Signal lamp time domain state detection method, model training method and related device

Abstract

The invention discloses a signal lamp time domain state detection method, a model training method and a related device, and the method comprises the steps: obtaining an image sequence which at least comprises two continuous frames of images, and the images comprise signal lamps; and inputting the images in the image sequence into the signal lamp time domain state detection model according to the time sequence of the images to obtain the time domain state of the signal lamp. Through the above mode, the change information of the signal lamp in the time domain can be identified, and the detection accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a signal light time-domain state detection method, a model training method and a related device. Background technique [0002] In the intelligent traffic electric police scene, the accurate positioning of signal lights and state detection technology are very important for regulating vehicle behavior, but the existing high-definition digital cameras can simultaneously identify information such as vehicle type, body color, license plate number, and face in the vehicle. Streaming and capturing pictures require long exposure time, the pixel value of the signal light area is oversaturated, the color of the red light is yellow or white, and the color is close to the yellow light, making it difficult to distinguish the status of the red light and the yellow light. [0003] There are defects in the single-frame image detection technology, such as the red light and the yellow lig...

AI Technical Summary

Problems solved by technology

[0002] In the intelligent traffic electric police scene, accurate positioning of signal lights and state detection technology are crucial to regulate vehicle behavior. Streaming and snapping pictures requires a long exposure time, the pixel value of the signal light area is oversaturated, and the color of the red light is yellowish or white, which is close to the color of the yellow light, making it difficult to distinguish the status of the red light and the yellow light

[0003] There are defects in the single-frame image detection technology, such as the red light and the yellow light are difficult to distinguish in color, and sometimes it is necessary to use the electronic signal detector to output the signal light status, which increases the workload of technicians and additional equipment for signal detectors, and the accuracy rate is low. and increase product cost

Images