72 results about "Laplacian pyramid" patented technology

The invention discloses an intelligent steel pipe surface defect recognition system based on deep learning, and particularly relates to the technical field of pipe surface defect analysis. An annular polarization light source array and a high-frame-rate CMOS sensor are adopted to synchronously collect visible light and near-infrared multi-polarization images; a surface normal is calculated based on Stokes parameters, mirror surface suppression and diffuse reflection enhancement are realized, a defect candidate area is generated by fusing multi-scale Laplacian pyramid residual error and Renyi entropy segmentation threshold positioning, multi-physical quantity registration is completed through white light interference and infrared thermal imaging, a six-channel feature cube is constructed, and a three-dimensional image is obtained. According to the method, space, spectrum and thermal characteristics are jointly extracted in the multi-head attention convolutional neural network, the confidence coefficient is evaluated in combination with Jensen-Shannon divergence, and the polarization angle and the focal length are dynamically adjusted according to the confidence coefficient, so that closed-loop parameter self-optimization is realized, and the micro-scale pitting corrosion and millimeter-scale crack detection precision is remarkably improved.

The invention provides a flue-cured tobacco leaf image distortion correction enhancement method, and belongs to the technical field of flue-cured tobaccos. Distortion segmentation point detection is carried out on an obtained flue-cured tobacco leaf image, and an illumination change area caused by unevenness of a tobacco leaf surface is identified by using an illumination homogenization algorithm based on a Poisson equation; secondly, constructing a distortion jump point matrix to mark gray abrupt change positions caused by shadows and light reflection between adjacent areas, then decomposing and reconstructing multi-scale image features by adopting a Laplacian pyramid image fusion algorithm, and eliminating optical interference generated by surface fluctuation through a designed fusion rule; and finishing processing when the accuracy reaches a set range, otherwise, carrying out correction and optimization again, thereby solving the technical problem that the image quality and the subsequent analysis accuracy are influenced by shadow and light reflection generated during image acquisition due to unevenness of the tobacco leaves in the prior art.

The invention discloses a low-light image enhancement method based on multilevel feature fusion. The low-light image enhancement method comprises the steps of acquiring a data set, dividing the data set, extracting features, constructing a synchronous multi-scale network, training the synchronous multi-scale network and testing the synchronous multi-scale network. According to the synchronous multi-scale low-light image enhancement method in combination with the Laplacian pyramid, the input image is processed in parallel by adopting a double-path structure: the preliminary enhancement image is obtained through the local-global convolutional neural network, and the detail and texture information of the image is enhanced based on the Laplacian pyramid decomposition network. A multi-scale network is adopted to process images in scenes of deblurring, defogging, rain removal, low light enhancement and the like, and details and features are extracted in a layered manner, so that the definition, color and contrast ratio of the images are effectively improved. Comparison experiments prove that the method has the advantages that noise is effectively suppressed, and remarkable effects are achieved in the aspects of detail recovery and color restoration. The method is suitable for image enhancement processing under various complex illumination conditions.

The invention relates to the technical field of image segmentation, in particular to an anaphora image segmentation method based on space-frequency dual tuning, and the method comprises the steps: dynamically generating a frequency domain learning prompt and a space domain learning prompt through a space frequency domain dual prompt technology; splicing interaction is carried out by utilizing spatial domain prompts and encoder features, and semantic representation of an anaphora target is enhanced; recovering high-frequency details by adopting a Laplacian pyramid and a LoRA-based frequency domain encoder, and enhancing key features through multiplication operation prompted by a frequency domain; and finally, double-domain optimization features are fused, and an accurate boundary segmentation result is generated through a mask decoder, so that the problems of detail degradation and boundary fuzziness caused by lack of frequency domain information in a traditional method are effectively solved.

The invention discloses a multi-scene statistical channel fingerprint construction method and system based on frequency perception. According to the method, unified tensor modeling is carried out on statistical channel state information, and various typical statistical channel fingerprint construction scenes are uniformly expressed as a tensor recovery problem. On the basis, multi-scale frequency decomposition and reconstruction of the statistical channel fingerprints are realized through a Laplacian pyramid, and multi-scale frequency sub-band features of the statistical channel fingerprints are obtained while the reasoning efficiency is improved; and through a shared mask learning mechanism, carrying out layer-by-layer self-adaptive refinement processing on high-frequency statistical channel fingerprint components under different scales. Besides, in order to expand the characteristic receptive field under the condition that the model parameter quantity is not obviously increased, convolution processing is carried out on different frequency components in a wavelet transform domain, and decoupling extraction and efficient modeling of the statistical channel fingerprint multi-frequency characteristics are achieved. According to the method, the construction precision and the calculation efficiency can be considered in various statistical channel fingerprint construction scenes.

