41 results about "Image mosaicking" patented technology

The invention discloses a panoramic parking assist system, which is a technique applied to the fields of automotive electronics and auto safety driving assistance. The system comprises a camera input module, an image correction module, a bird-eye perspective module, an image mosaicking module, a histogram equalization module and an image display module. The system is used for effectively solving the problem of car crash accidents caused by that the driver can not fully observe the situations around the car in the process of parking. By using the system, a 360-degree top view around a car bodyin real time can be showed for the drivers, so that the drivers can clearly see the relative positions of obstacles around the car body and the distances between the obstacles and the car body; and the blind visual areas around the car body can be eliminated so as to improve the security and stability of car in the process of parking. Through integrating a plurality of machine vision and digital image processing algorithms and fusing a plurality of advanced techniques in the field of machine vision, and based on the advantages of low cost, high performance, strong portability and the like, the system is convenient to be popularized and applied widely.

The invention provides an image mosaicking method based on video or a plurality of images, which comprises the following steps of: a) obtaining a video frame or image containing text; b) selecting the video frame or image from the continuous video frames or a plurality of images; c) extracting the text area or removing the background area from the video frame or image selected in step b ); and d) mosaicking the continuous video frame or image, or mosaicking character recognition results of the continuous video frame or image. The invention can improve the application scope of OCR systems from the traditional single image to continuous video signals, especially in special OCR application systems such as video-based card recognition systems.

A mosaicking method for large breadth cultural heritage image is provided, which relates to the technical field of image matching and image mosaicking. The invention comprises the following processing procedures: 1) aiming at the features of cultural heritage image, adopt an angle point detection method to extract the angle point of image, which can be taken as image feature for the matching of images; 2) calculate gradient of straight line connected between the matching points of nearby images, and; adopt a clustering method to pre-select the correlation points between images by utilizing the similarity of gradient; 3) adopt a best route method to generate a smaller mosaicking route with little pixel value, so as to evade the area with big pixel difference and remove the ghost image; 4) use a brightness component in HIS color space and blend the brightness via weighted function formula according to the mosaicking route. Compared with other mosaicking method, the method provided in the invention is able to greatly improve the speed for image mosaicking, eliminate the brightness difference of image, remove the ghost image in mosaicking and realize ideal mosaicking result.

The invention discloses a target detection method, a target detection device and electronic equipment. The method includes: subjecting a plurality of branch original images from various cameras to image mosaicking to obtain a panorama original image; subjecting the panorama original image to down-sampling to obtain a panorama down-sampled image; executing primary image detection on the panorama down-sampled image to determine whether a region of interest exists in the panorama down-sampled image or not; responding to the region of interest detected in the panorama down-sampled image to search a specific branch original image in the various branch original images, wherein the specific branch original image is a specific branch original image, in which the region of interest is positioned, detected in the panorama down-sampled image before image mosaicking of the panorama original image; storing the specific branch original image into a memory. Therefore, stability of a scene monitoring system is improved while mechanical cost is reduced.

A microminiaturized common image surface panorama imaging technique, wherein aspheric imaging lens and corner cube mirror constitute four identical imaging optical path rack and vertically fixed. The number of divided image surfaces by image surface coupler is same to the number of divided image surfaces by aspheric imaging lens and corner cube mirror. The three-dimensional space scene information obtained by aspheric imaging lens and corner cube mirror arrives the image surface coupler by the imaging optical path rack and the imaging surface of imaging device is divided into four same imaging areas in four quadrant using image surface coupler and the four path scene information synchronizes one path to image on the four imaging areas of image surface. Four images on the image surface respectively correspond space scene information on the four direction and are subjected to character matching and image mosaicking based on the overlap area between the two adjacent scene images, in order to obtain a intact space panoramic image. The invention has features of identical linearity, good resolution and real time performance, small aberrance, microminiaturization, particularly suitable for application with higher microminiaturization requirement.

The invention relates to the technical field of image processing, in particular to a remote sensing image registration algorithm. The registration algorithm comprises the following steps of: (1) reading primary remote sensing image data from a storage medium; (2) pre-processing each primary image; (3) performing binarization processing to realize image segmentation; (4) corroding and expanding the binary image; (5) extracting a monotropic edge from the eroded and expanded binary image by the Roberts cross gradient operator; (6) calculating the matching degree of the edge image and finding the optimal matching point; (7) conversing images; and (8) outputting registration information and registration images. The remote sensing image registration algorithm can be applied to multispectral data fusion and remote sensing image mosaicking.

