Abstract: By collecting, analyzing and processing a series of images captured by a camera one can estimate the motion that a device containing the camera has experienced. Exemplary techniques disclosed herein at least enable device motion estimation based on any selection of images from a camera related to the device.

Abstract: A method of analysing seismic data from a geological volume is provided. The geological volume is divided into a plurality of voxels. For each voxel a respective neighbourhood is defined which includes that voxel and a predetermined arrangement of neighbouring voxels. For each voxel, the respective normal vectors of a seismic attribute vector field derived from the seismic data are calculated. For each voxel, a respective local structure tensor based on the normal vectors of the voxels of the respective neighbourhood is calculated. For each voxel, the value of an expression which includes one or more of the eigenvalues (?1, ?2, ?3) of the respective local structure tensor is calculated. The method can be used for seismic surveying, or to manage operation of or drilling of a subterranean well.

Abstract: A method of processing seismic data so as to provide an image of a sub-surface region, comprises providing plurality of migrated shot gathers that contain information about the region, summing portions of the migrated shot gathers to provide a pilot stack, partitioning the plurality of gathers into a plurality of groups and summing the gathers in each group to provide a substack, wherein each group includes at least two migrated shots and wherein a substack is generated from each group, applying an amplitude normalization algorithm to the pilot stack so as to generate an amplitude-normalized pilot stack, calculating a weight function by comparing each substack to the normalized pilot stack, weighting each substack using the weight function so as to generate a plurality of weighted substacks, summing overlapping portions of the weighted substacks so as to generate a output stack, and using the output stack to generate an image.

Abstract: The Invention involves a person being able to quickly access the electronic profile of another person. When a person wants someone to receive his profile (or a portion of the profile), he obtains the electronic address of that person. Then the pertinent information from the profile is sent in real time to that electronic address. Another embodiment involves a person providing an electronic identifier to a second person, and that electronic identifier is then used by him to access the profile.

Abstract: A system and method are provided for implementing a scheme to apply commercial web search technologies to biometric matching and identification based on converting biometric identification data to one or more text strings. Collected biometric identification information regarding particular physical traits is converted to a form that facilitates application of commercial Web search technologies to implement biometric matching and identification. A scalability of multi-modal biometric identification systems is maintained while substantially eliminating reliance on proprietary matchers and templates in support of interoperability and customer satisfaction. Separate biometric templates are converted into strings of searchable text in any combination of alpha-numerics during a standard biometric data enrollment process in order to limit the data storage requirements and streamline the later undertaken comparison process.

Abstract: Some implementations may provide a method for generating a portrait of a subject for an identification document, the method including: receiving, at a mobile device, a photo image of the subject, the photo image including a foreground and a background, wherein the foreground includes the subject's face and the background does not include the subject's face; determining the background of the photo image based on the photo image alone and without user intervention; masking the determined background from the photo image; and subsequently generating the portrait of the subject based on the photo image with the background masked.

Abstract: Provided is a programmable display apparatus that enables post-hoc identification of a user who has been permitted to access an application through facial authentication. The programmable display apparatus stores feature data of a face of a user and identification information of the user in association with each other. The programmable display apparatus performs facial authentication based on image data of a user obtained through image capture and on the feature data. The programmable display apparatus permits a user to access the application if the user has been authenticated. The programmable display apparatus stores identification information of the authenticated user and a history indicating a state in which the access has been permitted in association with each other.

Abstract: An apparatus and method for imaging a sample of substantially undiluted whole blood is provided. The method includes the steps of: providing a substantially undiluted whole blood sample admixed with at least one non-Wright stain colorant, which colorant is operable to differentially identify constituents containing cytoplasmic material; providing an analysis device having an analyzer with at least one processor, at least one sample illuminator, and at least one image sensor; creating an image of the sample using the analysis device; and using the analysis device to transform the image to a transformed image having a coloration recognizable as a Wright stained sample.

Abstract: A processor configured to execute a process includes receiving image information including biometric information, extracting, from the image information, a first phase component image representing a phase component included in the image information, converting the image information into first frequency information and converts the first phase component image into second frequency information, extracting a first feature vector and a second feature vector respectively on the basis of amplitude information of the first frequency information and the second frequency information determined in advance, and combining the first feature vector and the second feature vector on the basis of a prescribed rule.

