37 results about "Human visual perception" patented technology

The invention discloses a non-reference image quality evaluation method and device based on multi-perception feature fusion and dynamic enhancement, and the method comprises the steps: obtaining the quality information of a multi-domain distorted image based on superpixel segmentation and Gaussian kernel filtering texture generation; quality related feature extraction is performed on multi-domain information through a semantic perception module and a distortion perception module, bidirectional modulation is performed on global visual features of an original distorted image through a cross attention mechanism, and dynamic fusion of multiple perception features is realized; through a parallel feature enhancement unit formed by local adaptive filtering of a visual self-attention block and a dynamic residual block, dynamic allocation of perception modes to different content areas is realized; generating a weighted quality score consistent with human visual perception through a weighted dual-path regression device; and outputting a predicted score consistent with the human score from the distorted image through the three sub-networks. According to the method, the problems of insufficient adaptability to complex content of a distorted image and low local distortion sensitivity are effectively solved.

The invention relates to the technical field of digital image processing, and discloses an image defogging method based on an atmospheric scattering model and color correction, and the method comprises the following steps: S1, carrying out the color correction of a foggy image with color cast; s2, calculating an atmospheric light value of the foggy image; s3, calculating the transmissivity value of the foggy image; s4, recovering the defogged image by adopting an atmospheric scattering model according to the atmospheric light value and the transmissivity value; and S5, solving a defogged image after adaptive brightness enhancement and adaptive contrast enhancement. According to the method, the color of the obtained defogged image can be recovered to be natural, the phenomena of color cast, incomplete defogging, detail information loss and overall darkness of the image are improved, the recovered defogged image better conforms to the perception of human eyes, meanwhile, the implementation process is simple, the time complexity is low, and better defogging efficiency is achieved.

The invention discloses a quantitative detection method for anti-perspective performance of a textile in a complex light environment, and belongs to the technical field of new material detection, a micro gap is arranged between the textile to be detected and a variable-frequency gray scale target to simulate a non-clinging state when clothes are worn and excite Fresnel diffraction and subsurface scattering effects, and the anti-perspective performance of the textile is detected. Complex illumination conditions such as backlight and sidelight are simulated by adjusting the light intensity ratio, and after a target perspective image is acquired by using an image acquisition unit, the modulation transfer function attenuation rate of a to-be-detected textile to the target is calculated, so that the anti-perspective performance of the textile is quantitatively represented; the interference of glare on the surface of the high-gloss fabric is effectively eliminated by introducing an orthogonal polarization modulation technology, and a detection result is highly consistent with the visual perception of human eyes by adopting a specific light source spectrum simulating the skin color of a human body; compared with a traditional light transmittance method, the method has the advantages that the dimension crossing from luminous flux measurement to image information fidelity evaluation is realized, and the accuracy, reliability and practicability of detection are remarkably improved.

The application discloses a perceptual-geometry joint code rate control method, system and medium, and belongs to the field of video coding. The method comprises the following steps: assigning weights to each CTU in each frame in a video according to the VVC standard; for each I frame, calculating the perceptual-geometry joint weight of each CTU in the I frame, and updating the weight of each CTU in the I frame; and assigning a code rate to each CTU according to the weight of each CTU in each frame to complete code rate control. The application can effectively eliminate geometric redundancy and improve human visual perception consistency, and promote efficient transmission of high-resolution videos.

The application discloses a kind of based on layered feature fusion's no reference image usability evaluation method.There is following step: first, respectively extracting the low-level picture quality feature vector of the image to be evaluated, middle layer structure feature vector and high-level semantic feature vector;Subsequently, respectively to feature vector is normalized and splicing;Then, total feature vector is input to the regression network of integrated layered attention fusion ware, the network passes through multi-head self-attention mechanism dynamically learns the contribution weight of each level feature to the final availability score, and carries out regression prediction, outputs the availability evaluation score of image.The application realizes the fundamental change of evaluation target from "human visual perception quality" to "machine task availability" by systematically fusing multidimensional features from picture quality to semantics, and the evaluation result is strongly related to the performance of high-level visual tasks such as object detection and pose estimation, and is suitable for image screening and quality control in scenarios such as autonomous driving and intelligent monitoring.