The invention provides a true-orthophotomap making method oriented to large-scale production. The method comprises the following steps of: S1) data source processing: preprocessing the acquired digital surface model and remote sensing image; S2) occlusion detection: detecting the region occluded by buildings; S3) occlusion restoration: restoring the detected occluded region according to the visibility of multiple overlapped images, and obtaining the orthophotomap; S4)image mosaicking: combining multiple neighboring orthophotomaps obtained in the step S3 in a mosaicking manner, toning, and obtaining the true-orthophotomap. The method is efficient, quick, accurate and steady, and has wide adaptive range.

The invention discloses a method for generating a body cavity full-view image based on capsule endoscope images, which comprises the following steps of: acquiring the capsule endoscope images and the image format; preprocessing the acquired images; generating the full-view image, wherein the acquired images are respectively subjected to circular image expansion, image registration and image mosaicking and the image obtained after mosaicking is the full-view image; and visually displaying the full-view image. By acquisition of the full-range cavity image through an endoscope, doctors can acquire more open and intuitive visual field during the diagnose, thereby the method is favorable to improve the accurately diagnostic rate of the doctors and shorten the image reading time.

The invention relates to a portable quick staff-free investigation system of a traffic accident scene based on binocular vision, comprising portable scene investigation equipment and an information processing system, wherein the portable scene investigation equipment conducts photography investigation and information acquisition by using a synchronous triggering binocular camera; the information processing system comprises an image processing module, a scene draft drawing module and an accident case management module; the image processing module is used for processing the images of investigated pictures to realize coordinate conversion and image mosaicking, which is used for carrying out size marking on the scene draft drawing; the scene draft drawing module is used for drawing, generating and printing traffic accident scene drafts in a mode of combining the invocation of drawing database symbols with the size marking; and the accident case management module is used for carrying out sort management on the investigated pictures, scene drafts and other related information in the form of cases. By using the system, the traffic accident scene is not required to be preprocessed, the equipment is convenient to carry and simple to operate, the measuring accuracy is high, and only one operator can execute the whole operation process.

The invention belongs to the technical field of remote sensing image processing, and relates to a green tide information extraction method. The method comprises: obtaining a sea area satellite remote sensing image with a conventional method, screening images of green tide regions, and performing preprocessing operations of geometric correction and image mosaicking; calculating and determining a green tide range by adopting a normalized difference vegetation index; cutting a region of interest in any shape to generate an irregular image file containing the green tide regions; extracting green tide information by adopting a split Bregman fast projection algorithm of a variational level set two-phase image segmentation based Chen-Wees model; and finally, quantitatively calculating the green tide regions by adopting a quantitative formula. The image segmentation based variational model accurately extracts and quantifies the green tide information on the satellite remote sensing image, so that a conventional manual threshold method can be completely replaced and operational application can be realized; and method is scientific and reasonable in principle, low in human factor quantity, high in calculation speed, accurate and stable in result, high in operability, friendly in application environment, high in practicality and easy to popularize.

The invention provides a seam line optimization method based on long-span region extraction, comprising the steps of calculating the difference of overlap region pixels; respectively carrying out image segmentation on images in left and right image overlap regions through selecting a proper partitioning algorithm, determining the preferential region of seam lines from the segmentation results according to the span of segmentation regions, and optimizing a cost matrix according to the determined preferential region of the seam lines; and searching the optimized seam lines by adopting a Dijkstra algorithm according to the cost matrix and starting and ending points. The method is applicable to the optimizing process of the seam lines when a digital orthoimage is subjected to image mosaicking, the directions of the seam lines can be optimized, the optimized seam lines are along large-span regions such as roads, rivers and bare lands as far as possible, obvious surface features such as buildings are prevented from being passed through, the integrity of ground targets is kept, and therefore the quality of image mosaicking is improved.

The present invention provides a method, device and system of generating a road orthographic projection image. The method comprises the steps of obtaining the coordinate and posture of an image at the current shooting moment; obtaining the orthographic projection image of a road pavement at the current moment shot by a panorama camera according to the image acquired by the panorama camera; according to the coordinate and posture of the image and the orthographic projection image of the road pavement, embedding the orthographic projection image of the next shooting moment in the orthographic projection image obtained at the previous shooting moment to generate the road orthographic projection image. By the above scheme, the road orthographic projection image is generated in a manner of carrying out the orthographic projection and the image embedment based on a panorama image, the road orthographic projection image can be generated rapidly and conveniently by the method, at the same time, the image production cost is reduced.

