192 results about "Image fusion algorithm" patented technology

Typical inventive practice provides for electronic communication of a computer with a display, an active radar device (for transmitting target-location data and environmental data), a light measurement device (for transmitting visual light data), and passive imaging devices covering bands in the visual, infrared (MWIR and / or LWIR), and millimeter wave regions of the electromagnetic spectrum. Inventive software in the computer's memory establishes “operational modes.” Each operational mode is defined at least by a predominant environmental (obscuration and lighting) character, ascribes “modal indices” to individual imaging devices, and carries its own multispectral image fusion algorithm (which, pursuant to the ascribed modal indices, attributes weights to the imaging data from the respective imaging devices). The inventive software aims the imaging devices toward the target, selects an operational mode (based on the environmental data), and executes the image fusion algorithm associated with the selected operational mode so that a fused multispectral image is displayed.

The invention relates to a behavior splicing method of a video scene, so that video scene splicing and behavior splicing of moving objects in different videos can be realized. The method comprises the following steps that: on the basis of image registration, meshing is carried out on a video image so as to form an image block node set and an image block label set; an image block clustering algorithm is utilized to generate an image block label type representative candidate set for each of the image block node; and a two dimensional Markov random field and a three dimensional Markov random fields of the image block node are constructed and solved, so that a static background and a dynamic background are generated; on the basis of extraction of tracks of moving objects, track similarity and position similarity between moving objects of different videos are calculated, so that a splicable property of moving object behaviors is obtained and video alignment is provided at time and space; and a poisson image fusion algorithm is utilized to fuse a panoramic dynamic background video and motions, so that a video scene after behavior splicing is generated.

The invention provides a multi-scale gradient domain image fusion algorithm which is used for fusing infrared thermal images with visible light images. The multi-scale gradient domain image fusion algorithm is characterized by comprising the following steps: a step of constructing gradient fields; a step of correcting gradient fusion weight; a step of reconstructing gradient fields; and a step of fusing images through a transparency method. The multi-scale gradient domain image fusion algorithm provided by the invention can be used for simultaneously reserving temperature rise areas and detail information of infrared thermal images and visible light images, removing a halation background-effect phenomenon and redundant information due to interaction among images and avoiding color inconsistency of an infrared thermal image temperature rise area.

The invention discloses a single-exposure high-dynamic range image generation method adapted to a medical image. The method comprises the steps that 1) images of different exposure are generated on the basis of reverse tone mapping, and a reverse tone mapping function is modeled; 2) according to a pseudo-exposure HDR image generated in the first step, a weight graph of the image is obtained on the basis of a pyramid decomposed multi-exposure image fusion algorithm; 3) Laplacian pyramid decomposition is carried out on a sequence of N multi-exposure images, Gaussian pyramid decomposition is carried out on N weight graphs, and images and weight graphs of different resolutions are obtained, and a fusion formula is obtained; and finally, Laplacian inverse transformation is carried out on a pyramid L{R}l to obtain a fused image R. Thus, an HDR image synthesized by input image is obtained. Compared with an original image, the synthesized HDR image is higher in contrast, more distinct in colors, and more reinforced in details; a fusion algorithm is low in computational complexity; and high dynamic range image generation can be realized in real time.

The invention discloses a novel image fusion algorithm based on combination of IHS (intensity-hue-saturation) transform and wavelet transform for effectively fusing a low-resolution multispectral image and a high-resolution full-color image. The method comprises the following steps: carrying out wavelet decomposition on a strength (I) component image and a high-resolution full-color image of a multispectral image; carrying out fusion with different standards according to respectively high and low frequency features; carrying out wavelet inverse transformation on the new formed high and low frequencies to obtain a new I component image; and finally carrying out IHS inverse transformation to obtain a final fusion image. A test result shows that the method is used for not only reducing the spectral distortion value, but also effectively increasing the spatial resolution.