The invention discloses a lamp light quality detection system and method, relates to the technical field of lamp detection, and solves the problems that traditional detection depends on physical parameters and cannot reflect real visual perception of a human body, and the system comprises a spectacle frame, and a physiological signal sensor, a signal processing unit and a light quality detection unit which are integrated on the spectacle frame. Visual physiological reaction signals of a user under illumination of the lamp are collected in real time through the sensor, and after physiological features are extracted through the processing unit, quantitative detection indexes of light quality are output through a model built in the detection unit. According to the invention, objective and personalized in-situ detection and evaluation of the light quality of the lamp in a natural eye using state are realized, and the method is mainly suitable for field detection and health evaluation of various lighting environments such as classrooms and offices.

This disclosure presents an efficient rendering method based on scene-aware mapping for complex scenes. One specific implementation of this method includes acquiring a scene model, camera parameters, and user gaze point information corresponding to the target scene; performing spatial mapping processing on the scene model based on the camera parameters to obtain a two-dimensional geometric scene graph; generating a consistent visual importance graph based on the user gaze point information and the two-dimensional geometric scene graph; generating a pixel size control graph based on the two-dimensional geometric scene graph and the consistent visual importance graph; and rendering the two-dimensional geometric scene graph based on the pixel size control graph to obtain a rendered scene image. This implementation can reduce the computational resources required for rendering and improve rendering speed while ensuring the quality of human visual perception.

The invention discloses a multispectral optical signal acquisition and AI intelligent analysis device and method, and belongs to the technical field of optical signal detection and artificial intelligence. A multi-spectral optical signal intelligent analysis deep network system (MSS-IDNS) is defined as a core, and the system takes a 300-1000nm multi-spectral optical signal as an input carrier and can be fused with various deep learning models. The device comprises a multispectral optical signal acquisition terminal and an AI intelligent analysis module. The method comprises the six steps of optical signal collection, data preprocessing, feature extraction, AI analysis, model iteration and intelligent response, so that intelligent analysis and biological state recognition of optical signals are completed. The method breaks through the human visual perception boundary and adapts to multiple scenes, core hardware is an existing mature industrial product, batch production can be achieved, and the method has extremely high civilian mass production potential and commercial value.

This application discloses a display device, including a display panel, a backlight module, a controller, and a memory. The memory stores a network model and human visual perception HK effect data. The controller first acquires image data and inputs it along with the HK effect data into the network model. After extracting image feature vectors and HK feature vectors, feature fusion is performed to obtain fused features. The network model then processes the fused features to obtain target image data. Based on the target image data, backlight values ​​and pixel drive values ​​are generated respectively, thereby controlling the backlight module and the display panel to complete image display. This solution not only improves the display effect but also enhances the user experience.

This invention discloses a lightweight low-light image enhancement method based on residual dense blocks, comprising the following steps: acquiring a paired low-light image dataset; constructing a conditional generative adversarial network (GAN) model, including designing a lightweight generator network based on residual dense blocks and channel attention mechanisms, and a fully convolutional discriminator network; determining a multimodal loss function based on global similarity loss, structural similarity loss, content similarity loss, color similarity loss, and local texture loss; and training and testing the GAN model. This invention can process 400*600 low-light images at 36 frames per second on an RTX 2080 Ti graphics card. The low-light images enhanced by this invention are more consistent with human visual perception and exhibit superior performance on common image evaluation metrics such as peak signal-to-noise ratio and structural similarity.

The application discloses a physical perception fusion driven adaptive texture generation optimization method and system. The method comprises the following steps: collecting material spectral reflectance data and material surface micro texture image data, and performing pretreatment; constructing an initial physical and perception fusion driven texture generation model; adopting a cross-domain joint training strategy, training and optimizing the model through an alternating optimization scheme of physical priority-perception priority-joint fine-tuning, to obtain a physical and perception fusion driven texture generation model; and performing actual texture generation based on the obtained physical and perception fusion driven texture generation model. The method fuses physical laws and human visual perception mechanisms in depth, constructs a new generation of adaptive texture optimization framework, solves the long-standing "physical-perception" split problem in the field of high-fidelity rendering, and realizes a breakthrough in spectral modeling accuracy, rendering efficiency and visual quality.

The embodiment of the invention provides an electronic image stabilization method, which is used for processing visible light video data of an airborne photoelectric hanging bin, and comprises the following steps of: 1, acquiring video sequence basic information; step 2, feature point detection and motion estimation; step 3, performing abnormal processing on the motion model; step 4, motion trail smoothing processing; 5, image stabilization transformation and post-processing are carried out; and step 6, outputting a result. Aiming at visible light video data of an airborne photoelectric pod, various forms of jitter motion can be accurately captured and compensated through multi-scale feature point tracking and intelligent motion estimation. Compared with a traditional method, the method shows higher precision and stability when a complex motion mode is processed. Especially in scenes with slight motion blur, illumination variation or partial shielding, the method can still keep reliable image stabilization performance. The smooth processing of the motion trail enables the finally output video to eliminate uncomfortable jittering and maintain the intentional motion of the camera, thereby conforming to the visual perception characteristics of human beings.