Abstract: A biometric imager may comprise a plurality of sensor element traces formed in or on a sensor substrate which may comprise at least a portion of a display screen defining a biometric sensing area and forming in-active pixel locations; an auxiliary active circuit formed in or on the sensor substrate on the periphery of the biometric sensing area and in direct or indirect electrical contact with the sensor element traces; and providing a signal processing interface to a remotely located controller integrated circuit. The sensor element traces may form a portion of one dimensional linear sensor array or pixel locations in a two dimensional grid array capacitive gap biometric imaging sensor. The auxiliary circuit may provide pixel location selection or pixel signal amplification. The auxiliary circuit may be mounted on a surface of the display screen. The auxiliary circuit further comprising a separate pixel location selection controller circuit.

Abstract: A method and system are provided for navigating an image series that, includes at least one image. The method and system involve receiving an input corresponding to a reference location; operating at least one processor for determining a target position in the image series based on the reference location, the at least one processor being configured to receive initial series data corresponding to an initial location in the image series and a separation distance corresponding to a distance between two sequential images in the image series; determine a target distance for the image series, the target distance corresponding to a distance from the reference location to the initial location; and determine the target position based on the separation distance and the target distance.

Abstract: The present invention provides a system and method for simultaneous variational and adaptive segmentation of single non-overlapping and multiple overlapping/occluded-objects in an image scene. The method according to the present invention synergistically combines shape priors with boundary and region-based active contours in a level set formulation with a watershed scheme for model initialization for identifying and resolving multiple object overlaps in an image scene. The method according to the present invention comprises learning a shape prior for a target object of interest and applying the shape prior into a hybrid active contour model to segment overlapping and non-overlapping objects simultaneously.

Abstract: A method of processing a medical image signal includes estimating first time courses and first spatial patterns for a group of objects from first brain function data for the group, and estimating second time courses and second spatial patterns for a target object from second brain function data obtained from the target object by using the first time courses and the first spatial patterns.

Abstract: A method and apparatus of image compensation are provided. The method may include: calculating an overlapping position between two adjacent scannings; obtaining two images at the overlapping position of the two adjacent scannings, and calculating mutual information of the two images by using a three dimensional non-rigid registration method; and acquiring a corresponding transformational matrix when the mutual information reaches a threshold, and compensating one of the two scans which needs to be compensated by using the transformational matrix. Images at the overlapping position of two neighboring scannings can be used to find a motion law at an identical z position of the two adjacent scannings and to obtain a corresponding match factor. Thus inconsistence of images caused by a patient's movement can be compensated.

Abstract: A method and a system for data compression are provided. The method may include: obtaining scanning data to be compressed; compressing the scanning data using a first compression method and a second compression method to obtain a first compressed data and a second compressed data respectively, where a compression ratio of the first compressed data is lower than a compression ratio of the second compressed data; and determining whether the compression ratio of the first compressed data meets a predetermined compression ratio requirement, if yes, determining the first compressed data as a compression result data corresponding to the scanning data, if no, determining the second compressed data as a compression result data corresponding to the scanning data. Scanning data compressed by the method or the system can meet target compression requirements.

Abstract: Systems and methods for characterizing spatial distortions in location data determined by an imaging system, for example as employed in imaged guided therapy. A three dimensional phantom is custom formed for a desired imaging space of a given imaging system. The phantom includes a large plurality of control points fixed rigidly in space to a high degree of known accuracy. The phantom is fixed to a stereotactic frame defining a known calibrated reference or zero and imaged. An algorithm customized for the phantom determines the spatial locations of the control points. A comparison is made between the known and the determined spatial locations for at least a subset of the control points. The comparison results in indicia for any determined spatial distortions observed. The raw image data can be manipulated to compensate for any spatial distortion. The control points can have fixed locations known to an accuracy of 100 ?m or better.

Abstract: A method for anatomical analysis and joint implant design. Embodiments provide users with the ability to anatomically analyze a single bone or a series of bones that exist in a database, evaluate surgical landmarks and axes, identify differences among specific characteristics of a given population, and modify existing implants or create new implant designs based on anatomical analyses.

Abstract: The present disclosure relates to a self-prior information based X-ray dual-energy CT reconstruction method, which can utilize information inherent in data to provide a prior model, thereby obtaining a reconstructed image with a high quality. The X-ray dual-energy CT reconstruction method according to the present disclosure comprises: (a) rating an energy spectrum and establishing a dual-energy lookup table; (b) collecting high-energy data pH and low-energy data pL of a dual-energy CT imaging system using a detector of the dual-energy CT imaging system; (c) obtaining projection images R1 and R2 of scaled images r1 and r2 according to the obtained high-energy data pH and low-energy data pL; (d) reconstructing the scaled image r2 using a first piece-wise smooth constraint condition and thereby obtaining an electron density image; and (e) reconstructing the scaled image r1 using a second piece-wise smooth constraint condition and thereby obtaining an equivalent atomic number image.