An integrated method for both super-resolution and multi-frame demosaicing includes an image fusion followed by simultaneous deblurring and interpolation. For the case of color super-resolution, the first step involves application of recursive image fusion separately on the three different color layers. The second step is based on minimizing a maximum a posteriori (MAP) cost function. In one embodiment, the MAP cost function is composed of several terms: a data fidelity penalty term that penalizes dissimilarity between the raw data and the super-resolved estimate, a luminance penalty term that favors sharp edges in the luminance component of the image, a chrominance penalty term that favors low spatial frequency changes in the chrominance component of the image, and an orientation penalty term that favors similar edge orientations across the color channels. The method is also applicable to color super-resolution (without demosaicing), where the low-quality input images are already demosaiced. In addition, for translational motion, the method may be used in a very fast image fusion algorithm to facilitate the implementation of dynamic, multi-input / multi-output color super-resolution / demosaicing.

The invention relates to an algorithm for fusing a multi-focusing image based on salient region extraction. The algorithm comprises the steps of 1, performing GBVS algorithm to obtain salient images of two source images; 2, performing binaryzation for the salient images, and respectively calculating the space frequency so as to obtain space frequency maps; 3, detecting the weak side edges of the space frequency maps by the watershed algorithm to obtain closed areas, classifying, comparing the space frequency of different regions to find out the false focusing areas, filtering the false focusing areas, and processing the rest regions by the morphological method to obtain a focusing area; 4, directly fusing the source image focusing regions, performing Shearlet conversion for the out-of-focus regions, and decomposing to obtain high frequency and low frequency sub-band coefficients, and respectively performing conversion and fusion based on PCNN and laplacian pyramid; 5, reconstructing the fusion coefficients to obtain a fusion image. With the adoption of the algorithm, the gray levels are dispersedly distributed, the image textures are rich, and the details are salient.

The invention discloses a venous visualizer and a visualizing method. The visualizer comprises an optical system for visualizing deep veins, and a liquid crystal display system, wherein the optical system comprises a near infrared light source and a venous image acquisition unit; the venous image acquisition unit is used for dividing reflected light into two paths so as to separate near infrared light from visible light; the near infrared light comprises information of deep veins (3 millimeters); after being subjected to image enhancement, the near infrared light is subjected to image fusion with a visible light image, and a fused image is displayed on the liquid crystal display screen for a doctor to refer to during venipuncture. Due to the adoption of a dynamic frame-by-frame image fusion algorithm, a venous enhanced image obtained by near infrared light activation can be overlapped on an ordinary image in real time, and an entire venipuncture process can be displayed completely on the liquid crystal screen.

The invention relates to a partial discharge detection method based on multi-source image fusion. The partial discharge detection method based on multi-source image fusion is characterized in that S100, an ultrasonic sensor array, a camera, an infrared thermal imager, and an ultraviolet imager are respectively used to acquire ultrasonic wave signals, visible images, infrared images, and ultraviolet images of a detected device synchronously; S 200, the ultrasonic visible images can be acquired based on the acquired ultrasonic wave signals and the visible images; S 300, the ultrasonic visible images, the infrared images, the ultraviolet images can be used as the partial discharge detection result after being fused by adopting the image fusion algorithm, and can be displayed. Compared to the prior art, the partial discharge detection method has advantages of detection precision and high reliability.

The invention discloses an infrared and low light image fusion method. The method comprises the following steps of: (1) acquiring an original infrared image by using an infrared camera, and acquiring an original low light image by using a low light camera; (2) respectively partitioning the acquired original infrared image and the original low light image so as to divide the original infrared image and the original low light image into N mutually corresponding original image sub-blocks; (3) in a parallel processing system, simultaneously carrying out image fusion on the mutually corresponding original image sub-blocks in the original infrared image and the original low light image so as to obtain fused image sub-blocks; and (4) combining the fused image sub-blocks so as to generate a final fused image. The fused image obtained by the invention not only has a high image quality, but also has a high fusion speed, and therefore, the infrared and low light image fusion method has a wide application prospect in the military and civil fields of night vision surveillance, security monitoring, and the like.

