128 results about "Correlation filter" patented technology

The invention discloses a ship target detection and tracking method and system based on video image processing, and the method comprises the steps: 1), collecting a channel panoramic video stream through a high-definition camera, and extracting a continuous image sequence; 2) constructing a dynamic channel background model by using a Gaussian mixture model (GMM), and updating the background in real time to eliminate interference of water surface fluctuation and illumination variation; (3) enhancing the data obtained in the step (1) by adopting a Mosaic enhancement method, and establishing a data set; 4) optimizing a Yov7 model, and introducing a lightweight CBAM attention mechanism to carry out model training; (5) the trained weight model is experimented on the verification set, and target detection of the ship is achieved; and 6) adopting a kernel correlation filtering algorithm to realize real-time tracking of the moving ship. According to the method, the technology in the field of computer vision is utilized, the real-time video image number of the large-flow channel is effectively utilized, multi-target recognition and real-time tracking are achieved, and the method has high accuracy and robustness.

An unmanned aerial vehicle target detection tracking method based on intelligent image matching comprises the steps that an unmanned aerial vehicle collects images to make a data set, a model file is obtained through twin neural network training, the model file is loaded to detect a video stream, a current frame target position and detection frame information are obtained, whether the frame is a first frame is judged, and if yes, the target is detected; using a target position information result to initialize a kernel filtering algorithm, and constructing a measurement vector; if not, calculating correlation by using a kernel correlation filter, taking the highest response position as a prediction bit, and constructing a measurement vector; calculating a Kalman gain, and inputting the Kalman gain into a Kalman filter to obtain a predicted state estimated value = (); comparing y-axis deviations of the detector and the tracker, and setting a threshold value for judgment; according to the method, target tracking under resource limitation is realized through light-weight twin network detection in combination with kernel filtering and improved Kalman filtering, the problems of high target loss rate and low precision are solved, and the method is suitable for the fields of military reconnaissance, intelligent autonomous attack and the like.

The invention discloses an automatic frequency stabilization system based on dual-core correlation matching intelligent peak searching. The automatic frequency stabilization system comprises the following steps that S1, a saturated absorption spectrum light path and a circuit are built, debugged and optimized; s2, constructing a double-matching template; s3, triangular wave voltage scanning and clock timing are started, and signals are collected and transmitted; s4, starting a KCF algorithm, applying a template to track model matching, judging a result obtained by matching, finding a peak point and solving a corresponding scanning voltage; and S5, recording a peak point scanning voltage, closing a scanning signal, starting sinusoidal signal modulation, and giving a triangular wave scanning voltage corresponding to a peak value to the sinusoidal signal as an offset. The spectrum line peak value suspected area can be effectively positioned, the double-branch and correlation filtering tracking method can perform precise secondary searching in the suspected area, the locking precision is greatly improved, the long-term stability of 10-12 orders of magnitude is ensured, and meanwhile the good vibration interference resistance can be achieved when a vibration signal occurs.

The invention relates to the technical field of target tracking, in particular to a target loss and recapture method based on correlation filtering, and the method comprises the steps: judging the target loss and recapture conditions through a correlation filtering algorithm and weighted logic; when the target appears again, judging whether the scale changes or not, and then increasing or reducing the corresponding step length to change the scale; the method comprises the following steps of: carrying out target repositioning by adopting an SURF (Speeded Up Robust Features), carrying out target detection by using the extracted SURF after a locked target is lost, and when the target appears again, re-determining the position of the target through feature matching; when the target is about to be lost, template updating is suspended, key frame features are reserved, and a recognition algorithm or SURF feature matching is utilized to recapture the target position; and the next frame of video stream is read for continuous tracking, and if the video stream reading is finished or the tracking fails, the tracking is stopped, so that the technical problems of low tracking success rate and low tracking accuracy in the prior art under the complex conditions of a fast moving target, long-time shielding, continuous change of the target size and the like are solved.

