71 results about "Perceptual image" patented technology

The invention provides an unmanned aerial vehicle full-time perception image reconstruction method based on multi-mode cooperative reinforcement learning and degeneration decoupling. A frequency perception feature modulation model, a dual-mode dual-domain transformation module and a dynamic bidirectional guide mechanism are included. According to the system, firstly, feature information of different frequency bands is adaptively separated and modulated through a frequency sensing feature modulation model, and decoupling and compensation of composite unknown degradation are achieved; realizing cross-domain interaction and information fusion of visible light and infrared characteristics in a spatial domain and a channel domain by using a bimodal dual-domain transformation module; and finally, realizing collaborative enhancement of cross-modal degradation perception through a bidirectional dynamic guide mechanism, and generating an unmanned aerial vehicle visible light reconstruction image and an infrared super-resolution image with higher structural consistency and texture fidelity. According to the method, deep fusion and degeneration decoupling of multi-modal information can be realized in a complex degeneration environment, and the imaging quality and the environmental adaptability of an unmanned aerial vehicle full-time sensing system are remarkably improved.

The invention provides an efficient image super-resolution method and device based on dual guidance semantic enhancement, and relates to the technical field of image super-resolution, visual content generation and the like in computer image process.The method comprises the steps that an image super-resolution model containing a pre-training diffusion model backbone structure is constructed, and a pre-training diffusion model is constructed; a trainable LoRA module is inserted into a U-Net structure and a VAE encoder of the image super-resolution model; calculating the perception image loss of the generated image and the real image by adopting a dual-guidance quality enhancement training strategy; based on a semantic alignment method of score matching, performing semantic feature constraint on the generated image through a condition vector of a pre-training diffusion model to form semantic consistency loss aligned with real image distribution; and carrying out end-to-end training on the image super-resolution model under joint optimization of perceptual image loss and semantic consistency loss, and after the training is finished, realizing high-resolution generation of a low-resolution image only through one-time U-Net reasoning.

The disclosure relates to systems and methods automatically extracting an image and related image components, computationally determining an understanding of the image, and generating mathematical vector embeddings via sentence encoders based on the computationally determined understanding. The mathematical vector embeddings may be used for semantic image retrieval that enables image searching based on a semantic understanding of input images and / or input text. The mathematical vector embeddings may be used for training and executing generative Artificial Intelligence (AI) models to create new content that includes retrieved images and / or generate new images.

The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a diffusion neural network for mask aware image and typography editing. For example, in one or more embodiments the disclosed systems utilize a text-image encoder to generate a base image embedding from a base digital image. Moreover, the disclosed systems generate a mask-segmented image by combining a shape mask with the base digital image. In one or more implementations, the disclosed systems utilize noising steps of a diffusion noising model to generate a mask-segmented image noise map from the mask-segmented image. Furthermore, the disclosed systems utilize a diffusion neural network to create a stylized image corresponding to the shape mask from the base image embedding and the mask-segmented image noise map.

The invention discloses an equipment identification and quality grade joint evaluation method for a transformer substation inspection image, and the method comprises the steps: inputting a collected original transformer substation image into an image identification and quality grade joint evaluation model; the model comprises a detection perception image enhancement module, a target detection module, an ROI extraction module and an image quality evaluation module which are connected in sequence. Performing enhancement processing on the original transformer substation image by using a detection perception image enhancement module to obtain an enhanced image; performing target detection on the enhanced image by using a target detection module to obtain a power equipment category label and ROI frame coordinate information; an ROI extraction module is utilized to cut the original substation image according to the ROI frame coordinate information to obtain a corresponding equipment ROI image; performing no-reference image quality evaluation on the ROI image of the equipment by using an image quality evaluation module to obtain a quality grade label; according to the method, the equipment identification accuracy is improved, and the image quality grade is credibly output.

The invention provides a semantic and structure perception image restoration method and device based on a diffusion model. The method comprises the steps of obtaining a to-be-processed image and a mask used for identifying a to-be-restored area; performing panoramic segmentation on the to-be-processed image to obtain a semantic feature map, and constructing a peripheral semantic candidate set for the mask boundary to constrain semantic distribution of the to-be-restored region; extracting a structural feature map of the to-be-processed image, wherein the structural feature map comprises at least one of edge information, line segment information and angular point information; and inputting the to-be-processed image, the mask, the semantic feature map and the structural feature map into a multi-conditional diffusion generation network, and generating repair content in the to-be-repaired area by the multi-conditional diffusion generation network under the constraint of the semantic feature map, the structural feature map and the peripheral semantic candidate set, and outputting the restored image.