The invention discloses a mosaicking method and system of a panoramic camera. The method comprises steps as follows: acquiring images of multiple image sensors and caching the images in an internal memory of the panoramic camera; selecting two left and right adjacent images from the internal memory for mosaicking, and determining matched window areas with a window matching algorithm; calculating rotating and translation matrixes required by image mosaicking through matched pixel coordinates, and rotating and translating the two images; performing pixel fusion on the left and right images to realize image mosaicking. According to the provided mosaicking method and system of the panoramic camera, two left and right adjacent images are selected from the internal memory of the panoramic camerafor mosaicking, and the matched window areas are found from the two images with the window matching algorithm; by means of the matching method, the matched search area and the calculation times can be effectively reduced, higher calculation efficiency is realized, and real-time image mosaicking is convenient to realize.

The invention relates to a movable mapping platform which is used for carrying out mapping image collecting and processing by utilizing a smart phone, and carrying out distributing, sharing and business requests by utilizing a cloud service platform, and solves the problems existing in an existing mapping technology that the resolution is low, and the existing mapping technology needs to be combined with other mapping products for use, so that the cost is high, mass needs cannot be met, and the like. The movable mapping platform comprises a mobile phone terminal image and auxiliary information collection module, a mobile phone terminal image processing module and a server side image mosaicking module, wherein the smart phone is adopted as a mapping terminal, an APP (Application) with a photographing function is installed in the smart phone, the APP with the photographing function is used for obtaining an image, processing the image and uploading the processed image to a server. According to the movable mapping platform disclosed by the invention, the smart phone is adopted as the mapping terminal, so that the system cost can be substantially reduced; meanwhile, a complete mapping map after seamless mosaicking is provided for a user.

The invention discloses a multi-camera image mosaicking method and a multi-camera image mosaicking device based on a same satellite platform. The multi-camera image mosaicking method includes the steps of acquiring multiple to-be-mosaicked camera images of the same satellite platform; within two current to-be-mosaicked camera images, selecting one camera image as a reference image, and selecting the other camera image as a to-be-calibrated image; computing spatial positional deviation and color deviation between the reference image and the to-be-calibrated image; calibrating the to-be-calibrated image according to the spatial positional deviation and the color deviation; splicing the reference image and the calibrated image. The multi-camera image mosaicking method and the multi-camera image mosaicking device are capable of performing quick mosaicking on the multiple camera images of the same satellite platform and wide in application range.

The invention provides a weak point target precisely positioning method and system based on space-time oversampling and scanning. The method comprises the steps of structuring M linear array detectors; performing scanning to obtain M groups of images, performing non-uniformity correction on the images obtained through scanning, and according to time and space sampling periods, arranging the M groups of images in a mosaic mode into a n image F', and removing edges of the image F'; eliminating random noise in the image F'; performing threshold filtering on the denoised image to obtain a binarized image F1; searching for weak point target regions in the image F1 through a connected region method; searching for the corresponding weak point target regions in the image F, and determining the positions of mass centers of weak point targets through a first-step-interval mass center extracting method to achieve precise positioning of the corresponding weak point targets in the image F'. The weak point target precisely positioning method and system based on space-time oversampling and scanning overcomes the problems of long sample data processing time and complex information processing processes in existing oversampling technology and can obtain high-precision target point location without changing the optical aperture and the focal length of an existing optical system.

A binocular range finding method, a binocular range finding device, a panoramic image mosaicking method and a system thereof are disclosed. The binocular range finding method includes determining a left image and a right image according to a position relationship among first and images and an overlapping region; for each distance template in a distance template group stored in advance, calculating the matching rate between a characteristic position of the left image and a characteristic position of the right image according to a present distance template; for the current distance template, calculating the average matching rate of images at characteristic positions of the left and right images based on the calculated matching rates; and when the average matching rate exceeds a preset threshold, adopting the current distance template as a target distance template, and adopting the distance from a lens of the target distance template to a scenery sample as a distance from lenses in the first and second images to the scenery. The method accurately determines the distance from the lenses in the first and second images to the scenery.