The invention relates to an image processing method and device. The method comprises the steps that whether a face in a to-be-processed face image wears a pair of glasses is detected; when it is detected that the face in the to-be-processed face image does not wear a pair of glasses, key point positioning is performed on the face in the to-be-processed face image, and a local image of an originalpouch area in the to-be-processed face image is acquired; beautifying processing is performed on the local image of the original pouch area, and a local image of a pouch area after beautifying processing is acquired; the local image of the pouch area after beautifying processing and the local image of the original pouch area are fused according to a preset image fusion algorithm, and a local imageof a target pouch area is obtained; the local image of the original pouch area in the to-be-processed face image is replaced with the local image of the target pouch area, and a processed face imageis obtained. Through two times of beautifying processing, the beautifying effect is effectively improved.

The detection equipment includes detection system and electric control system. The detection system includes case, separating machine, input port, light source, video camera, container conveying belt, cleaning unit, residual liquid detecting module, container side detecting module, photoelectronic sensor, inferior container eliminator and output port. The electric control system includes host control PC and detection subsystems, the detection subsystems consist of photoelectronic sensor, image collector, DSP processing module and I / O interface; and the host control PC is connected electrically via I / O interface to the detection subsystems. The present invention adopts infrared and visible image fusion algorithm and polyfocusing image fusion algorithm in the detection. The present invention has the beneficial effects of fast detection speed and high precision.

The embodiment of the invention discloses a video image processing method comprising the following steps of: obtaining one frame video image; extracting and segmenting a foreground image and a background image from the video image; optimizing the foreground image; carrying out processing of multi-frame accumulation algorithm on the background image; and combining the processed foreground image and background image into one image through an image fusion algorithm. According to the video image processing method provided by the invention, the foreground image and the background image are respectively processed to ensure that the image quality can be overall increased, the image layering is enhanced and the contour of an object in the background can be clear. In addition, the invention also provides a video image processing device.

The present invention discloses a hybrid multi-scale analysis-based infrared and visible light image fusion algorithm. The algorithm comprises the following steps that: step 1, NSCT (nonsubsampled contourlet transform) decomposition is performed on infrared and visible images to obtain low-frequency subbands and high-frequency subbands; step 2, static wavelet transformation is performed on the low-frequency subbands so as to obtain a low-frequency subband and three high-frequency subbands, and a local energy and maximum absolute value selection-combined method and a compressed sensing theory are adopted to fuse the low-frequency subband and the three high-frequency subbands; step 3, the definition of an image to be fused is judged, and the enhancement layers of an LSCN are selected according to judging criteria; step 4, the topmost layer high-frequency subband is fused according to a fusion rule of selecting a largest absolute value, and the other subbands are fused through adopting an improved PCNN model; and step 5, inverse NSCT is performed on fusion results, so that a final fused image is obtained. The fused image obtained by using the method of the invention has prominent edges and high contrast; a target in the fused image is prominent; and the indexes of the algorithm such as average gradient and spatial frequency are higher than those of algorithms in the prior art.

The invention discloses infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression, relating to the technical field of image processing.. The fusion method combinesadaptive dual channel pulsed cortex (ADC-SCM) and low rank matrix (LRR) theory to propose an effective infrared and visible image fusion algorithm. According to the fusion method, an effective infrared and visible light image fusion algorithm is provided by combining an adaptive double-channel pulse distribution cortex (ADC-SCM) and a low-rank matrix (LRR) theory; The method comprises the following steps: firstly, combining low-rank expression with a frequency modulation (FT) saliency algorithm to carry out salient region detection on an infrared source image, thereby separating a salient region from a background region in the source image; Secondly, fusing the two obtained regions respectively, and selecting a fusion rule with the maximum absolute value to fuse the significant regions inorder to retain the significant features to the maximum extent; And finally, obtaining a fused background through NSST inverse transformation, and superposing the fused salient region and the fused background region to obtain a final fused image. Experimental results show that the algorithm provided by the invention is superior to other common image fusion algorithms in subjective visual effect and objective evaluation indexes.