The invention provides a rainbow pattern elimination AR display device based on an angle correlation filtering film, and relates to the field of augmented reality display. The device comprises a micro display, an optical waveguide structure lens and angle correlation filtering films on the surfaces of the two sides of the lens. The angle correlation filtering film sequentially comprises a second protection layer, a second grating layer and a substrate layer; the second grating layer is composed of light-transmitting units and light-shading units in an alternating mode. The shading unit adopts an asymmetric structure, and the asymmetric angle response of the angle correlation filtering film is matched with the lens coupling-out grating; and the second grating layer adopts a special arrangement mode to inhibit the diffraction effect. According to the augmented reality display device, large-angle external environment light is prevented from entering the grating area through the angle correlation filtering film, so that rainbow lines of the augmented reality display device are eliminated, the augmented reality display device has the advantages of being insensitive to wavelength and polarization and light and thin, diffraction artifacts cannot be additionally introduced, and the imaging quality and user experience of the augmented reality display device can be improved.

The invention discloses a space-based distributed multi-sensor multi-target tracking and positioning method. The method comprises the following steps: firstly, acquiring a grayscale image of each sensor, and extracting coordinates of a target in the image; and matching a serial number for the extracted target, and taking a first frame coordinate and an image sequence of the target as tracking input. The tracking process is based on a discriminant correlation filter, an energy concentration threshold value of small target features is added, a double-constraint trajectory correlation model of target spacing and speed similarity between continuous frames is constructed, and a Kalman filtering algorithm is used to predict a target position. An adaptive covariance cross fusion positioning algorithm is designed among multiple sensors, a geometrical relationship between multiple detection satellites and a target is established, and the three-dimensional position of the target is calculated by using sensor observation parameters as a basis for adjusting fusion weights. The method can significantly improve the target tracking precision and suppress the positioning offset problem caused by instability of part of sensors, can adapt to the dynamic change of a distributed detection scene, and ensures the accurate target positioning.

The application discloses a structure interlayer displacement automatic measurement method and system based on visual data and belongs to the technical field of structure displacement measurement. The measurement method comprises the following steps: acquiring video data in the vibration process of a building based on a monitoring camera; processing the video data by using an improved kernel correlation filtering algorithm to extract building interlayer displacement information; verifying the extracted displacement information and outputting building interlayer displacement results. On the basis of a classical kernel correlation filtering target tracking method, the application utilizes image pyramid, robust feature extraction and discrete Fourier transform up-sampling technology to expand the tracking range, enhance the edge features and improve the tracking precision; the application fully utilizes the existing monitoring camera equipment to measure the interlayer displacement, does not need to additionally arrange sensors and reduces the cost budget.

The audio device comprises a receiver (201) arranged to receive a set of input audio signals. An audio beamformer (101) performs beamforming by combining the outputs of the filters. The feedback circuit (103) comprises a set of matched filters having a complex conjugate frequency response, and the beamforming adapter (105) adapts the filters in response to a comparison of the input audio signal and the feedback audio signal. An adaptation coefficient processor (207) determines decorrelation coefficients for a set of spatial decorrelation filters that generate a decorrelated output signal from an input audio signal, where the decorrelation coefficients are adapted based on the input signal. A set of spatial filters (205, 301, 401) is arranged to apply spatial filtering to the input audio signal or the feedback signal, wherein the set of spatial filters has coefficients determined from the decorrelation coefficients.

The invention provides an underwater target speed measurement method and device based on template correlation, and the method comprises the steps: obtaining an echo signal of a transmitting signal, the transmitting signal comprises a frequency modulation signal and a single-frequency pulse signal, and the transmitting signal forms the echo signal after being reflected by a target; determining a target frequency spectrum and a template frequency spectrum according to the echo signal, the frequency modulation signal and the single-frequency pulse signal; performing correlation filtering analysis on the target spectrum and the template spectrum to obtain a search spectrum; according to the transmitting frequency of the single-frequency pulse signal, determining the Doppler frequency corresponding to the maximum amplitude value from the search range of the search spectrum; and calculating the radial speed of the target according to the Doppler frequency and the transmitting frequency of the single-frequency pulse signal. Therefore, the accuracy of determining the movement speed of the target is improved.

