RESUMEN
Aiming to address soft sensing model degradation under changing working conditions, and to accommodate dynamic, nonlinear, and multimodal data characteristics, this paper proposes a nonlinear dynamic transfer soft sensor algorithm. The approach leverages time-delay data augmentation to capture dynamics and projects the augmented data into a latent space for constructing a nonlinear regression model. Two regular terms, distribution alignment regularity and first-order difference regularity, are introduced during data projection to address data distribution disparities. Laplace regularity is incorporated into the nonlinear regression model to ensure geometric structure preservation. The final optimization objective is formulated within the framework of partial least squares, and hyperparameters are determined using Bayesian optimization. The effectiveness of the proposed algorithm is demonstrated through experiments on three public datasets.
RESUMEN
Back-end optimization plays a key role in eliminating the accumulated error in Visual Simultaneous Localization And Mapping (VSLAM). Existing back-end optimization methods are usually premised on the Gaussian noise assumption which does not always hold true due to the non-convex nature of the image and the fact that non-Gaussian noises are often encountered in real scenes. In view of this, we propose a back-end optimization method based on Multi-Convex combined Maximum Correntropy Criterion (MCMCC). A MCMCC-based cost function is first tailored for nonlinear back-end optimization in the context of VSLAM and the optimization problem is solved through Levenberg-Marquardt algorithm iteratively. Then, the proposed method is applied to ORB-SLAM3 to test its performance on public indoor and outdoor datasets. The real time performance is also validated using a RaceBot platform in real indoor and outdoor environments. In addition, the reprojection error is statistically analyzed to demonstrate the non-Gaussian characteristics in the back-end optimization process. Finally, the suggestion parameters are also provided through experiments for further study.
RESUMEN
Existing key-frame extraction methods are basically video summary oriented; yet the index task of key-frames is ignored. This paper presents a novel key-frame extraction approach which can be available for both video summary and video index. First a dynamic distance separability algorithm is advanced to divide a shot into subshots based on semantic structure, and then appropriate key-frames are extracted in each subshot by SVD decomposition. Finally, three evaluation indicators are proposed to evaluate the performance of the new approach. Experimental results show that the proposed approach achieves good semantic structure for semantics-based video index and meanwhile produces video summary consistent with human perception.
