Detecting apparatus, position calculation system, and detecting method

A position calculation system configured to calculate a position of a vehicle contained in a captured image,

• the vehicle being configured to move in a factory in which a plurality of manufacturing steps is performed to manufacture and ship the vehicle,
• the vehicle being classified into a plurality of states in accordance with an appearance of the vehicle, the appearance varying among the plurality of manufacturing steps,
• the position calculation system comprising:
• a detecting apparatus configured to detect the vehicle contained in the captured image,
• the detecting apparatus comprising a first processor configured to:
• acquire the captured image;
• acquire state information indicating one of the states of the vehicle contained in the captured image;
• from among a plurality of first detection models that are machine learning models each prepared one by one for the states, acquire the first detection model selected in accordance with the one of the states, identified by the acquired state information;
• and
• detect the vehicle contained in the captured image by inputting the captured image to the acquired first detection model and identifying a target region representing the vehicle in the captured image;
• and
• generate a first mask image, in which a mask region is added to the target region that is a region representing the vehicle, by masking the target region in the captured image;
• and
• a position calculation apparatus configured to calculate a position of the vehicle, the position calculation apparatus including a second processor, the second processor being configured to
• generate a second mask image by performing perspective transformation of the first mask image,
• where a designated vertex of a first circumscribed rectangle set for the mask region in the first mask image is a first coordinate point and a vertex indicating the same position as the first coordinate point of a second circumscribed rectangle set for the mask region in the second mask image is a second coordinate point, calculate an image coordinate point indicating a position of the vehicle in an image coordinate system by correcting the first coordinate point using the second coordinate point, and
• convert the image coordinate point to a vehicle coordinate point indicating a position of the vehicle in a global coordinate system by using a distance from a reference point of the image capture device, calculated based on a position of the image capture device in the global coordinate system, and a distance from the reference point of a predetermined measuring point of the vehicle.

A detecting method of detecting a vehicle contained in a captured image,

• the vehicle being configured to move in a factory in which a plurality of manufacturing steps is performed to manufacture and ship the vehicle,
• the vehicle being classified into a plurality of states in accordance with an appearance of the vehicle, the appearance varying among the plurality of manufacturing steps,
• the detecting method comprising:
• acquiring the captured image;
• acquiring state information indicating one of the states of the vehicle contained in the captured image;
• from among a plurality of first detection models that are machine learning models each prepared one by one for the states, acquiring the first detection model selected in accordance with the one of the states, identified by the acquired state information;
• and
• detecting the vehicle contained in the captured image by inputting the captured image to the acquired first detection model and identifying a target region representing the vehicle in the captured image,
• wherein each of the plurality of first detection models is trained in advance to identify the target region by inputting a plurality of training images, and the plurality of training images includes M (M is an integer greater than or equal to two) first training images each containing the vehicle that is classified to the one of the states and N (N is an integer greater than or equal to zero and less than M) second training images each containing the vehicle that is classified to another one of the states, different from the one of the states.