For real-time target classification, a study was conducted to improve the AI-based target classification performance using RCS measurements that are vulnerable to noise, but can be obtained quickly. To compensate for the shortcomings of the RCS, a 1D CNN–GRU network with strengths in feature extraction and time-series processing was considered. The 1D CNN–GRU was experimentally changed and designed to fit the RCS characteristics. The performance of the proposed 1D CNN–GRU was compared and analyzed using the 1D CNN and 1D CNN–LSTM. The designed 1D CNN–GRU had the best classification performance with a high accuracy of 99.50% in complex situations, such as with different missile shapes with the same trajectory and with the same missile shapes that had the same trajectory. In addition, to confirm the general target classification performance for the RCS, a new class was verified. The 1D CNN–GRU had the highest classification performance at 99.40%. Finally, as a result of comparing three networks by adding noise to compensate for the shortcomings of the RCS, the 1D CNN–GRU, which was optimized for both the data set used in this paper and the newly constructed data set, was the most robust to noise.

In this paper, the dehazing algorithm is proposed using a one-channel grayscale depth image generated from a LiDAR point cloud 2D projection image. In depth image-based dehazing, the estimation of the scattering coefficient is the most important. Since scattering coefficients are used to estimate the transmission image for dehazing, the optimal coefficients for effective dehazing must be obtained depending on the level of haze generation. Thus, we estimated the optimal scattering coefficient for 100 synthetic haze images and represented the distribution between the optimal scattering coefficient and dark channels. Moreover, through linear regression of the aforementioned distribution, the equation between scattering coefficients and dark channels was estimated, enabling the estimation of appropriate scattering coefficient. Transmission image for dehazing is defined with a scattering coefficient and a grayscale depth image, obtained from LiDAR 2D projection. Finally, dehazing is performed based on the atmospheric scattering model through the defined atmospheric light and transmission image. The proposed method was quantitatively and qualitatively analyzed through simulation and image quality parameters. Qualitative analysis was conducted through YOLO v3 and quantitative analysis was conducted through MSE, PSNR, SSIM, etc. In quantitative analysis, SSIM showed an average performance improvement of 24%.

The fault tolerance estimation method is proposed to maintain reliable correspondences between sensor data and estimation performance regardless of the number of valid measurements. The proposed method is based on the 1-point random sample consensus (RANSAC) unscented Kalman filter (UKF), and the inverse covariance intersection (ICI)-based data fusion method is added to the update process in the proposed algorithm. To verify the performance of the proposed algorithm, two analyses are performed with respect to the degree of measurement error reduction and accuracy of generated information. In addition, experiments are conducted using the dead reckoning (DR)/global positioning system (GPS) navigation system with a barometric altimeter to confirm the performance of fault tolerance in the altitude. It is confirmed that the proposed algorithm maintains estimation performance when there are not enough valid measurements.

We propose a sequential Monte Carlo-based cardinalized probability hypothesis density (SMC-CPHD) filter with adaptive survival probability for multiple frequency tracking to enhance the tracking performance. The survival probability of the particles in the filter is adjusted using the pre-designed exponential function related to the distribution of the estimated particle points. In order to ensure whether the proposed survival probability affects the stability of the filter, the error bounds in the prediction process are analyzed. Moreover, an inverse covariance intersection-based compensation method is added to enhance cardinality tracking performance by integrating two types of cardinality information from the CPHD filter and data clustering process. To evaluate the proposed method’s performance, MATLAB-based simulations are performed. As a result, the tracking performance of the multiple frequencies has been confirmed, and the accuracy of cardinality estimates are improved compared to the existing filters.