The invention relates to the technical field of image detection, and provides an image forgery detection method based on a multi-modal large language model, which comprises the following steps: inputting a to-be-detected image into the multi-modal large language model; the multi-modal large language model outputs an authenticity identification result of the to-be-detected image; wherein the multi-modal large language model has three parallel expert branches of physical consistency, semantic consistency and underlying structure clue analysis. According to the method, semantic information in the image is perceived and the context logic and the physical logic of the image are understood by fully utilizing the powerful priori knowledge, the deep semantic understanding capability and the chained reasoning capability of the multi-modal large language model, and meanwhile, complex reasoning and explanation can be performed on a forged image through a natural language.

According to embodiments of this disclosure, a method and apparatus for data processing are provided. The method includes: determining a reference region corresponding to a target traffic light indicated by map data in an image coordinate system corresponding to a perceived image; determining a set of candidate objects from a plurality of candidate objects identified based on the perceived image, based on the positional relationship between the reference region and a plurality of candidate regions, wherein the plurality of candidate regions correspond to the plurality of candidate objects identified as traffic lights; determining a first correlation between a first attribute of the target traffic light and a second attribute of the set of candidate objects, wherein the first attribute is determined based on the map data and the second attribute is determined based on the perceived image; and matching the target traffic light with the target objects in the set of candidate objects based on the first correlation. Based on this approach, embodiments of this disclosure can more accurately identify and match traffic lights.

The invention relates to the field of vehicle energy management, and discloses a vehicle control method, device and equipment, a medium, a vehicle and a program product, and the method comprises the steps: determining the multi-dimensional features of the vehicle based on the driving data of the vehicle and a perception image; acquiring a torque control strategy matched with the multi-dimensional features; and controlling the output torque of the vehicle according to the torque control strategy. According to the method, the multi-dimensional features can be extracted from the driving data and the sensing image, then the torque control strategy is matched, optimal control over the output torque of the vehicle is achieved, and energy consumption of the vehicle is greatly reduced.

The application relates to a remote sensing image generation online map method, device, equipment and medium, a plurality of different transformed sample images are obtained by performing geometric transformation on remote sensing sample images in each group of sample image pairs, the plurality of transformed sample images are added to the corresponding sample image pairs to obtain a training data set, each training data set is used to train an online map generation model to obtain a trained online map generation model, an encoder in a perception image compression network is used to map remote sensing sample images and corresponding transformed sample images from a pixel space to a feature space, a forward diffusion and reverse denoising are performed on the feature space by a denoising diffusion bridge network, and then an output of the denoising diffusion bridge network is mapped from the feature space to the pixel space by a decoder in the perception image compression network, and a real-time remote sensing image is input into the trained online map generation model to obtain a real-time network map. By adopting the method, a map with clearer boundaries and brighter colors can be generated in real time.

The disclosure generally relates to methods and systems for image co-registration of multi-modal temporal sensing. Conventional techniques for image co-registration of multi-modality images focus on either the spatial or temporal domain and thus are not of high accuracy and do not preserve both global and local characteristics for the matching. The present disclosure solves the technical problems in the art for image co-registration of multi-modal temporal sensing using a deep-learning based multi-input-output encoder-decoder network with a Gabor Jet Model. The deep-learning based multi-input-output encoder-decoder network is utilized for the feature extraction. A distinctive Gabor-jet layer of the Gabor Jet Model is utilized for the similarity matching. The Gabor-jet layer generates a Gabor jet graph which provides sparse feature points for matching between matching images and reference images.

The invention belongs to the field of computer vision, and particularly relates to a multi-mode CNN-Transform fused image tampering detection method, which designs a CNN and Transform double-flow parallel feature extraction structure, effectively combines the advantage of CNN at capturing fine local features and the advantage of Transform in capturing long-distance dependency relationship and global semantic information, and improves the accuracy of image tampering detection. Local details and global tampering features in the image can be sensitively perceived at the same time, so that the detection capability and stability of image tampering are effectively improved. Processing the noise domain image filtered by the SRM through a CNN (Convolutional Neural Network), and capturing local texture and noise artifact features; meanwhile, a Transform branch processes an RGB spatial domain image, extracts rich global semantic information, and realizes deep interaction and advantage complementation of two types of modal information through a feature fusion module. The BAFM module provided by the invention can deeply mine feature information of different scales and different spatial directions, and more accurate spatial attention features are generated, so that the sensitivity and expression ability of the network to tampered regions are improved.

