Vicinity supervising device and method for supervising vicinity of vehicle

A method for supervising a vicinity of a vehicle comprising steps of:

• an image capturing step that captures a plurality of images in which an object is simultaneously captured at different locations;
• a matching processing step that calculates a parallax point and a reliability point, the parallax point being a number of pixel regions from which a parallax is calculated among a plurality of pixel regions divided by the plurality of images, and the reliability point being the number of pixel regions having high recognition reliability among the plurality of pixel regions;
• and
• an evaluation step that evaluates, based on the parallax point and the reliability point, an imaging environment where the plurality of images are captured, wherein
• the evaluation step includes:
• an evaluation value calculation step that calculates an evaluation value based on the following equation using the parallax point and the reliability point;
• a threshold calculation step that calculates a threshold used for evaluating the evaluation value;
• and
• a determination step that determines whether or not the imaging environment is deteriorated when a condition where the evaluation value is less than the threshold is met, wherein the evaluation value is given by
• E=R/P (1),
• where E represents the evaluation value, R represents the reliability point, and P represents the parallax point.

A non-transitory computer-readable medium having computer-executable instructions for supervising a vicinity of a vehicle, the computer-executable instructions comprising instructions for:

• capturing a plurality of images in which an object is simultaneously captured from different locations;
• calculating a parallax point and a reliability point, the parallax point being a number of pixel regions from which a parallax is calculated among a plurality of pixel regions divided by the plurality of images, and the reliability point being the number of pixel regions having high recognition reliability among the plurality of pixel regions;
• and
• evaluating, based on the parallax point and the reliability point, an imaging environment where the plurality of images are captured, wherein
• evaluating the imaging environment includes:
• calculating an evaluation value based on the following equation using the parallax point and the reliability point;
• calculating a threshold used for evaluating the evaluation value;
• and
• determining whether or not the imaging environment is deteriorated when a condition where the evaluation value is less than the threshold is met, wherein the evaluation value is given by
• E=R/P (1),
• where E represents the evaluation value, R represents the reliability point, and P represents the parallax point.