Night mode lens attached object detection method and system, terminal and storage medium

Abstract

The invention provides a night mode lens attached object detection method and system, a terminal and a storage medium, and the method comprises the following steps: searching one or more frames of images with a light source at the background, converting the images into a grey-scale map, and calculating the grey-scale histogram of the grey-scale map; grading pixel points in the grey level histogram, calculating spatial distances between different grey levels and other grey levels, and calculating the sum of distance values between the grey levels and the product of probability coefficients; therefore, obtaining saliency maps of different gray values, and separating out suspicious areas of the attachments; extracting a contour area which is fuzzy due to the attachments, carrying out statistical calculation on one or more evaluation indexes in the contour, judging whether the area is the attachments or not according to an index result, carrying out accumulative marking on the judgment area, and carrying out early warning triggering on a processing result of which the accumulative frequency exceeds an alarm threshold value. In a night mode or an environment with extremely low light intensity, attachments such as condensed water drops, fuzzy water spots and dark stains on the lens can be identified.

Description

Technical field [0001] The present invention relates to the technical field of automobile electronics, and in particular to a detection method, system, terminal and storage medium for night mode lens attachment. Background technique [0002] Among existing technologies, "Auto Valet Parking" has become one of the popular technologies in the field of autonomous driving, and it will also be an important milestone on the road to mass production of autonomous driving. As a complete self-driving car system, the AVP system drives the car at low speed or parks the car in a limited area, such as a parking lot or surrounding roads. In addition, as a function extension of parking assistance, it will also be one of the earliest commercialized fully automatic driving functions. [0003] During the driving of the vehicle, accidental reasons such as road conditions and weather are often encountered, which may cause stains on the lens and rain blockage. These scenarios have a destructive effect o...

AI Technical Summary

Problems solved by technology

[0003] During the driving process of the vehicle, accidental reasons such as road conditions and weather are often encountered, which will cause stains on the lens and rain cover. These situations have a destructive impact on the normal operation of the AVP system

Images