The invention discloses an illumination perception adaptive method and system for night pedestrian re-identification. The method comprises the following steps: S1, obtaining an input image; s2, processing the input image through an illumination perception image preprocessing network, and dynamically generating an enhancement coefficient graph and a noise confidence graph; s3, performing detail enhancement on the input image through an adaptive enhancement branch to obtain an enhanced image; performing noise suppression on the input image through a feature purification module to obtain a purified image; s4, performing feature extraction on the enhanced image and the purified image by using a shared backbone network to obtain enhanced features and purified features respectively; and S5, fusing the enhancement feature and the purification feature through an illumination perception controller to obtain a final identity representation. According to the invention, through end-to-end illumination perception adaptive processing, image enhancement and feature purification are effectively cooperated, and the discrimination capability and robustness of a night pedestrian re-identification model in a low-light environment are significantly improved.

A method and a system for performing image editing based on an attribute-specific text prompt includes acquiring a noise code (z), a textual instruction (Ai) specifying a target facial attribute to be edited, and a target camera pose (pt). Upon acquiring, mapping the noise code (z) to a latent code (w), via a mapping network. Once the mapping is done, editing the latent code (w) based on the textual instruction (Ai) to generate an edited latent code (ŵ), via a text-driven Latent Attribute Editor (LAE). Further, based on the edited latent code (ŵ), generating a color texture image and a set of alpha maps via a three-dimensional Generative Adversarial Network (3D GAN). Furthermore, based on the color texture image and the set of alpha maps, generating a 3D-aware and view-consistent image at the target camera pose (pt) via a differentiable renderer.

According to embodiments of this disclosure, a method, apparatus, device, storage medium, and program product for generating trajectories are provided. The method includes: determining visual features of a set of perceived images captured by an autonomous vehicle; acquiring a reference trajectory generated by a visual language model based on the visual features; and determining a target trajectory of the autonomous vehicle by a trajectory planning model based on the visual features and the reference trajectory, wherein the trajectory planning model is an end-to-end model. Based on this approach, embodiments of this disclosure can improve the quality of the generated trajectory.

The application discloses a multispectral image fusion method and device based on multi-target segmentation, and equipment, and relates to the technical field of image processing. Different fusion methods are adopted for different targets in the feature domain according to the category of multi-target segmentation, so that the image conforming to the human eye visual perception is generated, and the significant target in the infrared image is effectively highlighted. The method comprises the following steps: collecting a visible light image and an infrared image, performing image registration processing on the visible light image and the infrared image to obtain a registered target visible light image and a target infrared image; performing multi-target semantic segmentation on the target visible light image and the target infrared image by using a multi-target segmentation network to generate a multi-target segmentation image; extracting a first deep feature corresponding to the target visible light image and a second deep feature corresponding to the target infrared image based on a multispectral image fusion network; and generating a target fusion image by fusing the first deep feature, the second deep feature and the multi-target segmentation image.

The invention relates to an automatic driving perception data processing method, device and system and a vehicle, and the method comprises the steps: obtaining a data file of at least one automatic driving task, and recording perception annotation data and perception image data in the data file; based on the data file of the at least one automatic driving task, dictionary data of the at least one automatic driving task is established, and the dictionary data indicates summarized data feature values of the corresponding automatic driving tasks; based on the dictionary data and the data file, a report file is generated, the report file comprises at least one task record, and the task records are in one-to-one correspondence with the automatic driving tasks. The dictionary data is established for the data file, the summarized data type of each automatic driving task can be quickly obtained, the report file is generated by utilizing the dictionary data and the data file, the data of different files can be summarized into the report file in a unified format according to the automatic driving tasks, the data summarizing efficiency can be improved, and the data summarizing efficiency is improved. And the report error rate is reduced.

The invention discloses a screen shooting image moire quantification method and device and a storage medium, which are used for improving the compensation precision of a display screen. Acquiring a sub-pixel unit image of the display screen to be tested; performing brightness compensation processing on the sub-pixel unit image to generate an expected brightness compensation image; generating a compensation graph frequency spectrum amplitude image according to the brightness compensation image; generating a stripe frequency band sensing image according to the visual distance and the pixel pitch corresponding to the target color channel; carrying out region division on the frequency spectrum amplitude image of the compensation graph; standard deviations of the elliptical region and the plurality of elliptical ring regions are calculated, and a region standard deviation set is generated; filling a blank image with the standard deviation in the regional standard deviation set to generate a first elliptical ring standard deviation image; performing frequency domain filtering on the first elliptical ring standard deviation image by using the stripe frequency band sensing image to generate a first frequency domain filtering image; and generating a first moire quantization value corresponding to the brightness compensation image according to the compensation image frequency spectrum amplitude image and the first frequency domain filtering image.

