Image analysis technologies for assessing safety of vehicle operation
AssigneeState Farm Mutual Automobile Insurance Company
InventorsDingchao Zhang, Yuntao Li, Jeffrey S. Myers
Life of this patent
Estimating the term…
Abstract
Systems and methods for using image analysis techniques to assess unsafe driving conditions by a vehicle operator are discloses. According to aspects, a computing device may access and analyze image data depicting the vehicle operator. In analyzing the image, the computing device may measure certain visible metrics as depicted in the image data and compare the metrics to corresponding threshold values, and may accordingly determine whether the vehicle operator is exhibiting an unsafe driving condition. The computing device may generate and present alerts that indicate any determined unsafe driving condition.
Claims20
A system for assessing driving safety, comprising:
- at least one image sensor disposed on a vehicle and configured to capture image data, the image data comprising a plurality of image frames;
- a non-transitory memory storing computer-executable instructions;
- and
- a processor communicatively coupled to the at least one image sensor and the non-transitory memory, the processor being configured to execute the computer-executable instructions, wherein executing the computer-executable instructions causes the processor to:
- identify a portion of the plurality of image frames depicting a face of an operator of the vehicle,
- determine a first eye aspect ratio of the operator as depicted in the portion of the plurality of image frames,
- determine that the first eye aspect ratio is less than an eye aspect ratio threshold,
- determine a first number of consecutive image frames, of the portion of the plurality of image frames, in which the operator is depicted as having a second eye aspect ratio less than the eye aspect ratio threshold,
- determine that the first number of consecutive image frames exceeds an image frame threshold, and
- determine that an unsafe driving condition exists based at least in part on:
- the first eye aspect ratio being less than the eye aspect ratio threshold, and
- the first number of consecutive image frames exceeding the image frame threshold.
A computer-implemented method, comprising:
- identifying, from a plurality of image frames captured by an image sensor disposed on a vehicle, a portion of the plurality of image frames that depict a face of an operator of the vehicle,
- determining a first eye aspect ratio of the operator as depicted in the portion of the plurality of image frames,
- determine that the first eye aspect ratio is less than an eye aspect ratio threshold,
- determining a first number of consecutive image frames, of the portion of the plurality of image frames, in which the operator is depicted as having a second eye aspect ratio less than the eye aspect ratio threshold,
- determining that the first number of consecutive image frames exceeds an image frame threshold, and
- determining that an unsafe driving condition exists based at least in part on:
- the first eye aspect ratio being less than the eye aspect ratio threshold, and
- the first number of consecutive image frames exceeding the image frame threshold.
A non-transitory computer-readable medium, comprising:
- a plurality of instructions which, when executed by one or more processors, cause the one or more processors to:
- identify a portion of the plurality of image frames depicting a face of an operator of the vehicle,
- determine a first eye aspect ratio of the operator as depicted in the portion of the plurality of image frames,
- determine that the first eye aspect ratio is less than an eye aspect ratio threshold,
- determine a first number of consecutive image frames, of the portion of the plurality of image frames, in which the operator is depicted as having a second eye aspect ratio less than the eye aspect ratio threshold,
- determine that the first number of consecutive image frames exceeds an image frame threshold, and
- determine that an unsafe driving condition exists based at least in part on:
- the first eye aspect ratio being less than the eye aspect ratio threshold, and the first number of consecutive image frames exceeding the image frame threshold.
Dependencies are inferred from the claim text.