Abstract: A first-image and a second-image representing the same organ of the same subject imaged at the same time are obtained, and an organ-region is extracted from the first-image. The extracted organ-region is displayed on a display screen. An input of an air-region included in the first-image and an input of exceeding or lacking portion information representing that the air-region is a lacking portion or an exceeding portion of the organ are received, and the received air-region and the received exceeding or lacking portion information corresponding to the air-region are obtained, as correction information. Corresponding positions are matched with other between the first-image and the second-image. The organ-region extracted from the first-image is corrected based on the correction information. At least an air-region in the second-image located at a position corresponding to the air-region corresponding to the correction information is extracted, as a part of the organ-region in the second-image.

Abstract: Provided herein is a computerized image reconstruction apparatus and method that includes recording projection path information and energy loss information of a plurality of particles traversing an object being imaged and determining an estimated image of the object based on the projection path information and the energy loss information sampled into a projection format. The estimated image includes an active volume defined by an enclosure border. Cost function minimization uses an Adaptive-weighted Total Variation cost function, a Penalized Weighted Least-Squares cost function, or an Alpha-Divergence cost function to update the estimated image. An iterative updating algorithm corresponding to the cost function updates the estimated image and produces a final image based on the estimated image according to a predetermined threshold.

Abstract: A method for the reduction of artifacts based on an unequal representation of the same material classes in various locations, in particular of cupping artifacts, in a three-dimensional image data set, reconstructed from two-dimensional x-ray projection images is provided. An image datum, describing an attenuation value, is allocated respectively to a voxel, wherein at least two material class regions are located in a post-processing step, which receive, in particular, image data, which is homogeneously distributed and lies in an expected material class interval of the attenuation values, and, considering at least one characteristic of the material class regions, calculates a smooth homogenization function, which is to be applied to the image data of the entire image data set and is applied to the image data of the image data set.

Abstract: Methods for updating a 2D/3D registration between a three-dimensional image data set corresponding to a target area subjected to a movement and a plurality of two-dimensional projection images of the target area include: selecting a plurality of contour points along a contour, the contour being visible in a first projection image and a three-dimensional image data set registered therewith, the plurality of contour points being associated with a rigid object in the target area; determining a displacement of each contour point of the plurality of contour points between the first projection image and a successively captured second projection image; obtaining movement information for each contour point of the plurality of contour points based on the determined displacement, the movement information describing a movement of the rigid object; and updating the registration based on the obtained movement information.

Abstract: A method for inspecting a substrate having a plurality of holes formed on a plate-shaped material so as to extend over front and rear surfaces thereof. The method comprises picking-up an image of a plurality of holes formed on the substrate by imaging from one surface side of the substrate and obtaining a hole image of each hole (S103). Then, specifying a reference hole image of the plurality of holes from an imaging result obtained by the image acquisition step (S105). Thereafter, a similarity between each hole image, being the imaging result obtained by the image acquisition step is quantified and the reference hole image, is obtained by pattern matching processing using a specific correlative function (S105 to S107). Finally, a proper/improper hole shape of each of the plurality of holes is judged using a quantification result of each hole image obtained by the quantification step as an index (S108).

Abstract: A method segments n-dimensional by first determining prior information from the data. A fidelity term is determined from the prior information, and the data are represented as a graph. A graph Laplacian is determined from the graph from the graph, and a Laplacian spectrum constraint is determined from the graph Laplacian. Then, an objective function is minimized according to the fidelity term and the Laplacian spectrum constraint to identify a segment of target points in the data.

Abstract: An image processing system comprises an image processor implemented using at least one processing device and adapted for coupling to an image source, such as a depth imager. The image processor is configured to compute a convergence matrix and a noise threshold matrix, to estimate background information of an image utilizing the convergence matrix, and to eliminate at least a portion of the background information from the image utilizing the noise threshold matrix. The background estimation and elimination may involve the generation of static and dynamic background masks that include elements indicating which pixels of the image are part of respective static and dynamic background information. The computing, estimating and eliminating operations may be performed over a sequence of depth images, such as frames of a 3D video signal, with the convergence and noise threshold matrices being recomputed for each of at least a subset of the depth images.