The invention provides a multi-focus image fusion method based on sparse decomposition and a differential image. The multi-focus image fusion method is characterized by comprising the steps of utilizing RPCA to decompose an original image to obtain its sparse component and low-rank component, enhancing an edge of the sparse component through guide filtration, adding the enhanced sparse component to the low-rank component to construct an enhanced image comprising a strong edge, performing differential processing on the enhanced image and the original image, calculating spatial frequency of an obtained differential image, utilizing a self-adaptive threshold algorithm to obtain a spatial frequency diagram of the differential image, utilizing a morphological algorithm to remove a pseudo-focus region in the spatial frequency diagram to obtain a fusion decision-making diagram, and reconstructing a fusion image according to the fusion decision-making diagram and a fusion rule. Three index of the multi-focus image fusion method in evaluating an image fusion algorithm, namely a correlation coefficient, edge gradient information and an edge correlation factor are higher than that of other classical algorithms by more than 45%, 6% and 15% respectively.

The invention relates to a camera interchangeable dynamic light splitting imaging system and a method thereof applied to high-dynamic imaging. The system realizes high-quality imaging of a target by adopting a combined imaging mode, combining a rear-end image fusion processing algorithm, and forming a structure of a main lens, an adaptor, a plurality of cameras and multi-source image fusion. According to the system, a single-sensor imaging mode of a one-time single light path of a conventional optical measuring system is changed into a dynamic light splitting multi-sensor imaging mode; key technologies, such as a large dynamic range imaging scheme, a light splitting ratio dynamic adjustable adaptor module and a multi-wave band high-dynamic image fusion algorithm, are broken through; the problems about integrated installing and synchronous imaging of a plurality of types of advanced sensors, multi-source image fusion, an enhanced processing algorithm and the like are solved; optical measurement information are acquired to the maximal extent; high-dynamic, high-speed, multi-wave band, high-resolution and high-quality imaging of a target in a target range is realized; the optical measurement level of a test in the target range is effectively improved.

The invention discloses a wireless sensor network image fusion method based on multi-focus fusion and image splicing. According to the wireless sensor network image fusion method, multi-focus image acquisition is firstly carried out on an image acquisition node, a multi-focus image fusion algorithm based on direction area energy is called to perform multi-focus image fusion, a focused image is selected by an adaptive gradient threshold judging method and is transmitted to a splicing processing node, multi-focus images obtained from different directions in different acquisition nodes or the same acquisition node are spliced by the splicing processing node, and a multi-azimuth and multi-focus fusion image is obtained and is then transmitted. The invention combines the multi-focus image fusion technology with the image splicing technology, effectively fuses a large number of image data to be transmitted, so the data transmission quantity and transmission energy consumption of the sensor network are reduced, meanwhile, users are ensured to obtain more direct and more abundant information, the adaptive gradient threshold judging method is adopted to select splicing materials, and the adverse effect of focusing blurred images on fusion result is reduced.

The invention discloses a mixed-reality sandbox device and method. The sandbox device is formed by a prime module sandbox, a projector and a computer. The input is from a plurality of monitoring cameras in the real world, which collect local scenes of the real world and provide input video streams for the device; the prime module sandbox of the device is made according to the real world in a certain scale; the surfaces of regions corresponding to the input video streams are light-color diffuse reflection materials; and the projector is arranged above the prime module sandbox, and projects downwards onto the surface of the sandbox. The method adopts a two-step alignment strategy to calibrate the input video streams, then, carries out splicing on overlap regions through an edge-adaptive image fusion algorithm, and enables images and videos in the real scene to be fused and projected to the surface of the prime module sandbox in real time in the device operation process according to the obtained calibration result, thereby realizing real-time simulation and miniature reproduction of dynamic change of the real scene.

The invention discloses a multi-focus image fusion method based on a decision diagram and sparse representation. According to the method, a multi-focus image fusion framework which is different from the conventional multi-focus image fusion algorithm is put forward based on the characteristics of a human vision system, and analysis and research are performed for the transition region of multi-focus images so as to avoid the influence on the fusion result and enhance the quality of the fusion image. The implementation process comprises the steps that the decision diagram is generated on the basis of resolution analysis of the low-scale images of the multi-focus images, and a fusion result is acquired according to the decision diagram; the generated decision diagram has error due to the fact that judgment of the resolution of the transition region has deviation so that the transition region requires to be determined and processed by using the multi-focus image fusion algorithm based on sparse representation and the fusion result of the transition region can be acquired; and finally mean operation is performed on the fusion result based on the decision diagram and the fusion result of the transition region so that the final fusion image is acquired.

