SAR three-dimensional rotating target rotating speed estimation method based on CV-ConvLSTM
A target speed and three-dimensional rotation technology, applied in the field of image processing, can solve the problems of eliminating blur and low accuracy, achieve the effect of improving the estimation accuracy and meeting the needs of complex SAR speed estimation
Pending Publication Date: 2022-03-01
HARBIN INST OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is: aiming at the problem of low accuracy in eliminating blur by using the method of time-frequency analysis and imaging processing in the prior art, a method for estimating the rotational speed of a SAR three-dimensional rotating target based on CV-ConvLSTM is proposed
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0090] Specific implementation mode one: refer to Figure 11 Specifically illustrate this embodiment, the method for estimating the rotational speed of a SAR three-dimensional rotating target based on CV-ConvLSTM described in this embodiment includes the following steps:
[0091] Step 1: Demodulate and pulse compress the SAR echo with a relatively long accumulation time, then use the sub-aperture imaging method to generate a complex domain SAR image sequence, and obtain the rotational angular velocity corresponding to the SAR image sequence, the rotational angular velocity includes the yaw angular velocity , Pitch angular velocity and roll angular velocity;
[0092] Step 2: Input the SAR image sequence into the TSF network model to obtain the rotational angular velocity;
[0093] Step 3: Use the obtained rotational angular velocity and the rotational angular velocity corresponding to the SAR image sequence to obtain the loss function, and update the weight according to the CV...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a CV-ConvLSTM-based SAR (Synthetic Aperture Radar) three-dimensional rotating target rotating speed estimation method, relates to the technical field of image processing, and provides a CV-ConvLSTM for solving the problem of low accuracy of eliminating blurring by using a time-frequency analysis imaging processing method in the prior art. According to the CV-ConvLSTM, the whole network comprising a convolutional layer, an activation function, an input gate, a forgetting gate and an output gate is expanded to a complex domain, and on the basis, a complex domain time-dependent back propagation algorithm CV-BPTT for CV-ConvLSTM training is deduced. The TSF-Net architecture is designed based on the CV-ConvLSTM, SAR three-dimensional rotating target rotating speed estimation is carried out, an SAR rotating speed estimation task is converted into an image regression problem, target rotating speed estimation is achieved, and estimation precision is obviously improved. According to the method, the SAR imaging principle and the complex field deep learning technology are utilized, the requirement for complex SAR rotating speed estimation is better met, and the stability of view angle change, affine transformation and noise is kept to a certain degree.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method for estimating the rotational speed of a SAR three-dimensional rotating target based on CV-ConvLSTM. Background technique [0002] Synthetic Aperture Radar (SAR) has the ability to perform two-dimensional fine imaging of targets all day and all day, which makes it widely used in the fields of marine remote sensing target detection and recognition. When a ship sails on the actual sea surface, due to the influence of wind, air pressure and gravity, it will fluctuate with the waves. Affected by the thrust of the waves, the ship will produce three-dimensional rotation: pitch, roll and yaw. The three-dimensional rotation angular velocity is respectively yaw angular velocity, pitch angular velocity and roll angular velocity. The three-dimensional rotation makes the Doppler frequency shift of the ship target echo time-varying, so the Doppler spectrum of the echo cann...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01S13/90
CPCG01S13/9029
Inventor 张云化青龙冀振元姜义成李宏博徐丹
Owner HARBIN INST OF TECH