Abstract: A system and method of determining a depth map sequence for a subject two-dimensional video sequence by: determining a plurality of monocular depth cues for each frame of the subject two-dimensional video sequence; and determining a depth map for each frame of the subject two-dimensional video sequence based on the application of the plurality of monocular depth cues determined for the frame to a depth map model. The depth map model determined by: determining a plurality of monocular depth cues for one or more training two-dimensional video sequences; and determining a depth map model based the plurality of monocular depth cues of the one or more training two-dimensional video sequences and corresponding known depth maps for each of the one or more training two-dimensional video sequences.

Abstract: A method of decomposing an image or video into a plurality of components. The method comprises: obtaining (10) an intensity signal of the image or video; and decomposing (30) the intensity signal into a component representing the three-dimensional structure shape of one or more objects in the scene and at least one other component. Also provided is a method of performing an Empirical Mode Decomposition on data in two or more dimensions, using normalised convolution.

Abstract: Provided is an image processing device including a disparity detector configured to receive a plurality of 3D images and detect disparity of each of the 3D images, a disparity analyzer configured to generate statistical information about disparity of each 3D image using the disparity of each 3D image detected by the disparity detector, and a disparity controller configured to convert the disparity using the statistical information about disparity of each 3D image generated by the disparity analyzer in such a manner that the 3D images are not overlapped so that a range of the disparity is within a predetermined range.

Abstract: Three-dimensional (3-D) spatial image data may be received that is associated with at least one arm motion of an actor based on free-form movements of at least one hand of the actor, based on natural gesture motions of the at least one hand. A plurality of sequential 3-D spatial representations that each include 3-D spatial map data corresponding to a 3-D posture and position of the hand at sequential instances of time during the free-form movements may be determined, based on the received 3-D spatial image data. An integrated 3-D model may be generated, via a spatial object processor, based on incrementally integrating the 3-D spatial map data included in the determined sequential 3-D spatial representations and comparing a threshold time value with model time values indicating numbers of instances of time spent by the hand occupying a plurality of 3-D spatial regions during the free-form movements.

Abstract: Image restoration cascades are described, for example, where digital photographs containing noise are restored using a cascade formed from a plurality of layers of trained machine learning predictors connected in series. For example, noise may be from sensor noise, motion blur, dust, optical low pass filtering, chromatic aberration, compression and quantization artifacts, down sampling or other sources. For example, given a noisy image, each trained machine learning predictor produces an output image which is a restored version of the noisy input image; each trained machine learning predictor in a given internal layer of the cascade also takes input from the previous layer in the cascade. In various examples, a loss function expressing dissimilarity between input and output images of each trained machine learning predictor is directly minimized during training. In various examples, data partitioning is used to partition a training data set to facilitate generalization.

Abstract: A system may be configured as an image recognition machine that utilizes an image feature representation called local feature embedding (LFE). LFE enables generation of a feature vector that captures salient visual properties of an image to address both the fine-grained aspects and the coarse-grained aspects of recognizing a visual pattern depicted in the image. Configured to utilize image feature vectors with LFE, the system may implement a nearest class mean (NCM) classifier, as well as a scalable recognition algorithm with metric learning and max margin template selection. Accordingly, the system may be updated to accommodate new classes with very little added computational cost. This may have the effect of enabling the system to readily handle open-ended image classification problems.

Abstract: A classifier training system trains a classifier for evaluating image deblurring quality using a set of scored deblurred images. In some embodiments, the classifier training system trains the classifier based on a number of sub-images extracted from the scored deblurred images. An image deblurring system applies a number of different deblurring transformations to a given blurry reference image and uses the classifier trained by the classifier training system to evaluate deblurring quality, thereby finding a highest-quality deblurred image. In some embodiments, the classifier training system trains the classifier in the frequency domain, and the image deblurring system uses the classifier trained by the classifier training system to evaluate deblurring quality in the frequency domain. In some embodiments, the image deblurring system applies the different deblurring transformations iteratively.

Abstract: Disclosed are embodiments for a system, method, and computer program product for performing a process on an original image, the process being implemented by a computer system comprising at least one computer: performing a process on at least one image that renders the processed image more legible than then the original image.

Abstract: Data extraction templates are created and associated with source documents from a specific source document source. One or more known pictorial representations associated with one or more source document sources are then identified and key data is generated for the known pictorial representations. Source document data is then obtained and analyzed to identify potential pictorial representation data. Key data associated with the potential pictorial representation data is then generated and compared with the key data associated with one or more known pictorial representations and if the key data matches, the data extraction template associated with the matched known pictorial representations is obtained and used for identifying and extracting data from the source document data.