The invention relates to the digital image processing field and the image fusion algorithm field, for greatly improving the running speed of the whole fusion system on the premise that the quality and detail of the image are not impacted, the data volume of the image is greatly reduced and the amount of the data to be processed for fusion process is promoted. Therefore, according to the technical scheme, the image fusion method of compressed sensing framework comprises following steps: step 1, executing the single layer wavelet decomposition on the image to be fused; step 2, selecting the Gaussian along matrix as the measure matrix, measuring and obtaining the value; step 3, selecting the numerical value corresponding to each point for forming the new matrix; step 4, adopting the principal component analysis method for fusing the high-frequency components of the source images after measured; step 4, obtaining the high-frequency component, which is suitable for the wavelet inverse transform; and step 5, obtaining the fused image. The image fusion method of compressed sensing framework is mainly used for the digital image processing field.

The invention discloses and provides an effective multi-focus image fusion method based on the transformation between Pulse Coupled Neural Vetwork (PCNN) and Laplacian Pyramid (LP). Firstly, the LP is utilized to perform multi-scale decomposition to images with a tower structure and the PCNN is utilized to process the decomposed images of each of the scales so as to acquire a neurons firing frequency diagram of a describing feature cluster; the fusion to the images at each of LP decomposition scales is realized, based on the local space frequency (LSF) of the firing frequency diagram; and lastly, the fusion to the multi-focus images are realized through restricting algorithm of LP decomposition. The experimental results show that the multi-focus image fusion result acquired by the method of the invention has advantages over various traditional fusion algorithms at the aspects of subjective visual effect and objective evaluation index; and the method shows good performance.

The invention discloses a three-camera module and electronic equipment. The three-camera module comprises a first color lens, a second color lens, a black-white lens, a first triple prism, a second triple prism, a first color photosensitive chip, a second color photosensitive chip, a black-white photosensitive chip and an image processor; the first triple prism is used for reflecting the beam penetrating the first color lens to the first color photosensitive chip to perform the imaging; the second triple prism is used for reflecting the beam penetrating the second color lens to the second color photosensitive chip to perform the imaging; the black-white photosensitive chip and the black-white lens are opposite to each other so that the beam penetrating the black-white lens can directly enter the black-white photosensitive chip to perform the imaging; the image sensor acquires the image information on each of the first color photosensitive chip, the second color photosensitive chip andthe black-white photosensitive chip; and a target image after the image fusion is output through an image fusion algorithm. The three-camera module realizes a multifunctional camera module.

The invention provides a binocular visible light and infrared thermal imaging composite imaging system. The method and medium comprise the following steps: a thermal imaging module focuses infrared energy emitted from an object in a scene on an infrared detector by using an optical device, and then converts infrared data from each infrared detector into a preset picture format to obtain an original infrared image; Visible light imaging module: collecting the original visible light image through the camera; ARM system module: pre-processing the original infrared image to obtain the pre-processed infrared image. Compared with the conventional infrared instrument, the image fusion algorithm used in the invention can remove most redundant information in the infrared image, and the remaining contour information such as the object and the visible light image are fused with the image, so that the fused image not only has good object and background characteristics, can provide rich backgroundinformation, but also enhances important object information.

The present invention discloses a component level three dimensional model building method of bayesian network constraint. The method comprises the following steps of firstly, placing a target object on a turntable rotating slowly, using a Kinect to scan the target object to obtain a RGBD data sequence, and generating an initial three dimensional point cloud by combining a depth image fusion algorithm (KinectFusion); secondly, utilizing an interactive segmenting tool to modify the initial three dimensional point cloud to remove a noisy point and the redundant part; on the basis, utilizing a trained bayesian network to carry out the component segment on the three dimensional point cloud, automatically selecting a component model according with the requirement from a three dimensional model component base for each segmented component, registering a candidate three dimensional component to the model three dimensional point cloud by utilizing a non-rigid deformation algorithm, calculating the fitting degree of the candidate three dimensional component, and further selecting an optimal three dimensional component; finally, automatically splicing the optimal three dimensional component by utilizing a conformal deformation algorithm, and fitting to the model three dimensional point cloud in a deformation manner to obtain the three dimensional model possessing the component semantics finally.

