17 results about "Brightness perception" patented technology

Described are toric contact lenses that contain high energy visible (HEV) light absorbing compounds and their use for improving various vision attributes in astigmatic contact lens wearers, such as brightness perception and visual range.

The invention discloses a wind power blade tip detection method and system based on brightness self-adaption and multi-scale attention, and the method comprises the following steps: S1, collecting a plurality of wind power blade images including blade tips, carrying out the preprocessing, and constructing a data set; s2, replacing a first convolutional layer in a backbone network in the original YOLOv8 network with a brightness perception evaluation and branch fusion module, a small target sensitive feature extraction backbone network and a multi-scale context attention module which are connected in sequence, and after replacement, obtaining an improved YOLOv8 network; s3, training the improved YOLOv8 network by using the data set to obtain a trained YOLOv8 network; and S4, deploying the trained YOLOv8 network to an equipment end, and carrying out wind power blade tip detection to obtain a detection result. According to the method, combined detection and dynamic tracking of the blade and the blade tip are combined, and the blade tip positioning stability and clearance estimation precision are improved.

The invention discloses a multi-dimensional visual uniformity compensation and enhancement method for a curved-surface tail lamp. The method comprises the following steps of S1, performing angle and distance compensation on a display image of the curved-surface tail lamp; s2, splicing compensation is carried out on the curved surface tail lamp display image; and S3, performing color compensation on the curved surface tail lamp display image. The invention provides a multi-dimensional visual uniformity compensation and enhancement method for a curved surface tail lamp, so that the brightness perception of the whole tail lamp tends to be consistent no matter from which angle an observer sees in a preset observation area, and the brightness difference caused by the curved surface is eliminated. On the premise that hardware is not changed, edge transition is softened and strengthened through an algorithm, the abrupt feeling of a splicing seam is greatly weakened, and the integrity and continuity of display are improved. It is guaranteed that the tail lamp displays any color accurately and consistently, LED supersaturation or damage caused by excessive driving is avoided, reliability is improved, and the service life is prolonged.

The invention discloses an object recognition method and related equipment. The method comprises the following steps: acquiring a palm vein image and an image brightness perception model of a to-be-recognized object; performing feature extraction on the palm vein image to obtain vein feature information of the palm vein image; performing brightness sensing processing on the vein feature information through an image brightness sensing model to obtain vein brightness information; performing vein intensity detection on the palm vein image based on the vein brightness information; when it is detected that the vein intensity of the palm vein image does not meet a preset vein intensity condition, brightness adjustment processing is carried out on vein brightness information of the palm vein image, and target vein brightness information is obtained; adjusting the image brightness of the palm vein image according to the target vein brightness information to obtain a target palm vein image; and performing object recognition on the to-be-recognized object through the target palm vein image to obtain an object recognition result. According to the invention, the visibility of palm veins can be improved, so that the accuracy of object recognition is remarkably improved.

The application belongs to the technical field of pedestrian detection, and discloses a cross-scale infrared pedestrian detection method, system, medium, equipment and terminal, constructs a brightness perception module, obtains a reconstructed background image and a brightness feature image by combining a quadtree-Bessel interpolation operator and a guided filter, designs an EG-Chimp optimization model, iteratively optimizes a constructed objective function, obtains a dynamic feature optimization image, introduces a BiFPN feature pyramid structure under a YOLOv5 algorithm framework, designs a cross-scale feature fusion module to learn weight parameters between different scale features, and introduces a CIOU regression loss function to realize a cross-scale infrared pedestrian detection task. The application cross-fuses sensor technology and target detection algorithms, improves the pedestrian target feature expression capability of a detection network, improves the infrared pedestrian detection performance under multi-scale and partial occlusion conditions, and can realize cross-scale infrared pedestrian detection tasks in various complex environments.

The application provides a video special effect processing method, an electronic device and a storage medium. The method comprises the following steps: obtaining a to-be-processed video, performing frame segmentation processing on the to-be-processed video to obtain a plurality of processing frames; determining a foreground probability value corresponding to each pixel in each processing frame based on a pre-trained image segmentation model, determining a target perceived brightness value corresponding to each pixel in each processing frame according to a color component of each pixel in each processing frame, and determining fusion transparency information of each pixel in each processing frame according to the foreground probability value of each pixel in each processing frame and the target perceived brightness value of each pixel in each processing frame; and obtaining a target video according to the fusion transparency information of each pixel in each processing frame. The application performs image segmentation processing and brightness perception processing on the processing frames respectively, and fuses the obtained foreground probability value and target perceived brightness value, so that the target video meets the transparency processing requirements of luminous bodies and entities in the special effect video.