This invention discloses a method for inspecting the assembly quality of parts in confined spaces based on 3D enhanced correlation filtering, relating to the field of machine vision. The method includes: acquiring template images of correctly assembled parts and marking the locations of the parts as regions of interest; extracting region features and training a correlation filter; obtaining the overall correlation filter response using features from the tested image; performing multi-feature adaptive fusion based on preset evaluation metrics; correcting the fused correlation filter response using a depth-sensing 3D enhancement method; determining whether a part is occluded based on the fused correlation filter response; dividing the identified occluded region into sub-regions, detecting each sub-region to obtain the fused correlation filter response, and weighting and correcting it; determining the unoccluded areas of the part based on the enhancement results; and determining whether the part is incorrectly installed based on the 3D enhanced correlation filter response. This invention effectively solves the problems of incorrect, missing, and incomplete installation of parts in confined spaces with occluded targets.

The invention discloses a method for automatically tracking a target with a correlation filter guided by dynamic and static conditions, constructs a model for automatically tracking a target with a correlation filter guided by dynamic and static conditions, and optimizes and solves the model for automatically tracking a target with a correlation filter by using an ADMM method; inputs a first single-frame image and a target to be tracked; step 3: inputs the next single-frame image, performs dynamic and static guidance and target detection; step 4: performs N optimization iterations on the model for automatically tracking a target with a correlation filter, and updates the model for automatically tracking a target with a correlation filter by using a corresponding update formula; if the last single-frame image has not been reached, returns to step 3; if the video has reached the last single-frame image, outputs the target obtained by the final tracking of each frame of video and the average video tracking rate FPS. The features of a single-frame image are used as static guidance, and the correlation filter of the previous single-frame image is used as dynamic guidance, and the update of the correlation filter of the next single-frame image is jointly guided.

The present invention discloses a long-term target tracking method and system integrating depth information, the method comprising: using a laser rangefinder to measure the depth information of the target in the current frame; predicting the depth of the target in the next frame based on a CA model; using a position-related filter and a scale-related filter to estimate the target position and the target scale according to a new frame of input image; using the predicted depth information to construct a target confidence discriminant, discriminate the output of the position filter, and determine how to determine the target position; using the predicted depth, construct an adaptive scale factor to determine the target scale; inputting the estimated target position and scale into a hardware tracking system, aligning the pan / tilt with the target, and acquiring a new frame of image; repeating the above process; until the target tracking is completed. The present invention integrates the depth information of the target into the entire tracking process, and uses the difference between the target and the background in the depth direction to effectively reduce the adverse effects caused by occlusion and background aliasing, and realizes long-term and effective tracking of the target.

A system can include a distributed acoustic sensing (DAS) system and a computing device coupled with the DAS system. The DAS system can include a pulse generator and a sensing fiber that can be positioned in a wellbore. The system can generate a light pulse to be transmitted into the sensing fiber to make one or more measurements relating to a wellbore operation involving the wellbore. The system can receive an initial pulse that includes a reflection of the light pulse prior to the light pulse entering the sensing fiber. The system can apply a cross-correlation filter to one or more subsequently received pulse reflections originating from the sensing fiber. The cross-correlation filter can include the initial pulse reflection or synthetic initial pulse. The system can generate, based on applying the cross-correlation filter, an output signal that can be used to control the wellbore operation.

