32results about How to "Suppress background clutter" patented technology

A non-negative constrained 2D variational mode decomposition based infrared small and small target detection method, which solves the problem that the frequency band of infrared small and small targets is difficult to be accurately estimated in the prior art, the detection results are easily interfered by noise and background clutter, and the detection efficiency is low. The problem belongs to the technical field of infrared weak and small target detection. The invention includes obtaining an infrared image, using a band-pass filter to preprocess the infrared image, constructing an objective function by combining a two-dimensional variational mode decomposition method with non-negative constraints, and then inputting the preprocessing result into the objective function, and according to the objective function The solution outputs the decomposition result, and the result is K non-negative narrow-band sub-signals. Extract a narrow-band sub-signal corresponding to the infrared weak and small target in the above results to obtain the target sub-signal; perform adaptive threshold segmentation on the extracted target sub-signal, determine the position and size of the infrared weak and small target, and output the detection result. It is used for infrared weak and small target detection.

The invention relates to an infrared target detection method based on a space-time cooperation framework. The method comprises the following steps: 1. acquiring a background frame Bg and a current frame Ft of a video, combining the background frame Bg and the current frame Ft to carry out background clutter suppression and acquiring a background suppression graph Gt after the background clutter suppression is performed; 2. for the background suppression graph Gt obtained in the step 1, firstly establishing a space-time background model, and then carrying out target positioning aiming at space-time background model information after the model is established; 3. according to an imaging mechanism of the infrared target, analyzing a space difference of the infrared target and the surrounding background, using a fuzzy adaptive resonance nerve network to carry out local classification aiming at the target which is positioned in the step 2 and then extracting the infrared target. The method has the following advantages that: the method does not depend on any target shapes and motion information priori knowledge; the method is suitable for a complex outdoor scene; a signal to noise ratio can be increased; a target detection rate can be increased and a calculated amount can be reduced; false targets can be effectively removed and a false alarm rate can be reduced; the method is beneficial to follow-up target identification.

The invention discloses a method for locating a concealed target at a corner of a single building based on an ultra-wideband multipath radar, and mainly solves the problem of locating a non-direct sight target in an urban environment. The present invention utilizes the multi-path diffraction characteristics of electromagnetic waves to locate hidden targets behind corners, and first uses moving target display technology to perform background cancellation to suppress strong background clutter, and uses a median filter algorithm to smooth the canceled echo signals Denoising processing, and then use the unit average constant false alarm detection to extract the peak value corresponding to the direct diffraction path and the side wall reflection path from the echo, and calculate the Finally, the α-β filtering method is introduced to improve the positioning accuracy of moving targets. The present invention has the advantages of simple realization process, small amount of calculation in the whole process of target position acquisition, and high target positioning accuracy. The invention can be applied to fields such as urban street fighting, anti-terrorist stability maintenance, disaster rescue and the like.

The invention discloses a spatial variable-resolution infrared double-color imaging detection system, which comprises a double-view-field coaxial infrared double-color imaging light path system, a complex background clutter image double-color detection recognition signal processing system, an micro electro mechanical system (MEMS) scanning-based narrow-view-field imaging control system and a double-view-field image information fusion and decision system. The system mainly solves the problem that high-resolution, large-view field, real-time imaging and transmission cannot be taken into consideration at the same time in the modern optical reconnaissance, surveillance and early warning. The system has the advantages of high resolution, large view field, real-time imaging and the like, and can be used in fields of image compression, target recognition and tracking, surveillance and early warning and the like.

The invention discloses a point target detection method and system based on machine learning, comprising: determining an image to be detected, and dividing it into a plurality of sub-images with preset sizes; using MMF to filter each sub-image to obtain the filtered sub-image Output, if the filter output is less than or equal to the preset threshold, then it is judged that the sub-image is the background, otherwise the sub-image is marked as a candidate sub-image, and the filter scores of each candidate sub-image are determined; through the pre-trained BP neural network The classifier obtains the confidence score of each candidate sub-image containing the target; the filter score of each candidate sub-image and its confidence score of containing the target are input into the pre-trained Logistic regression classifier, and the output value of the Logistic regression classifier is combined Determine whether each candidate sub-image contains an object. The invention uses the Logistic regression algorithm to fuse the results of the MMF algorithm and the BP algorithm to make the classification result more accurate.

The invention discloses an infrared small target detection tracking and identification method. Two different tree building methods of Max-tree and Min-tree are used for respectively detecting targetswith different brightness, the Max-tree mainly aims at a target of which the gray value is brighter than that of a background, and the Min-tree is mainly used for a target of which the gray value is darker than that of the background; two most significant features of the infrared small target, namely size information of the infrared small target and contrast information between the small target and the background, are extracted by using two attributes of an area attribute and a height attribute; and finally, tracking of the small target is realized through Mean-shift. The method has the following advantages: in the Max-tree and Min-tree, discontinuous pruning strategies are respectively used for two attributes, and results obtained by different pruning values under the same attribute and results obtained by different attributes are fused through different fusion strategies.

The present invention provides a method for extracting oceanic internal wave parameters in SAR images. The method is based on local low-rank priors, and constructs a local low-rank optimization model for image slices containing oceanic internal waves, and solves the problem by alternately optimizing the model. , to obtain the optimal rotation angle low-rank image slice and high radiation resolution image slice to extract the SAR image ocean internal wave wavelength ω. The local low-rank optimization model constructed by the present invention makes full use of the statistical characteristics of SAR image coherence spots and the local low-rank characteristics of ocean internal waves, which can well suppress SAR image coherence spots, protect target structure information and target scattering characteristics Maintaining and effectively realizing SAR image target recognition, feature extraction can still be achieved in the case of weak ocean internal wave contrast and waveform damage, and the model can be robustly solved numerically, which is easy to implement.

The invention belongs to the field of image target recognition, and provides a remote sensing ship recognition method based on dense feature fusion and pixel-level attention. Target recognition is a target, a large number of small targets are missed, and bounding boxes are easy to overlap. The main scheme is to divide the remote sensing image data set into data sets, obtain the training set and test set, and perform data enhancement on the training set; calculate the RGB three-channel average value r of the original remote sensing image data set mean , g mean , b mean , the RGB three-channel value of the image in the expanded data set and r mean , g mean , b mean Corresponding subtraction; input the obtained data set into the improved Faster RCNN network for training, the core modules of the network are dense feature fusion network and pixel-level attention network, and the network outputs candidate rotation boxes and their category scores; The non-maximum suppression of the rotating frame based on the skew IOU can obtain the recognition result of the ship target in the remote sensing image.

The invention discloses a pretreatment method for decomposed, reconstituted and strengthened infrared small targets based on singular values. The method comprises the following steps: conducting singular value decomposition (SVD) on the inputted image to obtain the singular values of the image; analyzing and estimating singular value curves of the image to obtain prediction curves of the singular values, subtracting the obtained prediction curves of the singular values and the original singular value curves to obtain the differential singular value curves, and conducting normalization on the differential singular value curves to obtain differential percentage curves of the singular values; and reconstituting the image after singular value decomposition (SVD) based on the differential percentage curves of the singular values to obtain the strengthened infrared small target image. By using the method of the invention, the signal-to-noise ratio of the image can be well improved, background clutters can be suppressed, and the effect of the method is superior to that of the other methods at present.