The invention provides a substation equipment defect recognition method and device, and particularly relates to the technical field of data analysis and processing, and the method can comprise the steps: building an infrared and visible light double-vision system, and obtaining a visible light image and an infrared image of detected substation equipment; carrying out the fusion through employing an image fusion algorithm of IHS transformation and Contourlet transformation, and generating a to-be-recognized image after fusion; constructing a neural network, performing feature extraction on the batch of original video data, and establishing an equipment defect database including abnormal data of the power transformation equipment in different states; then constructing a transfer learning network based on infrared image features to obtain a temperature mode analysis result of the equipment area; and finally, carrying out anomaly identification and defect judgment on the to-be-recognized image by utilizing a multi-network fusion algorithm. Based on the scheme provided by the invention, the intelligent degree of substation equipment fault detection is improved, and the efficiency and accuracy of fault detection are improved.

The invention relates to a fast multi-focus image fusion algorithm. The algorithm comprises the following steps of firstly, decomposing a source image by using a smoothing filter and constructing thedecision graph model of multi-focus image fusion; secondly, using the correlation between the neighborhood pixels of multi-focus images to provide a fast steering filter optimization decision graph sothat calculating complexity is greatly reduced; then, reconstructing two scales of images; and finally, using the fusion method of the invention and other triple existing fusion methods to fuse the multi-focus images. Compared with the other three kinds of fusion methods, by using the method of the invention, regardless of subjective visual and objective evaluation indexes, the texture information, the significance information and other details of the multi-focus images can be preserved.

The invention provides a contrast pyramid image fusion method based on an area. The method is characterized by utilizing a plurality of out-of-focus images to obtain a sharp image. The method is characterized by, to begin with, utilizing Laplace energy in an image window as measurement for showing whether the area is clear or not; obtaining positions of clear pixel points in each image; marking the positions of the clear pixel points in a mask image; then carrying out optimization operation on the mask image to obtain an accurate position of the clear area in the image; fusing each layer of image of a contrast pyramid with a ground floor image according to the marked clear area in a mask image pyramid; and establishing a completely clear image by utilizing the fused contrast pyramid and the ground floor image. The multi-focus image fusion algorithm can be applied to the processing of criminal investigation images, medical microscopic images, and does not rely on any camera parameters.

The invention discloses a rapid image fusion algorithm based on the pixel level. The method comprises steps that firstly, color space transformation of a visible light image is carried out, and the visible light image is transformed from the RGB space to the YUV space; secondly, adaptive weights of the visible light image and an infrared image are acquired respectively; thirdly, the weighted meanmethod is utilized to process the fusion process of the visible light image and the infrared image; fourthly, the fusion result is optimized and adjusted; and lastly, color space transformation of thevisible light image is carried out, the image is transformed from the YUV color space to the RGB space, and the whole image fusion process is completed. The method is advantaged in that the visible light image and the infrared image can be fused on the pixel level, the abundant spectrum information and the high resolution of the visible light image and the unique heat radiation characteristic ofthe infrared image are fully integrated, and maximized image information fusion is realized.

The invention discloses a photographing method and related equipment, the photographing method is applied to electronic equipment, the electronic equipment comprises a media service module and an operating system, and an application layer of the operating system is provided with a third-party application; the method comprises the steps that the third-party application sends a data request to a hardware abstraction layer of the operating system; the hardware abstraction layer receives the data request, obtains to-be-processed original application data and calls an image fusion algorithm to process the original application data to obtain target application data, and the image fusion algorithm is that a third-party application requests an operating system to open to the third-party application in advance through a media service module; and the hardware abstraction layer sends the target application data to the third-party application. By adopting the embodiment of the invention, the imagequality shot by the third-party application can be improved.