The invention relates to the related technical field of automatic driving vehicle testing, in particular to a vehicle-road-cloud integrated automatic driving vehicle testing method and system, and the method comprises the steps: a cloud obtains a background vehicle motion trail through analyzing an OpenScenario test case, and transmits the background vehicle motion trail to a tested automatic driving vehicle through road end equipment; inputting randomly generated Gaussian noise into a pre-training diffusion model by taking an image obtained by a vehicle end and a virtual background vehicle state as input, and performing fusion image generation through T times of noise reduction at a cloud end; and the generated vivid image is sent to a vehicle end measured algorithm, so that the self-driving vehicle test based on virtual-real fusion is realized. According to the invention, the test efficiency can be effectively improved by combining the real automobile, the real driving road and the virtual-real test scene of the tested automatic driving automobile, and the reliability of the test result can be effectively ensured by the generated high-fidelity perception image.

The invention relates to a text controllable semantic perception image enhancement method and system for power equipment inspection, and the method comprises the steps: obtaining a to-be-enhanced inspection image collected by a power equipment inspection terminal, carrying out the feature extraction of the to-be-enhanced inspection image, and obtaining the image state information; and obtaining text control information corresponding to the inspection task, fusing the text control information and the image state information to generate a joint state representation, inputting the joint state representation into the trained parameter generation model, and outputting a low-dimensional image enhancement parameter vector for controlling the inspection image enhancement process by the parameter generation model. And constructing a parameterized mapping function according to the low-dimensional image enhancement parameter vector, performing pixel-level mapping processing on the to-be-enhanced inspection image by using the parameterized mapping function, and outputting an enhanced inspection image for defect detection or state evaluation of the power equipment as a final enhancement result. The method is suitable for efficient enhancement processing of the power equipment inspection image in a complex environment.

The invention provides an edge perception image segmentation method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the feature extraction of an input image through an SAM encoder, extracting the global edge features of the input image, and carrying out the dynamic fusion of the global edge features into the features of each layer of the SAM encoder, and forming edge-enhanced coding features; generating dense embedding according to the global edge features and the edge enhanced coding features; inputting an input image into an image description model to generate text description of the image, generating text semantic embedding by using a text embedding model, mapping global edge features to feature dimensions of the text semantic embedding, and fusing to form a multi-modal sparse prompt vector; the multi-modal sparse hint vector, the coding feature, and the dense embedding are input to an SAM decoder to generate a segmentation mask. The problem that the camouflage target is difficult to segment under a complex background is solved, and accurate extraction and efficient compression of key information in semantic communication are realized.

The application provides an image feature point extraction method and system, comprising: constructing a feature map, and obtaining the center coordinates of all circular horn mouths of heat insulation sleeves; image acquisition and preprocessing; target recognition and feature point extraction; feature point matching and position and posture calculation; positioning result optimization. The application identifies a circle (the heat insulation sleeve on the top of a nuclear power plant storage room has a circular horn mouth shape and faces downward) from a perception image, calculates the center position of the circle as a stable feature point, and matches the constructed map for robot positioning. The robot can overcome the problem of influence of light and view angle change on a traditional algorithm, and realizes stable positioning and navigation in a completely dark and simple structure storage room.

The invention discloses an image feature extraction method and device, equipment, a storage medium and a program product, and belongs to the technical field of image processing. The method comprises the steps of establishing a pre-training model comprising a to-be-trained feature extraction network based on comparative learning, training the pre-training model by adopting an unsupervised comparative learning strategy to obtain a feature extraction network, and then performing feature extraction on an original image based on the feature extraction network. In the pre-training process, the original image and the enhanced image are subjected to comparative learning, so that the feature extraction network can learn the capability of perceiving the significant features of the image, the performance of the feature extraction network is enhanced, and the effect of improving the accuracy of the image feature extraction method can be achieved.

This invention belongs to the field of computer vision and digital image processing technology, specifically relating to a semantically aware image enhancement method based on amplitude-phase dual-path collaboration. The invention includes: acquiring a degraded image to be processed; performing frequency domain decomposition on the degraded image to obtain amplitude and phase components; designing a semantically aware Mamba algorithm to enhance the amplitude component, and enhancing the phase component; using bidirectional cross-attention to collaboratively enhance the enhanced amplitude and phase features, obtaining optimized amplitude and phase features; recombining the optimized amplitude and phase features and transforming them to the spatial domain to obtain the enhanced image. This invention captures global dependencies by introducing a state-space model, decouples and enhances the amplitude and phase information of the image separately in the Fourier domain, and utilizes cross-attention to achieve collaborative optimization of the two, thereby achieving effective enhancement for various types of image degradation.