This invention provides a method, device, and display screen for brightness control of a MiniLED display screen based on multi-source environmental perception. By acquiring dynamic changes in ambient light and content features of the currently displayed image, the method inputs these information into a pre-defined human visual perception model to analyze perception requirements, obtaining a set of perception requirements features matching the current viewing scene. Based on this feature set, a dynamic mapping mechanism is invoked to construct a brightness mapping relationship, generating a dynamic brightness mapping curve reflecting the synergistic effect of ambient light and image content. A pre-constructed partitioned light effect model is then invoked, and inverse solving is performed based on the model and the dynamic brightness mapping curve to generate partitioned calibration driving parameters, which are then sent to the MiniLED backlight module for brightness adjustment. This invention effectively improves the accuracy of brightness control and visual comfort of the MiniLED display screen, while ensuring consistency between the actual hardware output and the target brightness.

This invention discloses a low-light image fusion method based on lightweight feature extraction and color restoration. A lightweight feature extraction (LFE) module extracts local and global features of the image in a lightweight manner, preserving image features to the maximum extent. A fusion module (FB) is used for image fusion and reconstruction to obtain a grayscale fused image that accurately describes the detailed features of the input image. A color restoration network (CR) is used to colorize the grayscale fused image, resulting in a color fused image that better conforms to human visual perception. Finally, a weighted adaptive loss function is applied, adaptively adjusting the weights of the loss function to constrain the network to achieve the optimal fusion result.

This application provides a lighting adjustment method, device, equipment, and medium based on the characteristics of human visual perception. The method includes: determining a base duty cycle for driving intelligent lighting based on the power-law characteristics of human vision; acquiring the actual ambient light intensity and the actual junction temperature of the luminaire; determining a light compensation coefficient based on the actual ambient light intensity; determining a temperature compensation coefficient based on the actual junction temperature of the luminaire; determining the actual duty cycle for driving intelligent lighting based on the base duty cycle, the light compensation coefficient, and the temperature compensation coefficient; and adjusting the brightness of the intelligent lighting based on the actual duty cycle. This application constructs a nonlinear dimming map based on the power-law characteristics of human vision, achieving a high degree of matching with visual perception; it integrates ambient light and temperature compensation mechanisms to ensure dimming accuracy; and it effectively solves the problems of low brightness flicker, coarse adjustment, and visual mismatch existing in existing PWM dimming, achieving highly refined, flicker-free, and energy-efficient intelligent dimming.

The application discloses a kind of based on inverted pyramid structure multi-scale attention mechanism's no reference image quality evaluation method, it is applicable to image processing field, including the following steps: first, the distorted image dataset is preprocessed;The data input to feature extraction network after processing is completed, four different scale image features are extracted using decomposition large kernel convolution operation;Four scale features extracted are adjusted to the same spatial size by adaptive average pooling, and learnable position coding is added for each spatial position.Subsequently, cross-scale attention mechanism (CSA block) is used to gradually fuse high-level semantic information into low-level features;These distorted features with semantic perception are aggregated by multilayer perceptron MLP, and finally the feature representation output by MLP is mapped into a quality score using a fully connected layer.The method introduces large kernel convolution, uses inverted pyramid structure in multi-scale feature network, and the extracted features are more consistent with human visual perception characteristics, making the image quality evaluation more accurate.

The application belongs to the technical field of deep learning, and particularly relates to an image quality evaluation method based on saliency information fusion, which comprises the following steps: firstly, extracting a saliency target mask of an image; then, learning the interaction relationship between each component by encoding the features of the salient region and the non-salient region through an attention mechanism; then, enhancing the features extracted by the network and improving the global context perception ability through a channel decoupling spatial attention module; finally, designing a saliency target guided Transformer network, realizing the deep fusion of saliency information and spatial domain features through a self-attention mechanism and a cross-attention mechanism, so as to more effectively improve the performance of image quality evaluation. The salient target region and the non-salient target region are divided in the form of components, and the self-attention is calculated between different components and in the same component, so that the salient target information is fully utilized, and more effective and more human visual perception conforming feature fusion is realized.