The application discloses a display screen environment adaptive brightness adjusting method and device, which fuses environmental illumination data and facial brightness data to form a brightness perception data frame, constructs an illumination distribution matrix through blink cycle shielding and scene type detection; performs illumination jump characteristic analysis on the illumination distribution matrix to identify a high-illumination jump area, determines an adjusting reference position through continuous jump attenuation priority enhancement analysis, positions a backlight adjusting node after comparing the adjusting reference position with the brightness perception data frame; determines backlight driving parameters according to the backlight adjusting node and generates a backlight optimization sequence, generates an adjusting configuration scheme through advanced multi-scene brightness fusion; determines an adjusting period based on visual masking window alignment of the adjusting configuration scheme, and executes PWM closed-loop modulation to output a brightness adjusting instruction. The application integrates multi-source perception fusion, jump identification and visual masking execution into a unified adjusting process, and improves the matching degree of display screen brightness adjustment and user visual comfort.

This invention belongs to the field of low-light image enhancement, specifically relating to a low-light image enhancement method based on spectral interaction. The method includes constructing a low-light image enhancement model, which comprises a spatial feature extraction module, a spectral real part interaction module, and a brightness-perceived fusion module. The model is trained, and the trained low-light image enhancement model is used to enhance low-light images. This invention employs a two-branch fusion strategy, which effectively utilizes the advantages of both branches while avoiding their respective shortcomings, further improving image quality and clarity.

The invention relates to a brightness adjusting method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: determining a first brightness value of a display screen of the electronic equipment in response to an ambient light brightness value obtained by the electronic equipment; performing nonlinear conversion on the first brightness value and the second brightness value to obtain a first sensing brightness value and a second sensing brightness value; and based on the first perception brightness value and the second perception brightness value, perception brightness values at different moments within the target adjustment duration are determined, and the brightness value of the display screen is adjusted based on the perception brightness values at different moments within the target adjustment duration. By introducing a perception brightness value, a nonlinear process of human eyes for brightness perception is simulated. Moreover, through the dynamic adjustment process of the perceived brightness value, the dynamic adjustment process of the brightness value of the display screen is realized, so that the dynamic adjustment process is smooth and non-inductive, and the requirement of a user for visual comfort is met to the greatest extent.

This application relates to the field of lighting technology, and discloses a spectral control method, device, computer equipment, and storage medium, including receiving a brightness adjustment command, the brightness adjustment command carrying target brightness level information; searching for the driving parameters of each light-emitting channel from a preset driving parameter table according to the target brightness level information, or calculating the driving parameters of each light-emitting channel according to a preset algorithm; outputting the driving parameters to a multi-channel LED driving circuit, so that the driving circuit adjusts the driving current or driving duty cycle of each channel, controlling the multi-channel LED to output a composite spectrum that matches the target brightness level and has high color recognition; the composite spectrum has a preset target spectral structure at the target brightness level, so as to solve the technical problem that the color rendering effect and brightness perception of existing 2700k–3500k warm white LED light sources deteriorate in low-illuminance environments.

A wind turbine blade tip detection method and system based on brightness adaptation and multi-scale attention, comprising the following steps: S1, first collect multiple wind turbine blade images containing the blade tip, and after preprocessing, construct a data set; S2, replace the first convolutional layer in the backbone network of the original YOLOv8 network with a brightness perception evaluation and branch fusion module, a small target sensitive feature extraction backbone network and a multi-scale context attention module connected in turn, and after replacement, obtain an improved YOLOv8 network; S3, train the improved YOLOv8 network using the data set to obtain a trained YOLOv8 network; S4, deploy the trained YOLOv8 network to the device end and perform wind turbine blade tip detection to obtain a detection result. The present application combines blade and blade tip joint detection and dynamic tracking, and improves the stability of blade tip positioning and the accuracy of clearance estimation.

