Hyperspectral Image Classification via Deep Structure Dictionary Learning

Predicting bentonite swelling pressure: optimized XGBoost versus neural networks

The swelling pressure of bentonite and bentonite mixtures is critical in designing barrier systems for deep geological radioactive waste repositories. Accurately predicting the maximum swelling pressure is essential for ensuring these systems' long-term stability and sealing characteristics. In this study, we developed a constrained machine learning model based on the extreme gradient boosting (XGBoost) algorithm tuned with grey wolf optimization (GWO) to determine the maximum swelling pressure of bentonite and bentonite mixtures. A dataset containing 305 experimental data points was compiled, including relevant soil properties such as montmorillonite content, liquid limit, plastic limit, plasticity index, initial water content, and soil dry density. The GWO-XGBoost model, incorporating a penalty term in the loss function, achieved an R2 value of 0.9832 and an RMSE of 0.5248 MPa in the testing phase, outperforming feed-forward and cascade-forward neural network models. The feature importance analysis revealed that dry density and montmorillonite content were the most influential factors in predicting maximum swelling pressure. While the developed model demonstrates high accuracy and reliability, it may have limitations in capturing extreme values due to the complex nature of bentonite swelling behavior. The proposed approach provides a valuable tool for predicting the maximum swelling pressure of bentonite-based materials under various conditions, supporting the design and analysis of effective barrier systems in geotechnical engineering applications.

Learning channel-selective and aberrance repressed correlation filter with memory model for unmanned aerial vehicle object tracking

To ensure that computers can accomplish specific tasks intelligently and autonomously, it is common to introduce more knowledge into artificial intelligence (AI) technology as prior information, by imitating the structure and mindset of the human brain. Currently, unmanned aerial vehicle (UAV) tracking plays an important role in military and civilian fields. However, robust and accurate UAV tracking remains a demanding task, due to limited computing capability, unanticipated object appearance variations, and a volatile environment. In this paper, inspired by the memory mechanism and cognitive process in the human brain, and considering the computing resources of the platform, a novel tracking method based on Discriminative Correlation Filter (DCF) based trackers and memory model is proposed, by introducing dynamic feature-channel weight and aberrance repressed regularization into the loss function, and by adding an additional historical model retrieval module. Specifically, the feature-channel weight integrated into the spatial regularization (SR) enables the filter to select features. The aberrance repressed regularization provides potential interference information to the tracker and is advantageous in suppressing the aberrances caused by both background clutter and appearance changes of the target. By optimizing the aforementioned two jointly, the proposed tracker could restrain the potential distractors, and train a robust filter simultaneously by focusing on more reliable features. Furthermore, the overall loss function could be optimized with the Alternative Direction Method of Multipliers (ADMM) method, thereby improving the calculation efficiency of the algorithm. Meanwhile, with the historical model retrieval module, the tracker is encouraged to adopt some historical models of past video frames to update the tracker, and it is also incentivized to make full use of the historical information to construct a more reliable target appearance representation. By evaluating the method on two challenging UAV benchmarks, the results prove that this tracker shows superior performance compared with most other advanced tracking algorithms.

Robust tactile object recognition in open-set scenarios using Gaussian prototype learning

Tactile object recognition is crucial for effective grasping and manipulation. Recently, it has started to attract increasing attention in robotic applications. While there are many works on tactile object recognition and they also achieved promising performances in some applications, most of them are usually limited to closed world scenarios, where the object instances to be recognition in deployment are known and the same as that of during training. Since robots usually operate in realistic open-set scenarios, they inevitably encounter unknown objects. If automation systems falsely recognize unknown objects as one of the known classes based on the pre-trained model, it can lead to potentially catastrophic consequences. It motivates us to break the closed world assumption and to study tactile object recognition in realistic open-set conditions. Although several open-set recognition methods have been proposed, they focused on visual tasks and may not be suitable for tactile recognition. It is mainly due to that these methods do not take into account the special characteristic of tactile data in their models. To this end, we develop a novel Gaussian Prototype Learning method for robust tactile object recognition. Particularly, the proposed method converts feature distributions to probabilistic representations, and exploit uncertainty for tactile recognition in open-set scenarios. Experiments on the two tactile recognition benchmarks demonstrate the effectiveness of the proposed method on open-set tasks.

An improved anchor-free SAR ship detection algorithm based on brain-inspired attention mechanism

As a computing platform that can deal with problems independently and adapt to different environments, the brain-inspired function is similar to the human brain, which can effectively make use of visual targets and their surrounding background information to make more efficient and accurate decision results. Currently synthetic aperture radar (SAR) ship target detection has an important role in military and civilian fields, but there are still great challenges in SAR ship target detection due to the problems of large span of ship scales and obvious feature differences. Therefore, this paper proposes an improved anchor-free SAR ship detection algorithm based on brain-inspired attention mechanism, which efficiently focuses on target information ignoring the interference of complex background. First of all, most target detection algorithms are based on the anchor method, which requires a large number of anchors to be defined in advance and has poor generalization capability and performance to be improved in multi-scale ship detection, so this paper adopts an anchor-free detection network to directly enumerate potential target locations to enhance algorithm robustness and improve detection performance. Secondly, in order to improve the SAR ship target feature extraction capability, a dense connection module is proposed for the deep part of the network to promote more adequate deep feature fusion. A visual attention module is proposed for the shallow part of the network to focus on the salient features of the ship target in the local area for the input SAR images and suppress the interference of the surrounding background with similar scattering characteristics. In addition, because the SAR image coherent speckle noise is similar to the edge of the ship target, this paper proposes a novel width height prediction constraint to suppress the noise scattering power effect and improve the SAR ship localization accuracy. Moreover, to prove the effectiveness of this algorithm, experiments are conducted on the SAR ship detection dataset (SSDD) and high resolution SAR images dataset (HRSID). The experimental results show that the proposed algorithm achieves the best detection performance with metrics AP of 68.2% and 62.2% on SSDD and HRSID, respectively.

Column-Spatial Correction Network for Remote Sensing Image Destriping

The stripe noise in the multispectral remote sensing images, possibly resulting from the instrument instability, slit contamination, and light interference, significantly degrades the imaging quality and impairs high-level visual tasks. The local consistency of homogeneous region in striped images is damaged because of the different gains and offsets of adjacent sensors regarding the same ground object, which leads to the structural characteristics of stripe noise. This can be characterized by the increased differences between columns in the remote sensing image. Therefore, the destriping can be viewed as a process of improving the local consistency of homogeneous region and the global uniformity of whole image. In recent years, convolutional neural network (CNN)-based models have been introduced to destriping tasks, and have achieved advanced results, relying on their powerful representation ability. Therefore, to effectively leverage both CNNs and the structural characteristics of stripe noise, we propose a multi-scaled column-spatial correction network (CSCNet) for remote sensing image destriping, in which the local structural characteristic of stripe noise and the global contextual information of the image are both explored at multiple feature scales. More specifically, the column-based correction module (CCM) and spatial-based correction module (SCM) were designed to improve the local consistency and global uniformity from the perspectives of column correction and full image correction, respectively. Moreover, a feature fusion module based on the channel attention mechanism was created to obtain discriminative features derived from different modules and scales. We compared the proposed model against both traditional and deep learning methods on simulated and real remote sensing images. The promising results indicate that CSCNet effectively removes image stripes and outperforms state-of-the-art methods in terms of qualitative and quantitative assessments.