Provided herein are methods, apparatuses, computer program products, and systems for fluorescence imaging. One method can include activating an ultraviolet (UV) light source to transmit UV light at a predetermined wavelength that is below a band of human visual perception to illuminate a region of a human body; generating a fluorescent image of the region of the human body based on fluorescent signals that are emitted from the region of the human body in response to illumination using the UV light and are captured by the camera device; and performing one or more actions using the fluorescent image of the region of the human body.

This invention relates to a neural video compression method and system based on visual saliency, belonging to the field of computer vision technology. Addressing the problems of existing end-to-end neural video compression methods, such as uniform bitrate allocation across regions within a frame and neglect of differences in human visual perception, this invention deeply integrates a lightweight visual saliency detection network with an end-to-end video compression framework. The method includes: using a saliency detection network with MobileNetV2 as its backbone to extract multi-scale features from video frames, generating a saliency probability map, which is then concatenated with the original video frames and input into a variable bitrate conditional video encoding / decoding framework; adaptively allocating the encoding precision of each region based on the saliency probability map, allowing salient regions to receive more bitrate; and employing an adaptive mask prior entropy model for checkerboard-style step-by-step entropy encoding, combined with spatial and channel-dimensional adaptive quantization to improve encoding efficiency. The system includes a saliency detection module, a variable bitrate conditional video encoding / decoding framework module, and an adaptive mask prior entropy model module, which work together to form an end-to-end optimized video compression system. Experimental results show that, at the same bitrate, the present invention can improve human visual image quality (EW-PSNR) by about 2 dB and save about 50% bitrate at the same quality.

The application provides a style migration method for converting a landscape photo into a Chinese landscape painting style. MS‑SSIM The loss function retains high-frequency information such as edges and details, and optimizes the brightness and color of the generated image. The loss function constrains the image after style migration from the aspects of brightness, contrast and structure, so that the generated image in the style conversion can be more consistent with human visual perception.

The invention provides a unified unsupervised image fusion method and device and electronic equipment, and the method comprises the steps: building a degradation perception dual mask scheme, and generating a complementary image for model training; constructing a mask diffusion model, and designing a loss function of the mask diffusion model; the mask diffusion model comprises a content encoder, a semantic encoder and a U-shaped denoising network; the mask diffusion model is trained through the complementary image; and acquiring a multi-source image, and fusing the multi-source image through the trained mask diffusion model to generate a fused image. Through the method, the image texture definition, the exposure level and the contrast expression are effectively improved, the human visual perception effect is improved, high-level visual tasks such as downstream target detection, identification and scene understanding are promoted, dependence on manual design prior is reduced, and the visual perception effect is improved. The problem of poor image fusion effect and universality in the prior art is solved.

This utility model relates to the field of identification technology and proposes an automatic paint color identification device, including: a conveyor and a controller, and a mounting plate fixedly installed on the rear side of the conveyor. The inner top wall of the mounting plate is respectively equipped with a vision detection module, an identification module, and an infrared sensor. When the infrared sensor detects material, it transmits the information to the controller, which then stops the conveyor. The vision detection module then detects the paint color on the material and transmits the detection information to the identification module. The identification module then checks whether the color is a preset color. If a different color is detected, the information is transmitted to the controller, which activates an alarm to alert personnel to take action. This achieves automatic paint color identification and effectively prevents inaccurate judgments caused by factors such as light, fatigue, and subjective judgment affecting human visual perception of paint color.

The invention relates to the technical field of 3D Gaussian splashing, in particular to a three-dimensional Gaussian compression method and system based on just perceptible distortion, and the method comprises the steps: collecting images, integrating and building a data set, and inputting the data set into a JND model to obtain a corresponding JND image; inputting the data set and the corresponding JND image into an anchor point-based 3DGS compression method model for training, sequentially obtaining the opacity and the JND score accumulation value of the anchor point, designing a loss function, and optimizing the attribute of the anchor point; judging whether the anchor point is pruned or not according to the opacity and the JND score accumulated value, and completing training of a 3DGS compression method model based on the anchor point; and the trained anchor point-based 3DGS compression method model outputs a rendered image. Extreme compression is achieved on the premise that human visual perception is not affected based on just perceptible differences, and an effective technical scheme is provided for storage and transmission of three-dimensional visual data.

