Search

In this paper, the ship target detection and recognition system of remote sensing imaging based on machine learning is designed according to the sparsity of interest targets in optical remote sensing image, and proposes a method of target detection and recognition based on morphological matching and machine learning. The slices of suspected targets are extracted quickly by visual enhancement technology that the amount of data processed is greatly reduced. The target information of interest is extracted in depth and the false alarm rate of detection is greatly reduced by using machine learning method to classify objects. In the system function and performance verification test, the real-time and accuracy index through 227 targets of 32 scenes GF-2 satellite images are tested what can detect and recognize about 20 objects per second. The recall rate of the system is more than 92%, and the efficiency of target detection method based on traditional morphological matching is less than 60% while the target recognition method base on machine learning improves the precision rate to over 97%.

Based on dual frequencies-dual apertures spaceborne SAR (synthetic aperture radar), a new SAR operation mode with four receiving channels is presented in this paper. High resolution imaging and moving target indication (MTI) are studied with this new mode. The coherent accumulation (CA) method, which combines dual channels data, is used to enhance the range resolution. With the data from all channels, the two aperture interferometric processing is executed to implement clutter cancellation. A pair of the clutter suppressed data are employed to implement double carrier frequency conjugated processing (DCFCP), then MTI processing is completed, followed by moving target imaging. The simulation results show the validity of the signal processing method and the feasibility of this new SAR mode.

According to the characteristic that the bandwidth of spaceborne SAR is generally quite wide, a new method called "Sub-band Double Carrier Frequency Conjugated Processing" is presented in this paper. The approach can decrease the equivalent central frequency of the synthetic signal and remove the Doppler ambiguity. Consequently, Keystone transform can be used to correct the linear range migration of the fast moving targets with low input SNR. After the target range curvature is corrected, time-frequency analysis can be used to implement low resolution imaging and targets detecting. The radial velocities of the targets can be obtained from targets detection, and high resolution imaging process can be completed to each moving target. The simulation results show the effectiveness of the new method.