This invention relates to an object detection device. The object detection device (1) includes: a drive signal generation unit (5) that generates a drive signal including frequency modulation; a first correlation filter (62) that performs correlation detection between the received signal and a first reference signal corresponding to the drive signal; a first determination unit (8) that determines whether the received wave is a reflected wave of a detection wave transmitted from a transmitting unit (40A) based on the correlation signal of the first correlation filter; a second correlation filter (63) that uses a signal corresponding to a portion of the drive signal as a second reference signal and performs correlation detection between the received signal and the second reference signal; a third correlation filter (64) that uses a signal including a portion of the drive signal with a frequency higher than the second reference signal as a third reference signal and performs correlation detection between the received signal and the third reference signal, wherein the third reference signal is a signal corresponding to a portion of the drive signal; and a second determination unit (9) that determines whether an object is within the detection range based on the correlation signals of the second and third correlation filters.

This invention provides an intelligent cockpit interaction management method, relating to the field of data processing technology. The method includes: receiving voice interaction data, gesture interaction data, and facial expression interaction data collected in the cockpit; performing intent parsing to extract triggering conditions and target functions; combining vehicle operating status parameters, in-vehicle noise level parameters, and driver gaze area parameters to perform correlation filtering; performing conflict detection to determine and remove interaction intents with abnormal triggering conditions or conflicting target functions as invalid; classifying tasks according to the category of target functions to generate a task candidate queue; confirming tasks in the task candidate queue and generating a valid task queue for tasks that meet the triggering conditions; and performing task scheduling according to the valid task queue, interrupting low-priority tasks and switching execution when a higher-priority task input is detected. This invention improves the accuracy of cockpit interaction management.

In various examples, image regions can be extracted from a batch of one or more images, and the image regions can be scaled to one or more template sizes in batches. In cases where the image region includes a search region for object localization, the scaled search region can be loaded into the Graphics Processing Unit (GPU) memory and processed in parallel for localization. Similarly, in cases where the image region is used for filter updates, the scaled image region can be loaded into the GPU memory and processed in parallel for filter updates. The image regions can be processed in batches from any number of images and / or from any number of single-object and / or multi-object trackers. Other aspects of the present disclosure provide methods for associating locations using correlation response values, methods for enabling a correlation filter to learn in object tracking based at least on focus windowing, and methods for enabling a correlation filter to learn in object tracking based at least on an occlusion map.

The invention relates to a method in the field of target tracking, in particular to a target tracking method based on a deep learning twin network, and aims to solve the problems that in the prior art, a tracking model can generate pollution superposition under the scenes of target shielding, severe deformation, view field exiting and the like; the difficulty of distinguishing similar targets is high; and a disordered background is easy to pollute the similar targets. The target tracking method based on the deep learning twin network comprises the following steps: capturing local and global context information by using a deep separable convolutional network, enhancing features by using a multi-scale large-kernel module, carrying out association operation by using the twin network, and obtaining a target bounding box by using a classification regression network, so that target tracking is accurate, efficient and flexible; compared with a traditional correlation filter algorithm, the method has better performance and algorithm robustness.

The object detection device of the present application is provided with: a transceiver (4) that transmits an ultrasonic wave encoded by frequency modulation and receives the ultrasonic wave and outputs a reception signal; a first quadrature detector (61) that generates a complex reception signal by quadrature detection of the reception signal and outputs it; a second quadrature detector (71) that generates a complex reference signal by quadrature detection of a reference signal and outputs it; a correlation filter (62) that performs correlation detection of the complex reception signal and the complex reference signal and outputs a correlation signal; and a code determination unit (8) that determines a code contained in the reception signal based on the correlation signal.

The invention discloses a narrow space part assembly quality detection method based on three-dimensional enhanced correlation filtering, and relates to the field of machine vision. Comprising the following steps: acquiring a template image of a correctly assembled part, and marking the position of the part as a region of interest; extracting regional features and training a correlation filter, and detecting the features of the detected image to obtain an overall correlation filter response; performing multi-feature adaptive fusion based on a preset evaluation index; correcting the fusion correlation filtering response by using a depth perception three-dimensional enhancement method; judging whether the part is shielded or not according to the fused correlation filtering response; dividing the area which is judged to be shielded into sub-areas, detecting each sub-area to obtain a fusion correlation filtering response, and carrying out weighted correction on the fusion correlation filtering response; judging an unshielded area of the part according to an enhancement result; and judging whether the parts are installed wrongly according to the three-dimensional enhanced correlation filtering response. The problems of wrong installation, neglected installation and not-in-place installation of parts under the condition of target shielding in a narrow space are effectively solved.

