Method for detecting vehicle deviation, electronic device, and storage medium

An electronic device comprising:

• a processor;
• and
• a storage device that stories a plurality of instructions, which when executed by the processor, cause the processor to:
• acquire a first foreground image;
• perform a distortion correction on the first foreground image and obtain a first corrected image;
• perform a perspective transformation on the first corrected image and obtain an aerial view;
• generate a distribution map of non-zero pixel points corresponding to the aerial view, based on a number of non-zero pixel points in each column of pixel points in the aerial view, the distribution map of non-zero pixel points is provided with a first peak and a second peak, and the first peak being on the left of the second peak;
• determine an initial position of a left lane line in the aerial view according to the first peak, and determine an initial position of a right lane line in the aerial view according to the second peak;
• determine the initial position of the left lane line and the initial position of the right lane line as a starting position of a sliding window respectively, and start moving the sliding window in the aerial view from the starting position;
• fit a first curve corresponding to the left lane line and a second curve corresponding to the right lane line according to non-zero pixel points covered by the sliding window while moving the sliding window and before arriving at a current position of the sliding window respectively;
• fit a third curve corresponding to the left lane line according to the first curve corresponding to the left lane line and non-zero pixel points covered by the sliding window at the current position, and fit a fourth curve corresponding to the right lane line according to the second curve corresponding to the right lane line and non-zero pixel points covered by the sliding window at the current position, dynamically adjusting a movement of the sliding window according to the first curve and the second curve;
• determine the left lane line according to the third curve corresponding to the left lane line, and determine the right lane line according to the fourth curve corresponding to the right lane line;
• calculate a first distance between a vehicle and the left lane line, and calculate a second distance between the vehicle and the right lane line;
• and
• determine whether the vehicle deviates from any one of the left lane line and the right lane line according to the first distance and the second distance.

A non-transitory storage medium having stored thereon at least one computer-readable instructions that, when executed by a processor of an electronic device, causes the processor to perform a method for adjusting moment cloud density, the method comprising:

• acquiring a first foreground image;
• performing a distortion correction on the first foreground image and obtaining a first corrected image;
• performing a perspective transformation on the first corrected image and obtaining an aerial view;
• generating a distribution map of non-zero pixel points corresponding to the aerial view, based on a number of non-zero pixel points in each column of pixel points in the aerial view, the distribution map of non-zero pixel points is provided with a first peak and a second peak, and the first peak being on the left of the second peak;
• determining an initial position of a left lane line in the aerial view according to the first peak, and determining an initial position of a right lane line in the aerial view according to the second peak;
• determining the initial position of the left lane line and the initial position of the right lane line as a starting position of a sliding window respectively, and starting moving the sliding window in the aerial view from the starting position;
• fitting a first curve corresponding to the left lane line and a second curve corresponding to the right lane line according to non-zero pixel points covered by the sliding window while moving the sliding window and before arriving at a current position of the sliding window respectively;
• fitting a third curve corresponding to the left lane line according to the first curve corresponding to the left lane line and non-zero pixel points covered by the sliding window at the current position, and fitting a fourth curve corresponding to the right lane line according to the second curve corresponding to the right lane line and non-zero pixel points covered by the sliding window at the current position, dynamically adjusting a movement of the sliding window according to the first curve and the second curve;
• determining the left lane line according to the third curve corresponding to the left lane line, and determining the right lane line according to the fourth curve corresponding to the right lane line;
• calculating a first distance between a vehicle and the left lane line, and calculating a second distance between the vehicle and the right lane line;
• and
• determining whether the vehicle deviates from any one of the left lane line and the right lane line according to the first distance and the second distance.