The invention discloses a display image content-based brightness perception optimization method, which is applied to a process of displaying an image by a display device, and comprises the following steps of: preprocessing the display image through image structural similarity judgment and image adjacent pixel classification, and introducing the complexity of a display image content factor, comprise image content contrast, shape, size, position and foreground and background contrast coefficient, and the brightness perception optimization of the display image based on the display image content is realized by combining subjective perception brightness scoring, so that the brightness required by the display image content can be accurately predicted and assisted; a user can read a display picture and obtain specific information prompts more efficiently and comfortably, meanwhile, the method can serve as a feedback mechanism of display driving, and the overall display power consumption is reduced. The method can be applied to panel and AR near-to-eye display, and higher adaptability and use comfort of screen display to brightness are enhanced.

The invention discloses an image quality evaluation method based on scene content and visual perception thereof, relates to the technical field of image communication, and provides an image quality evaluation method and model in combination with real scene content characteristics of an image and visual characteristics of masking, contrast sensitivity, brightness perception nonlinearity and comfort of a human visual system. In the method, firstly, sensed image information is divided into basic visual information, image texture and complexity sensing visual information, image definition and sensing visual information; respectively calculating the quality scores of the three parts of visual information by adopting the mode of defining the image quality by using the contrast ratio, and weighting and synthesizing the quality scores of the three parts of visual information; and finally, processing the quality scores of all the sub-blocks by adopting a global average pooling method to obtain an image quality evaluation score. According to the method, visual characteristics are fully utilized, a proper amount of effective image characteristics are extracted, and it is effectively guaranteed that the quality evaluation model has good precision, generalization and complexity.

In described techniques, a depth of an object may be determined with respect to a head-mounted device (HMD). A gaze duration with respect to the object may be determined, relative to a gaze duration threshold. Then, based on the depth and on the gaze duration exceeding the gaze duration threshold, virtual content may be rendered at a virtual depth with respect to the HMD that is different than the depth.

This invention discloses a lightweight target detection method and network for low-contrast, dim, and extended targets, belonging to the field of computer vision and target detection technology. Based on the YOLO11n architecture, a YOLO11-DET detection model is constructed. A LECA dim enhancement channel attention module is integrated at the backbone network entry point, performing dual-path parallel weighting of global brightness perception and local contrast perception on the input features to achieve channel and spatial collaborative enhancement. The neck network uses a DSFPN sparse dilated feature pyramid module, expanding the receptive field through multi-level dilated convolutions and filtering invalid background gradients with sparse gating. The cross-scale fusion node uses a MAIM multi-scale adaptive fusion module, decomposing features into high- and low-frequency components and implementing differentiated weighted fusion. The detection head adopts a three-scale decoupled structure, using a CIoU loss function with an added dim target perception regularization term to complete classification and regression. This invention can significantly improve the detection accuracy of low-contrast, dim, and extended targets, and can be widely applied in scenarios such as infrared early warning and nighttime surveillance.

The present application relates to a kind of low perceptible adversarial sample generation method based on human visual optimization, belong to artificial intelligence security field.For the problem that existing adversarial sample disturbance is easily perceived by naked eye, after initializing image, target model and disturbance parameter, the comprehensive objective function of fusion classification loss and perception constraint is constructed to carry out iterative optimization in the method.Specifically, it includes: by visual brightness perception and color channel differentiation allocation constraint, control disturbance in human eye sensitive threshold;Gradient regularization, norm restriction and spatial sparsity are used to optimize disturbance distribution;Dynamic adjustment constraint weight parameter to adapt to different image features.Finally, the optimized disturbance and original image are fused to generate adversarial sample.The present application significantly reduces the visibility of disturbance in brightness, color and texture structure while ensuring attack efficiency, and the adversarial sample generated has little visual difference with the original image, and has stronger concealment.

This application provides a method and system for optimizing the energy consumption of bus stop signs based on multi-source data fusion, belonging to the field of display energy consumption optimization technology. The method involves real-time acquisition of the brightness of the bus stop sign's display screen and the illuminance and color temperature information of the current display environment; determining the brightness perception domain that a viewer can perceive under the current display environment based on the screen brightness and illuminance and color temperature information; acquiring the current display content of the bus stop sign; performing block-based equivalent optimization on the current display content based on the brightness perception domain; and generating an optimized display image of the bus stop sign under the current display environment. The optimized display image is then used to replace the current display content of the bus stop sign, thereby completing the display energy consumption optimization of the bus stop sign. This application, through the above technical solution, can combine ambient lighting characteristics and viewer brightness perception characteristics to perform differentiated optimization of display content, achieving accuracy in display energy consumption optimization under different environmental conditions.