The invention belongs to the technical field of image analysis and processing, and relates to an automobile circuit board solder paste printing quality detection method and system. The method comprises the steps of constructing a Laplacian pyramid for a target solder paste area image, extracting multi-level geometric and position features, performing weighting based on local phase consistency to obtain a first fusion feature, and comparing the first fusion feature with a first fusion feature of a historical qualified sample to obtain a second fusion feature; calculating a time sequence drift correction characteristic capable of correcting the drift in the production process; constructing a neighborhood feature map by combining the first fusion features of the target region and the spatial neighborhood of the target region, and extracting spatial morphological features by using an orthogonal Gabor filter; and performing vector splicing on the first fusion feature, the time sequence drift correction feature and the spatial form feature to generate a comprehensive combined feature, and inputting the comprehensive combined feature into a predetermined classification model to obtain a printing quality detection result. According to the invention, the detection rate of the solder paste area defect on the automobile circuit board can be improved.

The invention discloses a panoramic image splicing method, system and device, and relates to the technical field of image processing, and the method comprises the steps: collecting images around a vehicle at different visual angles; using the MASK masks to generate overlapping region masks of the different view angle images, and performing local feature detection on the overlapping region masks to generate a transformation matrix; aligning the images of different visual angles according to the transformation matrix; a Canny edge detection operator is fused in splicing seam energy detection, the energy weight of the image edge area of the aligned image is enhanced, and a splicing seam is guided to actively avoid an object with remarkable structural features; b spline interpolation is introduced to optimize an initial splicing seam path; constructing a Laplacian pyramid along Gaussian blur of a splicing seam, and sequentially carrying out gradual fusion to generate a seamless panoramic image; according to the method, the basic function of eliminating the visual blind area is realized, a clear and visual panoramic view can be provided for a driver, and the driving safety is effectively improved.

The invention relates to the technical field of video generation, in particular to a video frame generation system and display equipment based on texture reconstruction and trajectory optimization, and the system comprises a motion breakpoint detection module, a trajectory interpolation frame generation module, a texture anomaly positioning module, a texture interpolation reconstruction module and a video frame synthesis module. According to the method, an edge feature map is generated through edge detection and non-maximum suppression, the boundary recognition precision is improved, noise is suppressed, candidate regions are divided through region growth, the local feature extraction efficiency is enhanced, global redundancy is reduced, three-frame optical flow analysis captures trajectory breakpoints, and motion vector correction path deviation is predicted in combination with a Lucas-Kanade method. Color consistency verification optimizes interpolation to reduce cross-frame abrupt change; 64 * 64 grids and a gray level co-occurrence matrix locate texture abnormity; five-frame similarity strengthens time sequence stability; Gabor filtering extracts a main direction and combines an adjacent frame reconstruction texture direction to ensure consistency; and trajectory smoothness and visual consistency are optimized through multi-frame cooperation and layered detection.

The invention discloses an underwater image enhancement method and system based on three-input multi-scale fusion. The method comprises the following steps: carrying out visibility recovery on an image to be processed; performing contrast enhancement through a nonlinear mapping function; carrying out enhancement processing on the contour of the high response area; respectively calculating a Laplacian contrast weight map, a saliency weight map and a saturation weight map of the three processed images; linearly combining all types of weight maps to obtain an aggregation weight map, and normalizing the aggregation weight to obtain a normalized weight map; decomposing the three processed images into a Laplacian pyramid, decomposing the normalized weight map into a Gaussian pyramid, and performing fusion through upward sampling and addition reconstruction; carrying out smoothing processing and edge-preserving sharpening processing on the fused image to obtain an image after underwater image enhancement and restoration; according to the method, the color cast problem of the underwater image is solved, the image contrast is effectively improved, and the texture details of the image are improved.

