred from the claim text.

patentgrep

Loading patent…

Abstract

A system for maintaining a bridge by analyzing bridge image data received from a drone using artificial intelligence, comprising:

the drone that photographs a bridge to generate the bridge image data;
and
an artificial intelligence bridge maintenance apparatus that finds a part of the bridge requiring maintenance, and calculates an optimal maintenance solution and an optimal maintenance estimate necessary for the bridge maintenance,
wherein the artificial intelligence bridge maintenance apparatus includes:
a communicating unit that communicates with the drone to receive the bridge image data and transmits a drone control signal;
a DB that stores bridge data and the bridge image data;
a primary bridge image data generating unit that controls the drone under the control of an artificial intelligence processing unit to perform drone photographing to generate primary bridge image data for a concerned area of the bridge;
and
the artificial intelligence processing unit that analyzes the bridge data and the bridge image data through big data and artificial intelligence to divide the bridge into drone photographing areas, analyzes the primary bridge image data to select a dangerous part that requires intensive photographing for the bridge maintenance, performs precise drone photographing for the dangerous part to generate secondary bridge image data including corrected features for cracks, and analyzes the secondary bridge image data to calculate a maintenance solution and a maintenance estimate for the bridge,
wherein the artificial intelligence processing unit includes:
a drone photographing area dividing unit that determines structural features of the bridge using at least one of the bridge data and the bridge image data to divide the bridge into the drone photographing areas according to priority;
a dangerous part selecting unit that analyzes the primary bridge image data through a dangerous part selecting artificial intelligence method to select the dangerous part that requires the intensive photographing for the bridge maintenance;
a secondary bridge image data generating unit that performs the precise drone photographing for the dangerous part through a precise crack photographing artificial intelligence method to generate the secondary bridge image data including the corrected features for the cracks;
and
a maintenance solution and estimate calculating unit that analyzes the secondary bridge image data using a bridge maintenance artificial intelligence method to calculate the maintenance solution and the maintenance estimate for the dangerous part, and
wherein the dangerous part selecting unit analyzes at least one of a photographing route of the drone and photographing information included in the primary bridge image data stored in the DB, performs drone photographing to match the photographing route of the drone, performs correction to be the same or similar to the photographing information to generate the primary bridge image data, and selects a part of the bridge in which a change of at least one of a shape, color, and features of cracks in the primary bridge image data is equal to or greater than a reference range as a dangerous part, using a CNN (Convolution Neural Network) method for optimally changing a filter and a channel according to features to be compared between the generated primary bridge image data and existing bridge image data.

13 more elements