A method is provided. The method comprises: obtaining HR filter data indicative of a set of head-related HR filters for generating audio corresponding to temporal and / or spectral variations of sound waves; determining a time interval for evaluating HR filters included in the set of HR filters; and evaluating at least one HR filter included in the set of HR filters using the determined time interval. Audio is generated based on the evaluation.

To provide a signal processing method that provides an adaptive tonality control, a program, and a digital signal processing apparatus.SOLUTION: A method includes: calculating a shape dependent filter magnitude response (30); calculating a level dependent filter magnitude response (20); calculating a result response based on the shape and level dependent filter magnitude responses (40); and calculating an output signal by convolving an input signal with the result response (50). The calculation of the shape dependent filter magnitude response comprises: calculating a magnitude spectrum of a signal (110); filtering the resulting magnitude spectrum by using a first smoothing filter (120); applying a predetermined weighting curve to the spectrum (130); detrending the weighted spectrum by fitting a curve to the weighted spectrum and subtracting the fitted curve from the weighted spectrum (140); and inverting the resulting spectrum to form the shape dependent filter magnitude response (150).SELECTED DRAWING: Figure 1

A signal processing method for processing audio signals and in particular for adjusting the tone of music signals is disclosed. The method provides adaptive tonality control. Here, a shape dependent filter magnitude response is calculated, a level dependent filter magnitude response is calculated, a result response is calculated based on the shape and level dependent filter magnitude responses, and an output signal is calculated by convolving an input signal with the result response. In particular, the calculation of the shape dependent filter magnitude response comprises at least the steps of calculating a magnitude spectrum of a signal, filtering the resulting magnitude spectrum using a first smoothing filter, applying a predetermined weighting curve to the spectrum, detrending the weighted spectrum by fitting a curve to said weighted spectrum and subtracting said fitted curve from said weighted spectrum, and inverting the resulting spectrum to form the shape dependent filter magnitude response.

In various examples, a technique for computing feature correlations given a stereo image pair (captured using two or more image sensors having at least partially overlapping fields of view) is disclosed. The technique includes, for one or more channels in a set of feature channels, receiving a first feature map for a first image in a stereo image pair and a second feature map for a second image in the stereo image pair and computing a corresponding set of correlation maps. The technique also includes generating a set of compressed correlation maps; masking one or more portions of individual compressed correlation maps of the set compressed correlation maps based at least on a respective correlation filter to generate a corresponding set of masked correlation maps; and generating a depth map associated with the stereo image pair based at least on the set of masked correlation maps.

The application relates to a target tracking method for a high-speed rotating platform, which comprises the following steps: acquiring an initial frame image for target tracking; acquiring a next frame image, performing image rotation according to a rotation angle existing in the initial frame image, and obtaining a rotated image eliminating the rotation angle; taking a target point coordinate of a previous frame image as a center, adopting a correlation filtering model to perform target detection in the rotated image, and obtaining a target point coordinate in the rotated image; converting the target point coordinate in the rotated image to a target point coordinate in a pre-rotated image, and taking the target point coordinate in the pre-rotated image as a center to obtain a search region; updating the correlation filtering model, and performing target tracking on a next frame image; and further performing target tracking on all subsequent frame images. The application realizes stable tracking in the high-speed rotating process of the image.