The invention relates to the technical field of digital image processing, in particular to a real-time image quality enhancement method for a vehicle-mounted camera EMC test, and the method comprises the steps: obtaining real-time image data and historical image data; and performing multi-branch collaborative decoupling processing on the real-time image data to generate a frequency domain purification graph, a core structure graph, a space domain purification graph and a time domain stability graph. And performing local statistical analysis on the real-time image data to generate an artifact intensity map and a perception saliency map. Under a multi-resolution Laplacian pyramid framework, fusing the frequency domain purification graph and the space domain purification graph; the weight of the fusion process is intelligently regulated and controlled spatially and hierarchically by an artifact intensity graph, a perception saliency graph and a time domain stabilization graph which are constructed based on a Gaussian pyramid, and finally a high-quality enhanced image is reconstructed and generated. According to the invention, through a multi-branch cooperative decoupling and intelligent fusion method, real-time enhancement of the vehicle-mounted camera image under EMC interference is realized.

The invention discloses a spacecraft micro-deformation measurement method and system based on femtosecond laser interference, and relates to the technical field of laser interference measurement, and the method comprises the steps: extracting an interference phase signal corresponding to residual distribution, obtaining frequency domain representation through fast short-time Fourier transform, and calculating the spectral intensity; performing frequency domain decomposition on the spectral intensity by using a Laplacian pyramid, calculating local energy density and performing normalization processing to obtain a scale weight, converting residual distribution into a frequency domain deformation spectrum through Fourier transform, and performing weighted fusion in combination with the scale weight to generate a fusion deformation field; the measurement precision and real-time performance in a complex environment are improved by accurately controlling the optical main axis, temperature compensation and interference fringe analysis, deformation field information can be accurately extracted by combining the Laplacian pyramid and the frequency domain fusion technology, and the measurement sensitivity and accuracy are improved.

The application discloses a large-format cross-scale adhesive film defect detection method and device. The method comprises the following steps: rough focusing of a camera and capturing an adhesive film image, rough scanning of the adhesive film image and extraction of information of printed graphics in the adhesive film image by using an image difference method, input of an output differential image into an anchor frame algorithm, input of output fine scanning target region coordinates into a genetic algorithm, combination of motor S-curve planning characteristics to output an optimized fine scanning path; driving a motion platform to complete path execution by using a double-shaft linkage control combined with the fine scanning path, focusing of the camera during path execution, collection of high-resolution images of defect regions and registration, image stitching and fusion of the registered images by using an optimal seam line algorithm combined with an improved Laplacian pyramid fusion method, and defect detection on the complete adhesive film image after fusion. The application has high stitching accuracy, fast processing efficiency, and can effectively retain more detailed information.

The present application belongs to the technical field of image processing, and particularly relates to a geological disaster risk assessment method and system based on big data, which comprises the following steps: collecting multi-level remote sensing videos with different time spans, performing STL decomposition on the pixel value sequence of the pixel points at the same position in the same layer of the Laplacian pyramid of each frame of the remote sensing videos, determining the magnification multiple according to the change of the obtained trend term and the level number of the corresponding remote sensing video, magnifying the periodic term of each group of pixel points, and then reconstructing the Laplacian pyramid to obtain the remote sensing videos after action magnification, determining the geological deformation probability within the corresponding time span according to the edge change in the remote sensing videos after action magnification, and thus obtaining the geological disaster probability. The present application magnifies the subtle geological changes in the remote sensing videos, and is more accurate in geological disaster risk assessment.

The application discloses a tone mapping method and system based on a lookup table and a Laplace filter, and belongs to the technical field of image processing.The input image is first decomposed into an adaptive Laplace pyramid;then a low-frequency image at the bottom layer of the adaptive Laplace pyramid is input into a weight predictor to obtain a pixel-level weight map, and a three-dimensional lookup table is used to perform three-linear interpolation on the low-frequency image to obtain a preliminary mapping image; then the preliminary mapping image and the weight map are fused pixel by pixel to generate an image at the bottom layer of the fine-tuned Laplace pyramid; then a filter parameter prediction module is used to learn a parameter value map of the remaining layer images of the adaptive Laplace pyramid, and the parameter value map is applied to a local Laplace filter to obtain the remaining layer images of the fine-tuned Laplace pyramid; finally, the fine-tuned Laplace pyramid is reconstructed to obtain a tone-mapped image.The application can retain local edge details of an image while performing global tone mapping.