The invention discloses a data conduction extension device for a turnover light-emitting diode (LED) studio screen and relates to a turnover LED display screen. The data conduction extension device for the turnover LED studio screen is characterized by consisting of a rotor and a stator; the rotor and the stator are arranged between an upper layer LED triangular module and a lower layer LED triangular module, so that the upper layer LED triangular module and the lower layer LED triangular module synchronously rotate; the rotor is provided with a combined slip ring; the combined slip ring is connected with an output data line and is led out into an inner cavity of the lower layer LED triangular module; the stator is provided with an electric brush module at the inner side of a hollow sting; the electric brush module is connected with an input data line, is led out to the outside and is connected with peripheral equipment; the combined slip ring and the electric brush module are correspondingly contacted in the inner cavity of the hollow sting of the stator to form information conduction between a fixed object and a rotary object; externally input data information is transmitted to the inner cavity of the lower layer LED triangular module; and the combined slip ring is connected with LED light bars of the lower layer LED triangular module. According to the extension device disclosed by the invention, multi-way information transmission between the fixed object and the rotary object is realized and not only is the problem that a wire is wound solved but also the image playback quality of an ultrahigh LED digital studio screen can be improved through the image mosaicking technology.

The embodiments of the invention disclose a capsule endoscope, an endoscope system and an image acquisition method for the endoscope. The capsule endoscope comprises a shell; an image acquisition system, comprising a lens and an image processing device; and a visual angle control device connected with the image acquisition system, wherein the visual angle control device is used for controlling a visual field angle mode of the capsule endoscope according to attitude information on the capsule endoscope, and the image acquisition system acquires images in different visual field angle ranges whenthe capsule endoscope is in different visual field angle modes; the lens is arranged at the end part of the capsule endoscope and acquires first image information through a pupil entrance visual field angle; and the image processing device is used for processing the first image information according to the visual field angle mode so as to obtain second image information. According to the capsuleendoscope, the endoscope system and the image acquisition method, disclosed by the embodiments of the invention, the visual field angle mode can be switched to acquire images of higher quality, reducedistortion of the images and facilitate image mosaicking; and meanwhile, a data transmission quantity is reduced.

The invention relates to a shipborne safety navigation electro-optical aided system. The shipborne safety navigation electro-optical aided system comprises a video acquisition unit, a control host, a display device and a control key; the video acquisition unit comprises a thermal imaging lens I, a thermal imaging lens II, a thermal imaging lens III and a super low illumination lens; the focal length of the thermal imaging lens II is the same as that of the thermal imaging lens III; the control host comprises a DSP (Digital Signal Processor) processing board and a video selection module; and the DSP processing board comprises an image pretreatment module, an image mosaicking module and an image fusion module. According to the shipborne safety navigation electro-optical aided system provided by the invention, the finally formed video image is wide in range and large in depth of field, so that a scene observed by the shipborne safety navigation electro-optical aided system is larger and the definition is higher, thus the shipborne safety navigation electro-optical aided system can be widely installed and used in various ships.

The invention relates to a mapping system for a traffic accident scene. The mapping system comprises a first image gatherer, an image recognizer, a second image gatherer, an image mosaicking processor, a central processor, an image drafting device, a color printer and a wireless transmitting device. The first image gatherer is connected with the central processor through the image recognizer; the second image gatherer is connected to the central processor by the image mosaicking processor; the central processor is respectively connected with the wireless transmitting device and the image drafting device; and the image drafting device is connected with the color printer. The mapping system has the advantages of simple structure and reasonable design, provides on-site data processing and scene drafting, greatly shortens the scene handling time, improves work efficiency, and ensures safety.

The application discloses a hemispherical playing method and system of a video. The method comprises: video frame images are collected at a preset time interval from each shooting angle of each shooting scene in a video shooting environment; the video frame images are processed, and the processed video frame images are embedded in corresponding positions of the corresponding video shooting scenes; video frame images of the same video shooting scene are processed by image mosaicking to form a panoramic video image in the same shooting scene and then the image mosaicking of all panoramic video images is completed; a plurality of panoramic video images are numbered sequentially according to the sequence of shooting and combined to form a video file; a corresponding display position of each video frame image on a hemispheroid model when the video file is projected onto the hemispheroid model is computed; and rendering playing is implemented sequentially on the plurality of panoramic video images on the hemispheroid model and an observation point is disposed at the sphere center of the hemispheroid.

A method of processing images captured using an endoscope comprising a camera is disclosed. According to this method, regular images captured by the camera are received while the endoscope travels through a human gastrointestinal (GI) tract. The regular images are mosaicked to determine any missed or insufficiently imaged area in a section of the human GI tract already travelled by the endoscope. If any missed or insufficiently imaged area is detected, information regarding any missed or insufficiently imaged area is provided. When a target area in the regular images is lack of parallax, the target area is determined as one missed area and an edge corresponding to a structure of the human lumen is highlighted. For a capsule endoscope, the endoscope can be configured to be controlled or steered to move so as to re-image the missed or insufficiently imaged area.