The application discloses an image reconstruction method coupled with multi-branch feature domain gradient updating and attention mechanism, and comprises the following steps: constructing and training a deep unfolding compressed sensing model coupled with a multi-branch feature domain gradient updating module and a cross-attention feature reconstruction module, using the trained deep unfolding compressed sensing model to recover an original image to obtain a reconstructed image x^; the specific process of the deep unfolding compressed sensing model recovery is as follows: firstly, for a target compressed sensing rate, a block sparse sampling is performed on the input original image by using a convolutional form sampling matrix Phi; then, an initialized image is mapped to a feature space as input features of the first reconstruction stage. The application introduces a multi-branch feature domain gradient updating module and a cross-iteration / cross-channel attention mechanism, thereby improving the accuracy and stability of compressed sensing image reconstruction.

The invention discloses an image generation model-oriented watermark generation and detection method and system, and the method comprises the steps: a model provider pre-embeds an invisible watermark in a diffusion model, and provides a high-quality non-perception image generation service for a legal user; when a malicious user generates and propagates illegal or harmful images by using an API, a detection request can be provided to a model party through a supervision party, and a model provider performs watermark detection on suspicious images; and the model provider extracts watermark information from the suspicious image, judges whether the watermark information is generated by the model or not, and submits a detection result to the supervisor to judge whether the watermark information is legal or not. According to the method, a watermarking mechanism which is only used for'detection 'instead of'traceability' is designed, the speech freedom and privacy of legal users are protected while the identifiability requirement of supervision on AI generation content is met, direct tracking of user identities is avoided, and therefore effective balance between content safety guarantee and user right maintenance is achieved, and user experience is improved. And the fairness and acceptability of AI content governance are obviously improved.

The acquisition unit (15a) acquires data that is a detection target and normal reference data. The calculation unit (15b) calculates an LPIPS (Learned Perceptual Image Patch Similarity) distance between the acquired data and the reference data. The classification unit (15d) acquires data to be classified using a model that classifies the acquired data as a clean sample or an adversarial example using the calculated LPIPS distance.

This invention discloses a method, apparatus, device, and medium for morphological operations based on local density maps, relating to the field of image processing technology. The method includes: calculating a local density map based on a target image; using the local density map to characterize the local grayscale distribution features of each pixel; assigning structural element parameters of different sizes to different regions based on the local density map; performing morphological operations on the target image using structural element parameters of different sizes to obtain multiple morphological operation results; and fusing the multiple morphological operation results based on the local density map to obtain the final morphological operation result. This invention accurately perceives local image features through local density maps, adaptively assigns structural element parameters of different sizes to different regions, and organically combines the processing advantages of different parameters through a fusion strategy. While maintaining high computational efficiency, it effectively balances detail preservation and noise suppression, significantly improving the processing quality of morphological operations.

The invention relates to a method for operating a display system with smart glasses in a vehicle, wherein the display system comprises a vehicle assistance system and smart glasses connected to it via a mobile device, wherein the smart glasses are designed to variably adjust the tint of the lenses and to display an image with predefinable display properties, comprising the following steps. - Providing a perceived image with which a user perceives the background of the environment and / or the vehicle through the viewing lenses of the data glasses; - Evaluating, in particular using a brightness model, a brightness of the perceived image and especially an ambient brightness, to determine a tint to be set and a display property to be set for a display image to be shown in the data glasses; - Adjusting the tint to be set in the lenses of the data glasses; - Modifying the display image according to the display properties to be set; - Displaying the modified display image in the data glasses.

The application provides a trolley straight driving control method and system, acquires sensing images at left and right ends of a trolley advancing direction; based on the sensing images at left and right ends of the trolley advancing direction, left straight line endpoint coordinates and right straight line endpoint coordinates are acquired; based on the left straight line endpoint coordinates and the right straight line endpoint coordinates, a deviation pixel value is calculated; when the displacement deviation value does not satisfy a preset deviation requirement, the deviation pixel value is corrected through a preset pixel control algorithm to obtain deviation correction data; based on the deviation correction data, a trolley driving posture is controlled in real time. The application solves the problem that the prior art is prone to yaw in a complex work scene. The method of navigating through left and right double visual processing images completely acquires environmental information by itself and greatly improves navigation accuracy through pixel-level deviation processing, thereby reducing the occurrence of yaw.