4results about How to "Remove motion blur" patented technology

This invention relates to a high-precision visual inspection device for pet food production lines, belonging to the field of pet food inspection technology. It includes a main body with a conveyor belt installed inside. A first inspection component is located at the upper end of the conveyor belt, used for preliminary inspection of stains and damaged areas on the material surface. A centering and rejection component is located on one side of the first inspection component, used for centering and rejecting unqualified materials during the conveying process. A first damage detection component is located inside the centering and rejection component, used for initial verification of damaged materials detected by the first inspection component. This invention significantly reduces the rate of missed and false detections through a tiered inspection mode of initial inspection with an industrial camera, initial verification with heating thermal imaging, and secondary verification with airflow temperature difference.

The application discloses an end-edge collaborative adaptive enhancement and coding method for low-light video analysis, comprising: a terminal device collects a low-light video stream in real time and synchronously monitors environmental light intensity, edge computing power and network bandwidth; an edge side generates a collaborative enhancement strategy based on multi-modal perception data, dynamically selects an enhancement level and a coding resolution, and delivers them to the terminal; the terminal executes brightness correction and contrast stretching through a lightweight spatial enhancement network, then encodes and transmits to the edge side according to the strategy resolution; after decoding the video stream, the edge side optimizes cross-frame motion compensation and noise suppression through a timing enhancement network; finally, a target detection model is input for inference, and the result is fed back to optimize the strategy. Through dynamic resource scheduling, division of labor and cooperation of neural enhancement networks and closed-loop feedback mechanism, the performance of low-light video analysis is significantly improved; through deep reinforcement learning, the enhancement level and resolution are optimized in real time, and the accuracy, delay and resource efficiency are balanced.

The application provides a ship load measurement method and system based on computer-aided images, and relates to the technical fields of computer vision and image processing. In view of the problems that in the prior art, when load measurement is performed, an effective response mechanism for the dynamic motion characteristics of a ship is lacked, the adaptability to bad weather such as rain and snow is poor, and a transient shielding compensation mechanism is lacked, the application adopts an unmanned aerial vehicle to cruise and collect video images, determines ship roll periods, trim periods and water splash distribution based on an optical flow method and a fast Fourier transform, constructs a motion phase function to predict a stable time and monitor a posture angle change rate in real time, controls the unmanned aerial vehicle to descend at a rain and snow actual falling speed to collect a draft image when the ship is stable, generates a composite image through multi-frame projection and time domain median filtering, and then performs rain and snow erasing and water splash removing, so that the interference of rain and snow and water splash on draft identification is reduced. The application improves the measurement precision, operation efficiency and environmental adaptability of load measurement.

This invention discloses a low-light enhancement method from the perspective of a drone, relating to the field of image processing and enhancement technology. It involves acquiring a sequence of consecutive low-light image frames of a target during drone flight, performing preprocessing operations including denoising and normalization to form a low-light image set, and using an image recognition algorithm to estimate motion between adjacent frames. This invention improves image clarity and visibility in low-light environments through dynamic range compression and detail enhancement processing. The dynamic range compression algorithm balances brightness differences in the images, avoiding local overexposure or underexposure, ensuring good visual effects under different lighting conditions. Detail enhancement processing, through multi-scale gradient fusion and adaptive sharpening, highlights texture and edge information in the image, improving detail clarity in low light. This allows the drone to more clearly identify targets when performing tasks at night or in low-light environments, improving the efficiency and accuracy of task execution.