The present invention discloses an image mosaicking method. The method comprises the steps of: performing distortion correction of an image to be mosaicked according to a radial distortion coefficientof a lens; calculating an affine transformation matrix to perform image registration by identifying mark points; generating a fusion seam by employing a region growing method based on a pixel spatialdistance; calculating a mapping relation of a histogram consistency by employing a color histogram; performing brightness correction of a fused image; and finally, generating one contour layer and one detail layer corresponding to each layer by employing an image pyramid, and performing reconstruction to generate the fused image. The image mosaicking method employs the region growing method basedon the pixel spatial distance to generate the fusion seam of the image, and combines a traditional image super-resolution image pyramid reconstruction method to enhance an optimization effect; and moreover, the image mosaicking method is not limited by scenes and targets and can automatically calculate the fusion seam for targets with different scenes, depths of field and color spaces, so that the robustness and the generalization of image mosaicking are improved.

A microminiaturized common image surface panorama imaging technique, wherein aspheric imaging lens and corner cube mirror constitute four identical imaging optical path rack and vertically fixed. The number of divided image surfaces by image surface coupler is same to the number of divided image surfaces by aspheric imaging lens and corner cube mirror. The three-dimensional space scene information obtained by aspheric imaging lens and corner cube mirror arrives the image surface coupler by the imaging optical path rack and the imaging surface of imaging device is divided into four same imaging areas in four quadrant using image surface coupler and the four path scene information synchronizes one path to image on the four imaging areas of image surface. Four images on the image surface respectively correspond space scene information on the four direction and are subjected to character matching and image mosaicking based on the overlap area between the two adjacent scene images, in order to obtain a intact space panoramic image. The invention has features of identical linearity, good resolution and real time performance, small aberrance, microminiaturization, particularly suitable for application with higher microminiaturization requirement.

A binocular range finding method, a binocular range finding device, a panoramic image mosaicking method and a system thereof are disclosed. The binocular range finding method includes determining a left image and a right image according to a position relationship among first and images and an overlapping region; for each distance template in a distance template group stored in advance, calculating the matching rate between a characteristic position of the left image and a characteristic position of the right image according to a present distance template; for the current distance template, calculating the average matching rate of images at characteristic positions of the left and right images based on the calculated matching rates; and when the average matching rate exceeds a preset threshold, adopting the current distance template as a target distance template, and adopting the distance from a lens of the target distance template to a scenery sample as a distance from lenses in the first and second images to the scenery. The method accurately determines the distance from the lenses in the first and second images to the scenery.

The invention provides a weak point target precisely positioning method and system based on space-time oversampling and scanning. The method comprises the steps of structuring M linear array detectors; performing scanning to obtain M groups of images, performing non-uniformity correction on the images obtained through scanning, and according to time and space sampling periods, arranging the M groups of images in a mosaic mode into a n image F', and removing edges of the image F'; eliminating random noise in the image F'; performing threshold filtering on the denoised image to obtain a binarized image F1; searching for weak point target regions in the image F1 through a connected region method; searching for the corresponding weak point target regions in the image F, and determining the positions of mass centers of weak point targets through a first-step-interval mass center extracting method to achieve precise positioning of the corresponding weak point targets in the image F'. The weak point target precisely positioning method and system based on space-time oversampling and scanning overcomes the problems of long sample data processing time and complex information processing processes in existing oversampling technology and can obtain high-precision target point location without changing the optical aperture and the focal length of an existing optical system.

The invention provides a large-scale ground-distance satellite-borne SAR image mosaic method, which relates to the field of satellite SAR (Synthetic Aperture Radar) image mosaic. The original image is firstly subjected to necessary preprocessing, and then the preprocessed image is extracted with geographic location information to The location information is used as prior knowledge to correct the cross-correlation of the image to obtain the mosaic error information, and use the mosaic error information to compensate the image mosaic error; after the mosaic error compensation, the Wallis filter is used to search for the updated SAR image. The method is used for uniform color processing, and the mosaiced image is finally generated; the present invention provides an optional solution for the determination of the matching offset by adapting the cross-correlation method according to different terrains or the binary matching statistics method based on the zero-crossing point; providing A search and update strategy, which guarantees the effect of uniform color processing in multiple overlapping areas and directions, and can well protect the texture details in the image.