A system is configured to receive synthetic aperture radar (SAR) backscatter signatures of a geographical area including the object of interest from a SAR device. The system also extracts feature vectors from the SAR backscatter signature based on the intensity values of the SAR backscatter signature. The system inputs the one or more feature vectors into a neural network model. The system receives, as output from the neural network model, coordinate values indicating one or more visual features of the object of interest. Using these coordinate values, the system determines one or more measurements of the object of interest.

A data generation device is provided with environment setting means (200), model setting means (210), image calculation means (220) and data output means (230). The environment setting means sets a radar parameter that indicates a specification of a radar that is a synthetic aperture radar or an inverse synthetic aperture radar. The model setting means sets a three-dimensional model that indicates a shape of a target object to identify. The image calculation means calculates a simulation image based on the three-dimensional model and the radar parameter. The data output means outputs training data in that the simulation image and a type of the target object are associated to each other. In addition, the data output means outputs difference data that indicate a difference between a radar image and the simulation image. The model setting means changes the three-dimensional model based on model correction data inputted based on the difference data.

A radar image processing device includes: an estimation unit 1 for setting, as a target pixel, each pixel of a two-dimensional map image, and estimating to which type each target pixel belongs among a pixel caused by the main lobe, a pixel due to the sidelobe, and any other pixel; a pixel value replacement unit 2 for replacing the pixel value of the pixel caused by the main lobe and the pixel value of the pixel due to the sidelobe with pixel values generated in pixel value interpolation processing based on the type of each pixel estimated by the estimation unit 1 to generate a first corrected image; a speckle noise suppression unit 3 for applying speckle noise suppression processing to the first corrected image to generate a second corrected image; and an output image generation unit 4 for generating an output image, in which speckle noise and sidelobes are suppressed, by using the two-dimensional map image, the second corrected image, and the type of each pixel.

Described is a system for transferring learned knowledge from an electro-optical (EO) domain to a synthetic-aperture-radar (SAR) domain. The system uses a measured similarity between the EO domain and the SAR domain to train a model for classifying SAR images using knowledge previously learned from the electro-optical (EO) domain. Using the trained model, a SAR image is processed to determine regions of interest in the SAR image. A region of interest is classified to determine whether the region of interest corresponds to an object of interest, and classified regions of interest that contain the object of interest are output. The object of interest is displayed on a visualization map, and the visualization map is automatically updated to reflect a change in position of the object of interest.

The image processing device 10 includes intensity calculation means 11 for calculating intensity of the sample pixel, neighboring pixel selection means 12 for selecting neighboring pixels that have a similar statistical property of intensity to the sample pixel, based on the intensity of the sample pixel, phase specifying means 13 for specifying phases of the neighboring pixels, and pixel classification means 14 for classifying the neighboring pixels based on correlation of the phases of the neighboring pixels.

A method for operating a synthetic aperture radar, SAR, mode, in an SAR instrument, wherein the method comprises the steps of: acquiring at least one subswath positioned in an across track direction of a movement of the SAR instrument, wherein the at least one subswath is acquired during at least one acquisition burst duration and/or at a predetermined radio frequency bandwidth; adjusting the at least one acquisition burst duration and/or the predetermined radio frequency bandwidth and/or a number of parallel simultaneous subswaths and/or an inserted burst duration for a further subswath based upon a predetermined parameter; constructing an SAR image based on the acquired at least one subswath.

A frequency-modulated continuous wave (FMCW) millimeter-wave (MMW) radar system. Preferred embodiments operate within a frequency range between about 77 and 81 GHz (wavelengths between about 3.846 mm and 3.304 mm). The MMW frequency in these embodiments is increased or decreased (“chirped ”) in a very linear fashion over some or all of this operating frequency range. Over the chirp period, the time derivative of the transmit frequency, df/dt, is held constant. In the time τ it takes for the radar's transmit signal, moving at the speed of light c, to travel from the antenna to a target at a range R and return back to the antenna (τ=2R/c), the transmitter's output frequency will have moved by an amount (df/dt)*τ. Thus, the more distant the reflecting target, the greater the two-way signal time of flight and consequently the greater the frequency change. By mixing the delayed returning signal with the current transmitter output signal, this difference frequency is measured directly, determining uniquely the distance from the radar to the reflecting target.

The invention concerns a monitoring method that comprises coupling in an integral manner at least one electromagnetic mirror of passive type with a given target to be monitored and monitoring the given target; wherein monitoring the given target includes: acquiring, via one or more synthetic aperture radar(s) installed on board one or more satellites and/or one or more aerial platforms, SAR images of a given area of the earth's surface where the given target is located; and determining, via a processing unit, a movement of the electromagnetic mirror on the basis of the acquired SAR images.

The present disclosure relates to a method for enhancing sematic features of SAR image oriented small set of samples, comprising: acquiring a sample set of an SAR target image, and performing transfer learning and training on the sample set to obtain a initialized deep neural network of an SAR target image, the sample set comprising an SAR target image and an SAR target virtual image; performing network optimization on the deep neural network by an activation function, and extracting features of the SAR target image by the optimized deep neural network to obtain a feature map; and mapping, by an auto-encoder, the feature map between a feature space and a semantic space to obtain a deep visual feature with an enhanced semantic feature.

Disclosed are a method and an apparatus for end-to-end SAR image recognition, and a storage medium. According to the disclosure, a generative adversarial network is used to enhance data and improve data richness of a SAR image, which is beneficial to subsequent network training; a semantic feature enhancement technology is also introduced to enhance semantic information of a SAR deep feature by a coding-decoding structure, which improves performances of SAR target recognition; and meanwhile, an end-to-end SAR image target recognition model with high integrity for big scenes like the Bay Area is constructed, which is helpful to improve a synthetic aperture radar target recognition model for big scenes like the Bay Area from local optimum to global optimum, increases the stability and generalization ability of the model, reduces the network complexity, and improves the target recognition accuracy.