The application discloses a medical image segmentation method based on Laplacian pyramid and dynamic Transformer, S1. Form a preprocessed medical image; S2. The preprocessed medical image is decomposed into a plurality of image sublayers of different scales; S3. Corresponding multi-scale feature representation is generated; S4. The multi-scale feature representation is input into the dynamic Transformer module to generate the fused global feature representation; S5. The fused global feature representation is subjected to decoding processing to generate a preliminary segmentation map, and a post-processing algorithm is applied to the preliminary segmentation map to perform morphological operation, edge repair and noise removal, and obtain a medical image segmentation result with clear boundaries and coherent regions. The application generates a medical image segmentation result with clear boundaries, coherent regions and accurate semantics, and improves the practicability of the model in clinical application, and has obvious advantages in processing images with blurred tumor boundaries and densely overlapped tissues.

This invention belongs to the field of medical image processing technology, specifically relating to an X-ray image enhancement method, system, and storage medium. The method includes: inputting an original X-ray image and reapplying window width and window level; performing noise reduction processing; copying the X-ray image into a normal tissue layer, a cancerous tissue layer, and a calcification point layer, adjusting the brightness and contrast of each layer using gamma adjustment; performing image enhancement and Retinex enhancement; acquiring the three enhanced layers and the Retinex-enhanced normal tissue layer, and performing Laplacian pyramid fusion to obtain the enhanced image. This invention also provides an X-ray image enhancement system for implementing the above method. This invention can achieve excellent image enhancement results without excessive magnification or contrast enhancement, supporting doctors in rapid and accurate diagnosis, and has excellent application prospects.

The invention relates to the technical field of three-dimensional reconstruction, and discloses a face three-dimensional reconstruction method, system and device based on a portable device and a medium, and the method comprises the steps: collecting a face image frame sequence of a target user through the portable device; performing face key point detection on each frame of face image in the face image frame sequence, and performing face geometric reconstruction based on a face key point result in combination with a multi-stage fusion algorithm to obtain a face geometric reconstruction model; determining a plurality of key face images in the face image frame sequence based on a frame selection strategy, performing de-illumination processing on each key face image, and fusing each de-illuminated face texture image through a Laplacian pyramid network to generate a face texture reconstruction model; and mapping the face texture reconstruction model to the face geometric reconstruction model to obtain a complete face three-dimensional reconstruction result. According to the invention, the hardware cost can be reduced, the convenience is improved, remote medical treatment is realized, and the face three-dimensional reconstruction precision and quality are improved.

This invention discloses a method and system for transferring the style of traditional Chinese painting based on the Laplacian pyramid, belonging to the field of computer vision technology. The method constructs a multi-scale style transfer model based on the Laplacian pyramid. The multi-scale style transfer model includes a Laplacian pyramid decomposition module, a basic style transfer network, a detail enhancement network, an edge information selection module, and a Laplacian pyramid reconstruction module. Preprocessed content image datasets and preprocessed style image datasets are input into the multi-scale style transfer model for training. Style loss functions and content loss functions are used to optimize the multi-scale style transfer model, resulting in a multi-scale style transfer generation model. The target content image is then input into the multi-scale style transfer generation model to generate a stylized image in the style of traditional Chinese painting. This invention can generate high-quality stylized images with the style of traditional Chinese painting.

The application discloses a fine-grained representation remote sensing image interpretation method and system based on Shearlet prior knowledge, adopts Shearlet transformation to extract high-frequency sub-band information of preprocessed remote sensing image data; uses Laplace pyramid and shearlet filter to obtain high-frequency components and multi-direction high-frequency sub-bands after directional splitting; through a spatial attention mechanism, sub-bands of the same level are adaptively fused to generate a detail-enhanced feature map; high-frequency components extracted through Shearlet transformation are prior to multi-scale and multi-level weighted fusion of deep residual blocks obtained through a deep residual network; a trained detail-enhanced backbone and different detection heads of multiple tasks are used to output accurate remote sensing image analysis results; through combination of Shearlet transformation and an advanced deep learning architecture, the accuracy and efficiency of remote sensing image interpretation are significantly improved, meanwhile, good model generalization ability and practicability are maintained, and it is expected that the application will promote the development of remote sensing image processing in a more intelligent and automatic direction.

