2results about How to "Suppress saturation" patented technology

The application provides a UAV-InSAR-based magnetic suspension system multi-point collaborative reinforcement learning compensation control method, system, device and medium, the method comprises the following steps: using a UAV to carry a lightweight X-band interferometric synthetic aperture radar system to carry out high-precision surveying and mapping on a magnetic suspension line, and constructing an orbit irregularity power spectrum model; a hierarchical control system is constructed, the amplitude saturation controller in the lower layer generates a basic electromagnetic force control law according to the state quantity of the current suspension point; the upper layer compensation controller based on reinforcement learning is an agent, interacts with the environment composed of the suspension frame, the track and the amplitude saturation controller, trains by using the standardized irregularity function obtained from the track irregularity power spectrum model, and outputs the compensation control quantity for each suspension point; the basic electromagnetic force control law and the compensation control quantity are superimposed to generate the total electromagnetic force control law of each suspension point, and the suspension system is actively compensated and globally stably suspended. The application significantly improves the comprehensive control performance of the suspension system.

The invention discloses a signal lamp halo processing method, a signal lamp halo processing device and electronic equipment. The signal lamp halo processing method comprises the following steps: acquiring a bright frame and a dark frame for capturing the same Bayer; performing gamma mapping on the highlight area in the dark frame to obtain a fusion mask of the bright frame and the dark frame; performing brightness and saturation suppression on the original RGB data of the dark frame based on the pixel values of the original RGB data of the dark frame in different color channels to obtain first RGB data after dark frame suppression; converting the first RGB data into first YUV data after dark frame optimization; fusing the first YUV data with the original YUV data of the bright frame based on the current height and the fusion mask in combination with the pixel-level gradient weight and the height gradient light intensity gain of the current pixel to obtain second YUV data of a first fusion image of the bright frame and the dark frame; converting the first RGB data into second RGB data of the first fused image; and in combination with a preset halo removal level, performing halo removal processing on a halo region in the second RGB data of the first fused image.