Abstract: A method and system is provided for combining information from a plurality of source images to form a fused image. The fused image is generated by the combination of the source images based on both local features and global features computed from the source images. Local features are computed for local regions in each source image. For each source image, the computed local features are further processed to form a local weight matrix. Global features are computed for the source images. For each source image, the computed global features are further processed to form a global weight vector. For each source image, its corresponding local weight matrix and its corresponding global weight vector are combined to form a final weight matrix. The source images are then weighted by the final weight matrices to generate the fused image.

Abstract: The present invention relates to charts, stacks and methods for evaluating skin color of a mammalian subject. The chart may include a substrate and an indicia visible from a first side of the substrate that includes a plurality of images of mammalian skin tones having varying degrees of yellowness, wherein each indicia is correlated with an index value. Also, the present invention relates to packaged topical cosmetic products that include a skin chart as well as to methods for evaluating anti-aging and skin lightening products.

Abstract: The disclosure concerns processing of electronic images, such as hyperspectral or multispectral images (302) to determine an output colour value for a component spectrum of a decomposed multispectral or hyperspectral image. A processor (120) first determines or accesses the component spectrum and a first colour value for the component spectrum and receives an input colour value for a pixel location in the image, wherein the component spectrum contributes to the pixel. The processor (120) then determines the output colour value for the component spectrum based on the first colour value for the component spectrum, the input colour value and a utility score and stores the output colour value for the component spectrum on a datastore (118). It is an advantage that the processor (120) receives a colour value for a pixel location but the output colour value is not exactly the received colour value but one that is determined based on a utility score.

Abstract: A computer implemented method and apparatus for a memory efficient approach for decoding progressive JPEG images. The method comprises (a) accessing a progressive JPEG image, wherein the progressive JPEG image comprises a plurality of compressed scans and wherein each scan in the plurality of scans comprises a plurality of compressed rows of image data; (b) decompressing not more than half of the compressed rows of each scan in the plurality of scans into a memory buffer; (c) copying a remaining plurality of compressed rows of each scan in the plurality of scans into a plurality of small memory buffers; (d) decoding, in place, the decompressed rows in the memory buffer; and (e) repeating steps (b)—(d) until a predefined number of rows are remaining in the plurality of small memory buffers, at which time the remaining rows are decompressed and decoded.

Abstract: Systems and methods are provided for simulating strobe effects with digital image content. In one embodiment, an image manipulation application can receive image content. The image manipulation application can generate blurred image content by applying a blurring operation to a portion of the received image content along a blur trajectory. The image manipulation application can sample pixels from multiple positions in the received image content along the blur trajectory. The image manipulation application can generate a simulated strobe images based on the sampled pixels and at least some of the blurred image content.

Abstract: Certain aspects relate to systems and techniques for correction of color artifacts including both color aberration and color spot artifacts using a unified framework. For example, both color aberration and color spot artifacts can be corrected using a post-processing method implementing directional median filtering on chroma channels. A pixel-by-pixel correction ratio map can be built by analyzing the luma and chroma components of the image to indicate a type of color artifact associated with each pixel in the image, and a directional median filter can be selected for each pixel based on the corresponding correction ratio map value.

Abstract: A method for applying a filter to data to improve data quality and/or reduce file size. In one example, a region of interest of an image is identified. A histogram is generated of pixel intensity values in the region of interest. The histogram is iteratively updated to focus (zoom) in on the highest peak in the histogram. A Gaussian curve is fitted to the updated histogram. A bilateral filter is applied to the images, where parameters of the bilateral filter are based on the parameters of the Gaussian curve.

Abstract: An overlapped handwriting input method, which includes: moving a touch unit on a touch screen, recording and displaying the track of a stroke on a handwriting area of the screen; determining whether the stroke currently being written and all previously input strokes having a color A belong to the same character; if yes, keeping the current stroke color unchanged; otherwise, determining whether an inactive visual layer character is present on the screen; if yes, clearing an image of the inactive character and related stroke information; otherwise, defining as the inactive character all strokes having the color A, excluding the current stroke; submitting data of the current inactive character to a recognition engine, and outputting a recognition result. Thus, the interface friendliness for users to continuously input handwriting according to their natural writing practice is ensured, and multiple handwritten characters can be written continuously without pause, thereby improving handwriting input efficiency.