The application discloses a brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion, and comprises the following steps: inputting multi-modal medical image data into a Laplacian pyramid multi-modal fusion learning model to generate a fusion graph, then inputting the fusion graph into a U-net segmentation model comprising an encoder and a decoder to obtain a segmentation mask under the multi-modal fusion graph; and finally, based on the multi-modal fusion graph and the segmentation mask, adopting a Marching cubes (MC) algorithm to perform three-dimensional reconstruction visualization of brain regions and brain tumor region labeling. The brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion provided by the application optimizes the disadvantages of insufficient information and incomplete modeling under single modal, fully utilizes the advantages of the completeness of multi-modal data, performs multi-modal fusion, segmentation and three-dimensional visualization, can more comprehensively assist surgeons in treatment, and improves the accuracy in the operation process.

Embodiments of the present application disclose an image fusion method, an electronic device and a storage medium, including: performing Laplacian pyramid decomposition on each image to be fused; determining fusion weights of other decomposition images of a highest layer according to frame differences between a reference decomposition image of the highest layer and other decomposition images of the highest layer; the reference decomposition image being a decomposition image of the image to be fused with the highest definition; determining fusion weights of other decomposition images of a second highest layer according to frame differences between a reference decomposition image of the second highest layer and other decomposition images of the second highest layer and the fusion weights of the other decomposition images of the highest layer; performing the above determining process on remaining layers until fusion weights of other decomposition images of a lowest layer are obtained; fusing the decomposition images of each layer based on the fusion weights of the decomposition images of each layer to obtain intermediate fusion images of each layer; the fusion weights of motion regions in the other decomposition images of each layer being 0, and the fusion weights of motion regions in the reference decomposition images of each layer being 1; and generating a target image based on the intermediate fusion images of each layer.

The application discloses an image semantic segmentation method for blind road scenes, which is characterized by a semantic segmentation model constructed by a Laplacian pyramid texture module, a Laplacian texture self-attention module and a decoder for segmenting blind road scene images, wherein the model comprises an LPTT block, a Segformer block and a decoder; the LPTT block extracts clear low-level features through a texture self-attention extraction layer; the Segformer block extracts accurate high-level semantic features; and the decoder fuses multi-level features. Compared with the prior art, the application has lower complexity than other semantic segmentation networks, solves the problem of slow segmentation speed of widely used semantic segmentation networks for blind road scene images, and has a segmentation accuracy comparable to other semantic segmentation networks in a large number of experiments in different environments.

The embodiment of the invention provides an electrowetting display driving system and related equipment, and belongs to the technical field of electrowetting display. The system comprises a processor unit which obtains an image set and carries out image decoding on the image set to obtain first image data; the illumination decomposition module constructs a Gaussian pyramid according to the first image data, and constructs a corresponding Laplacian pyramid according to the Gaussian pyramid; the illumination reconstruction module performs illumination reconstruction according to the Laplacian pyramid to obtain a corresponding illumination reconstruction pyramid; the illuminance fusion module performs illuminance fusion according to the illuminance reconstruction pyramid and the Gaussian pyramid to obtain optimized illuminance image data; the color rendition module carries out color rendition according to the optimized illumination image data to obtain target image data; the display driving unit is used for generating a display driving signal according to the target image data; and the image display unit performs image display according to the display driving signal. According to the embodiment of the invention, the accuracy of images displayed by the electrowetting display screen can be improved.

The invention discloses a method and device for generating a high dynamic range image based on FPGA double-exposure multi-scale fusion, and belongs to the technical field of image processing.The method comprises the steps that a double-exposure LDRI is obtained, and then an input image data stream is obtained; the method comprises the following steps: calculating the contrast, saturation and exposure satisfaction of an image based on an input image data stream, and carrying out normalization processing on a weight value formed by the contrast, the saturation and the exposure satisfaction to obtain a normalized weight map; completing the construction of a Gaussian pyramid of the normalized weight map; completing the construction of a Laplacian pyramid for the obtained input image data stream; and performing same-scale fusion on each layer of the output image subjected to Gaussian pyramid construction and each layer of the output image subjected to Laplacian pyramid construction with the same resolution, performing Gaussian blur and up-sampling reconstruction on the fused pyramid, and restoring the image to the initial resolution. According to the invention, the image fusion efficiency and the operation speed of the whole system are improved.