The application relates to a cartoon video quality blind evaluation method, which solves the defect of poor reliability of a cartoon video evaluation method compared with prior art. The application comprises the following steps: obtaining and preprocessing original cartoon videos and corresponding distorted videos; constructing a cartoon video quality blind evaluation model; pre-training the cartoon video quality blind evaluation model; obtaining and preprocessing cartoon videos with real quality labels and cartoon videos to be evaluated; and obtaining cartoon video quality blind evaluation results. The application overcomes the problem of insufficient cartoon label data sets and improves the reliability and generalization of cartoon video quality evaluation, so that the evaluation of cartoon video quality is more in line with human visual perception.

The present application relates to the technical field of human-computer interaction, in particular to a UI world state construction interaction method and system based on human visual perception, comprising: dividing the interface perception process into discrete perception cycles, collecting multi-source perception data in parallel in each cycle and converting into candidate object descriptors with uniform format. By calculating the theoretical perception boundary combined with the viewport, scroll position and visual focus area, the candidate object set that can be perceived by the user is screened out, and correlation analysis is carried out to construct a unified world state. The audit log of the traceable decision process is generated according to the object source and confidence. The method reduces the data processing amount by simulating the visual attention mechanism, improves the state construction efficiency and accuracy, and at the same time, the process audit enhances the credibility of the state model and the maintainability of the system.

An automobile sun shield with a turnover type double-sided cosmetic mirror comprises a sun shield body and a cosmetic mirror assembly. The sun visor body is composed of an upper sun visor body piece and a lower sun visor body piece, the upper sun visor body piece and the lower sun visor body piece are oppositely buckled and fixedly assembled together, and a through hole for containing a cosmetic mirror assembly is formed in the middle of the sun visor body; the cosmetic mirror assembly is of a double-sided mirror structure, a plane mirror is arranged on one side of the cosmetic mirror assembly, a concave mirror is arranged on the other side of the cosmetic mirror assembly, the cosmetic mirror assembly is arranged in the through hole of the sun shield body and hinged to the sun shield body through overturning shafts arranged on the left side and the right side of the cosmetic mirror assembly, and the cosmetic mirror assembly overturns around the overturning shafts to achieve switching of the using states of the plane mirror and the concave mirror. According to the utility model, through the overturning structure of the double-sided cosmetic mirror, the switching between the use states of the plane mirror and the concave mirror is realized, and the pleasant driving experience is provided for drivers and passengers by virtue of the combined action of optical reflection of the concave mirror, visual perception of a human body and psychological factors.

The invention discloses a perception-geometry combined code rate control method and system and a medium, and belongs to the field of video coding, and the method comprises the steps: distributing a weight for each CTU in each frame in a video according to a VVC standard; for each I frame, calculating the perception-geometry joint weight of each CTU in the I frame, and updating the weight of each CTU in the I frame; and allocating a code rate to each CTU according to the weight of each CTU in each frame to complete code rate control. According to the method, geometric redundancy can be effectively eliminated, the human visual perception consistency is improved, and efficient transmission of high-resolution videos is promoted.

The invention discloses a non-reference image availability evaluation method based on hierarchical feature fusion. Comprising the following steps: firstly, respectively extracting a low-layer image quality feature vector, a middle-layer structure feature vector and a high-layer semantic feature vector of a to-be-evaluated image; thirdly, performing normalization processing and splicing on the feature vectors respectively; and then, inputting the total feature vector into a regression network of an integrated hierarchical attention fuser, dynamically learning the contribution weight of each level feature to a final availability score by the network through a multi-head self-attention mechanism, performing regression prediction, and outputting an availability evaluation score of the image. According to the method, multi-dimensional features from image quality to semantics are systematically fused, so that the fundamental transformation of an evaluation target from human visual perception quality to machine task availability is realized, and an evaluation result is strongly related to high-level visual task performance such as target detection and attitude estimation; the method is suitable for image screening and quality control of scenes such as automatic driving and intelligent monitoring.

The invention discloses an intelligent measurement system and method for marble surface whiteness. The intelligent measurement system comprises a control and communication module, a spectral measurement module, a color measurement module, a visual acquisition and processing module, a whiteness calculation and fusion module, a calibration and storage module and a man-machine interaction and data interface module. The control and communication module is used for coordinating data acquisition and communication among the color measurement module, the spectral measurement module and the visual acquisition and processing module, preprocessing the acquired data and providing input for the whiteness calculation and fusion module. The method overcomes the defects that point measurement of marble surface whiteness measurement is dominant, is easily interfered by texture defects, is difficult to online and the like in the prior art, and realizes multi-point sampling, texture recognition and result correction of marble plate surface whiteness through fusion of a spectrum sensor, a color sensor and AI vision. And thus, a whiteness evaluation result more conforming to human eye visual perception is obtained.