Deep learning-based black smoke blackness detection method and device

Abstract

The invention provides a deep learning-based black smoke blackness detection method and device. The method comprises the following steps: acquiring a video stream of a vehicle shot by a camera; inputting a video frame in the video stream into a target detection network to obtain a vehicle position; determining black smoke position information of a black smoke to-be-detected area in the video frame based on the vehicle position; and determining the relative gray scale of the black smoke based on the gray scale value of the black smoke position in the video frame and the background reference image. The video frame in the video stream of the vehicle shot by the camera is processed in a deep learning mode, and the relative gray scale of the black smoke of the black smoke vehicle is calculated by using the background reference image, so that the calculation result is more accurate. Therefore, the black smoke blackness of the black smoke vehicle can be accurately detected in real time, the vehicle does not need to be stopped, and meanwhile, the equipment cost and the maintenance cost are reduced.

Description

technical field [0001] The invention relates to the field of traffic technology, in particular to a deep learning-based method and device for detecting black smoke blackness. Background technique [0002] In recent years, the blackness detection of smoky vehicles mainly includes contact detection and remote sensing detection. Due to the large and expensive equipment, high maintenance cost, and many limitations of the test conditions, these two methods lead to high cost and low test efficiency. Moreover, the contact detection method requires the vehicle to be in an abnormal driving state, and cannot obtain the true normal driving emission of the vehicle. The cost of remote sensing detection is too high, not only the normal maintenance of software and hardware is required, but also the maintenance of standard gas is required, which greatly increases the cost of maintenance. [0003] Therefore, how to propose a detection scheme for a smoky car, which can check the blackness o...

AI Technical Summary

Problems solved by technology

Due to the large and expensive equipment, high maintenance cost, and many limitations of the test conditions, these two methods lead to high cost and low test efficiency.

Moreover, the contact detection method requires the vehicle to be in an abnormal driving state, and cannot obtain the real normal driving emission of the vehicle.

The cost of remote sensing detection is too high, not only the normal maintenance of software and hardware is required, but also the maintenance of standard gas is required, which greatly increases the cost of maintenance

Images