Automobile data recorder video detection method and device based on ffmpeg and image recognition

Abstract

The invention discloses an automobile data recorder video detection method and device based on ffmpeg and image recognition, and the method comprises the following steps: obtaining a preset resolution image of a first frame in the first second of a video file, comparing the preset resolution image with a thumbnail of the video file, and determining whether the video file is abnormal or not according to the difference degree; obtaining an original image of one frame of the video file per second based on ffmpeg, cutting out a time watermark region, extracting a time watermark value in the time watermark region based on image recognition, and judging whether the video file is continuous and normally segmented according to the time watermark value; and comparing the real time length of the video file with a preset video time length, and judging whether the video file is abnormal or not according to the error degree. According to the method, a large number of video files can be automatically detected in a short time, videos possibly having problems and specific time points when the problems occur are positioned, testing manpower is saved, testing efficiency and testing accuracy are improved, and testing time is shortened.

Description

technical field [0001] The invention relates to the technical field of video recording testing of driving recorders, in particular to a method and device for detecting video recordings of driving recorders based on ffmpeg and image recognition. Background technique [0002] As the driving recorder market continues to boom, the quality of the product is becoming more and more important. As the core function of the driving recorder, video recording has strict requirements different from other products. During the testing process, there are many video files, many test items, and manual testing. time-consuming problem. [0003] A large number of video files will be generated during the working process of the driving recorder. For example, a 16G TF with a coverage threshold of 90%, and a 1-minute video file of 100M as an example, can generate about 144 files, a total of 2.5 hours of video recording , if through the ordinary manual test method, it will take 2.5 hours to play all ...

AI Technical Summary

Problems solved by technology

[0002] As the driving recorder market continues to boom, the quality of the product is becoming more and more important. As the core function of the driving recorder, video recording has strict requirements different from other products. During the testing process, there are many video files, many test items, and manual testing. time consuming problem

[0003] A large number of video files will be generated during the working process of the driving recorder. For example, a 16G TF with a coverage threshold of 90%, and a 1-minute video file of 100M as an example, can generate about 144 files, a total of 2.5 hours of video recording , if through the ordinary manual test method, it will take 2.5 hours to play all the video files from the beginning to the end, and then check other items according to the above video requirements, the time required is far more than 2.5 hours, such as the number of TF cards doubled, the time required is clearly unacceptable

Images