A multi-exposure dynamic range enhancement method for low-light images, for a group of low-light image sequences which are registered, continuous multi-exposure imaging of the same scene, for different exposure time original images, first, calculate the contrast, texture and exposure weight factors for each pixel, the three weighted multiplication and normalization to get the weight map corresponding to different exposure time; second, the original image of different exposure time is decomposed by Laplacian pyramid, and the weight map corresponding to different exposure time is decomposed by Gaussian pyramid; third, the Gaussian pyramid weight coefficient of different exposure time is weighted and averaged with the Laplacian pyramid layer by layer, and the new Laplacian pyramid is fused; finally, the fused Laplacian pyramid is reconstructed, and the final fused target scene high dynamic range low-light image is obtained.

The disclosure provides an image processing method, an image processing device, a computer readable storage medium and an electronic device, and relates to the technical field of images. The image processing method comprises the following steps: acquiring a plurality of to-be-fused images of a same shooting scene; decomposing each to-be-fused image to obtain a Gaussian pyramid and a Laplacian pyramid of each to-be-fused image; fusing pyramid images located at the same layer in the Gaussian pyramid of each to-be-fused image to obtain a fused Gaussian pyramid; fusing pyramid images located at the same layer in the Laplacian pyramid of each to-be-fused image to obtain a fused Laplacian pyramid; and generating a fused image corresponding to the plurality of to-be-fused images by using the fused Gaussian pyramid and the fused Laplacian pyramid. The disclosure can improve the image quality.

The invention discloses a high-reflection surface three-dimensional reconstruction method and device based on virtual exposure fusion. The method comprises the following steps: collecting a plurality of exposure image groups of a to-be-reconstructed target; one exposure image group corresponds to one projection frequency and comprises a plurality of exposure image subgroups; generating a corresponding intermediate exposure image group based on each exposure image subgroup, and then performing weighted fusion to obtain a corresponding virtual exposure image; fusing the virtual exposure image corresponding to each middle exposure image group and the high-exposure image and the low-exposure image in the corresponding exposure image subgroup by adopting a Laplacian pyramid multi-scale fusion mode to obtain a corresponding fused image; based on each fused image, obtaining an absolute phase distribution diagram through a phase shift method and a multi-frequency heterodyne method; and generating a three-dimensional point cloud of the to-be-reconstructed target according to the absolute phase distribution diagram, thereby providing a high-reflection surface three-dimensional reconstruction method which is wide in application range, simpler in process and higher in precision.

The invention discloses a mask-based hierarchical Laplacian matting method, and the method employs an end-to-end deep learning network, achieves the generation from a rough mask to a fine gray-scale map through a strategy of combining multi-scale feature extraction and multi-scale Laplacian supervision, and achieves the matting of the rough mask and the fine gray-scale map. The method comprises the main technical steps of multi-scale feature coding, construction of Laplacian pyramid supervision signals and multi-scale independent prediction and fusion. According to the method, Laplacian pyramid supervision is adopted, and a complex prediction task is decomposed into low-frequency rough main body contour prediction and high-frequency fine edge residual prediction, so that a model learning target is clearer. A real image is decomposed into a low-frequency orthogonal component and a high-frequency orthogonal component through a Laplacian operator, and a high-resolution decoding layer is specially supervised to predict a high-frequency residual error extracted by the Laplacian operator, so that the network can more directly and effectively pay attention to and recover an extremely fine edge and a semitransparent region, which is difficult to solve by a traditional method.

The invention provides a lung image recognition method and system for clinical diagnosis of the respiratory medicine department. The method comprises the steps that a binary mask containing complete lung parenchyma is obtained from a lung image; segmenting a target lung field image from the lung image based on the binary mask, and extracting a texture saliency map from the target lung field image; performing pixel-level fusion on the texture saliency map and the target lung field image to obtain a lung feature image, and performing multi-resolution pyramid decomposition on the lung feature image to obtain a Gaussian pyramid layer and a Laplacian pyramid layer; direction gradient histogram features and local binary pattern features are extracted from the Gaussian pyramid layer and the Laplacian pyramid layer respectively, and then a multi-resolution joint feature vector is constructed; and inputting the multi-resolution joint feature vector into a pre-trained image analysis network, and positioning a focus area in the lung image. According to the technical scheme provided by the invention, the lesion area in the lung image can be identified under the coupling interference of the anatomical structure and the pathological features.