Abstract: A method includes determining a position and length of a non-zero run in a row of a pixel map. The method also includes determining a number of neighbors for the non-zero run in a preceding row, based at least in part on the position and the length. In addition, the method includes updating a correspondence map of the non-zero run and a correspondence map of a first neighbor of the non-zero run, based at least in part on a correspondence map of a second neighbor of the non-zero run, in response to a determination that the non-zero run has at least two neighbors in the preceding row.

Abstract: Important information about an object is detected using less arithmetic processing. An object detection unit generates an edge image from a color image. The object detection unit evaluates symmetry of an image included in the edge image by performing processing in accordance with the position of a target pixel. The object detection unit identifies a symmetry center pixel forming an object having symmetry. The object detection unit detects an object width for each symmetry center pixel. The object detection unit identifies the width of the object in the vertical direction based on the width of the symmetry center pixels in the vertical direction, and identifies the width of the object in the horizontal direction based on the object width identified for each symmetry center pixel.

Abstract: The present invention is a method for carrying out high-level activity recognition on a wide variety of videos. In one embodiment, the invention leverages the fact that a large number of smaller action detectors, when pooled appropriately, can provide high-level semantically rich features that are superior to low-level features in discriminating videos. Another embodiment recognizes activity using a bank of template objects corresponding to actions and having template sub-vectors. The video is processed to obtain a featurized video and a corresponding vector is calculated. The vector is correlated with each template object sub-vector to obtain a correlation vector. The correlation vectors are computed into a volume, and maximum values are determined corresponding to one or more actions.

Abstract: Method of measuring a point cloud of an object includes obtaining the point cloud of the object from a storage device of the electronic device. Based on the point cloud, a triangular mesh surface is constructed and triangles of the triangular mesh surface are determined. According to the triangles, a reference plane is determined. According to the reference plane, a three dimensional (3D) object coordinate system is established. 3D object coordinates of points in the point cloud are calculated in the 3D object coordinate system. Measurement elements of a profile of the point cloud are determined and points in the point cloud corresponding to each of the measurement elements are determined. According to the 3D object coordinates of the determined points corresponding to each of the measurement elements, each of the measurement elements are fit. A distance and an angle of two fit measurement elements are calculated.

Abstract: An image processing device includes an image sequence acquisition section that acquires an image sequence that includes a plurality of images, and a processing section that performs an image summarization process that deletes some of the plurality of images included in the image sequence acquired by the image sequence acquisition section to acquire a summary image sequence, the processing section selecting a reference image and a determination target image from the plurality of images, and determining whether or not the determination target image can be deleted based on the results of a process that utilizes deformation information about the reference image and the determination target image, and a process that utilizes a structural element that corresponds to an attention area.

Abstract: The present disclosure relates to a method and apparatus for classifying pixels in an input image and image processing system. The apparatus includes a first confidence determination unit configured for determining a first confidence of each of the pixels in the input image belonging to each of a plurality of predetermined classes; a detection unit configured for acquiring, by using a detector for detecting a particular class among the plurality of predetermined classes, detection results used to indicate pixels which belong to the particular class; an updating unit configured for updating the first confidences according to the detection results; and a class determination unit configured for determining the class to which each of the pixels in the input image belongs among the plurality of predetermined classes, according to the updated first confidences.

Abstract: Multi-sensor compressive imaging systems can include an imaging component (such an an RF, microwave, or mmW metamaterial surface antenna) and an auxialiary sensing component (such as an EO/IR sensor). In some approaches, the auxiliary sensing component includes a structured light sensor configured to identify the location or posture of an imaging target within a field of view of the imaging component. In some approaches, a reconstructed RF, microwave, or mmW image may be combined with a visual image of a region of interest to provide a multi-spectral representation of the region of interest.

Abstract: A method includes implementing, through a processor communicatively coupled to a memory and/or a hardware block, a Bilateral Filter (BF) including a spatial filter component and a range filter component, and implementing the spatial filter component with a low-complexity function to allow for focus on the range filter component. The method also includes determining, through the processor, filter tap value(s) related to the range filter component as a function of radiometric distance between a pixel of a video frame and/or an image and other pixels thereof based on a pre-computed corpus of data related to execution of an application in accordance with a filtering requirement of the pixel by the application. Further, the method includes constraining, through the processor, the filter tap value(s) to a form i×base based on the BF implementation. i is an integer and base is a floating point base.