Construction site defect and hazard detection using artificial intelligence
AssigneeFaro Technologies, Inc.
InventorsDenis Wohlfeld, Evelyn Schmitz
Life of this patent
Estimating the term…
Abstract
A system and method for detecting construction site defects and hazards using artificial intelligence (AI) is provided. The system includes a movable base unit, a coordinate measurement scanner, a vision based sensor, and one or more processors. The one or more processors perform operations that include generating a two-dimensional (2D) map of the environment based at least in part on output from the coordinate measurement scanner, applying image recognition to the video stream data to identify and label a defect or hazard in the video data stream, correlating a location of the defect or hazard in the video stream data with the location in the 2D map, and recording the location of the defect or hazard in the 2D map.
Claims27
A system of detecting defects and hazards in an environment, the system comprising:
- a movable base unit;
- a coordinate measurement scanner coupled to the base unit, the coordinate measurement scanner comprising a light source, an image sensor and a controller, the light source emits a beam of light to illuminate object points in the environment, the image sensor is arranged to receive light reflected from the object points, and the controller being operable to determine a distance value to at least one of the object points;
- a vision based sensor coupled to the base unit, the vision based sensor operable to capture video stream data of at least a portion of the environment in response to an activation signal from an operator;
- and
- one or more processors operably coupled to the base unit, the coordinate measurement scanner, and the vision based sensor, the one or more processors being responsive to non-transitory executable instructions for performing operations comprising:
- generating a two-dimensional (2D) map of the environment based at least in part on output from the coordinate measurement scanner;
- applying image recognition to the video stream data to identify and label a defect or hazard in the video data stream;
- correlating a location of the defect or hazard in the video stream data with the location in the 2D map;
- and
- recording the location of the defect or hazard in the 2D map.
A method for detecting defects and hazards in an environment, the method comprising:
- receiving a two-dimensional (2D) map of an environment, the 2D map generated based at least in part on output from a coordinate measurement device that comprises a light source, an image sensor and a controller, the light source emits a beam of light to illuminate object points in the environment, the image sensor is arranged to receive light reflected from the object points, and the controller being operable to determine a distance value to at least one of the object points;
- receiving video stream data of at least a portion of the environment, the video stream data captured by a vision based sensor in response to an activation signal from an operator;
- applying image recognition to the video stream data to identify and label a defect or hazard in the video stream data;
- correlating a location of the defect or hazard in the video stream data with the location in the 2D map;
- and
- recording the location of the defect or hazard in the 2D map.
A system comprising:
- one or more processors for executing computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
- receiving a two-dimensional (2D) map of an environment, the 2D map generated based at least in part on output from a coordinate measurement device that comprises a light source, an image sensor and a controller, the light source emits a beam of light to illuminate object points in the environment, the image sensor is arranged to receive light reflected from the object points, and the controller being operable to determine a distance value to at least one of the object points;
- receiving video stream data of at least a portion of the environment, the video stream data captured by a vision based sensor in response to an activation signal from an operator;
- applying image recognition to the video stream data to identify and label a defect or hazard in the video stream data;
- correlating a location of the defect or hazard in the video stream data with the location in the 2D map;
- and
- recording the location of the defect or hazard in the 2D map.
Dependencies are inferred from the claim text.