The application discloses a visual target tracking system and method based on a nano unmanned aerial vehicle, aiming at the problem that a traditional kernel correlation filter tracking algorithm cannot adapt to target size change, introduces a scale filter, so that the tracking algorithm can adaptively adjust the size and position of a target frame according to the change of the target scale; a method based on time context information is adopted to realize template updating, so that the tracking template has time correlation and can more accurately reflect the change of the target in appearance and motion state; a long-short-term tracking strategy is adopted to combine the information of short-term tracking and long-term tracking, so that the target tracker can still maintain high precision and robustness in a long-time tracking task, and the real-time requirement is met; the application is experimented on a Crazyflie2.1 nano quadrotor platform, and realizes stable and rapid target tracking control on the nano quadrotor unmanned aerial vehicle.

The present invention discloses a method for tracking hidden targets behind walls applicable to low signal-to-noise ratio environments, which is applied to the field of radar tracking technology. Aiming at the problem in the prior art that in a complex electromagnetic environment, there is a lot of clutter and noise in the echo, resulting in poor imaging quality and thus difficult target tracking. The present invention first reconstructs the scene by using the back-projection method. Then, it extracts the target area features and establishes a target template based on the ridge regression idea, establishes a scale pool with small scale change in the range direction and large scale change in the azimuth direction based on the through-wall radar target imaging mechanism and the characteristics of the target after imaging. Then, it tracks the target in the next frame based on the correlation filtering idea, updates the target template for each frame to adapt to the changes in the through-wall radar target features, and finally dynamically estimates the target area and obtains the tracking trajectory. The present invention can achieve precise tracking of hidden targets behind walls in low signal-to-noise ratio scenarios.

The aircraft tracking method, storage medium and electronic device based on background-aware correlation filtering relate to the technical field of remote sensing video tracking and solve the problem of cloud and fog occlusion. The method includes: initializing the BACF correlation filter, determining the object function, calculating the feature maps of CN and HOG respectively and fusing them to obtain the final feature map; converting the BACF correlation filter to the frequency domain, using L2 regularization to constrain the update of the time series, and using the ADMM algorithm to solve the problem after the constraint; calculating the average peak correlation energy and temporarily storing the point with the largest response value as the final result; judging that the average peak correlation energy in the previous step meets the high confidence, updating the model and the target position based on the calculation result; otherwise, using the motion estimator to estimate the motion state, and weightedly fusing the result of the motion estimator and the calculation result to obtain the updated result; S5, repeating S2, S3 and S4 until the video playback ends.

The application provides a template pool matching-based anti-occlusion tracking and re-detection system and method, which comprises two parts of a template pool tracking module and a sparse matrix re-detection module; the template pool tracking module is mainly optimized for a traditional kernel correlation filter algorithm, an adaptive feature fusion strategy is used to cope with scenes rich in texture information and scenes rich in color information respectively, and APCE and PSR two criteria are combined to judge the occlusion condition in the tracking process; the template pool strategy stores and compares the space-time context information to cope with the occlusion scene; the sparse matrix re-detection module searches the possible positions of the target through a sparse sampling method in multiple threads to achieve the purpose of fast recapture when the target loss occurs.

A method for generating a head-related (HR) filter for audio rendering is provided. The method comprises generating HR filter model data which indicates an HR filter model, and based on the generated HR filter model data, (i) sampling one or more basis functions and (ii) generating first basis function shape data and shape metadata. The method further comprises providing the generated first basis function shape data and the shape metadata for storing in one or more storage mediums.

The present application discloses a deep discriminant target tracking method, device, electronic device and computer-readable storage medium for improving the robustness and effectiveness of target tracking. The method includes: determining the search area of ​​the current frame image based on the center position of the target area of ​​the previous frame image tracking; dividing the search area into components to obtain a first overall component and a first local component; based on the features of the first overall component and the features of each first local component, using the corresponding correlation filter of each component to act on each component respectively, to obtain the correlation response map of the first overall component and the correlation response map of each first local component; based on the correlation response map of the first overall component and the correlation response map of each first local component, to obtain the overall correlation response map; using a particle filter framework to collect multiple candidate tracking target areas from the overall correlation response map, and using the candidate tracking target area with the highest confidence as the tracking target area of ​​the current frame image.