Accurate metric depth completion across wide depth ranges is critical for autonomous systems. However, existing methods often struggle to efficiently capture depth features at both close and long ranges, primarily due to the inadequate modeling of fine-grained depth cues specific to different depth ranges. To address these limitations, we propose AirDC, an adaptive iterative depth refinement framework for full-range metric depth completion. The core contributions of our model lie in the design of two key modules. Specifically, we first construct an adaptive fine-grained stereo-LiDAR feature fusion module to fundamentally strengthen the model's capacity to preserve original full-range depth information. Built upon metric-aligned depth volumes (i.e., a 3D representation composed of cubic voxels uniformly partitioned in real-world metric space), this module employs an adaptive sub-voxel depth attention mechanism to enhance sensitivity to subtle depth variations across the full range, thereby both avoiding long-range accuracy degradation introduced by conventional disparity conversion and alleviating the coarse near-range granularity inherent in metric depth representations. Second, we introduce an iterative hypothesis-guided depth refinement module to improve prediction accuracy while maintaining memory efficiency. By integrating multi-scale multi-modal guidance information from depth hypotheses, this module enables explicit and progressive refinement of the initial depth estimation with a small parameter overhead. Experiments on multiple mainstream real-world and synthetic benchmarks demonstrate that AirDC achieves state-of-the-art performance, providing an effective solution for full-range metric depth completion. The code and data are available at https://github.com/yunqidu/AirDC.

Free of tuning regularization parameters, sparse unmixing based on multi-objective methods have become increasingly popular for the hyperspectral image in recent years. Moreover, inherent signatures of a hyperspectral image have been exploited in various single objective based methods and proved relevant for improving unmixing performance. However, their utilizations in multi-objective optimization are still scarce. With the overarching goal of exploiting the spatial signature in an explicit way for hyperspectral unmixing, this work proposes a Multi-objective Method Leveraging Spatial Spectral Relationship for Hyperspectral Unmixing (GMoSU). Firstly, a multi-objective sparse unmixing model based on spatial signatures encoded by the graph laplacian is put forward. Then, to solve this model efficiently, an improved Tchebycheff decomposition approach and a novel local recombination strategy are rationally proposed, both of them and an operation of encoding the solution as a binary vector are plugged into the framework of MOEA/D. Theoretically, the improved Tchebycheff formula formed by introducing a mixed spectral similarity metric enables the Pareto-optimal front to converge to a single solution exactly. Encoding the solution as a binary vector could help effectively addressing the endmember selection problem. The novel local recombination strategy that an individual is updated through recombining with another individual selected randomly in its neighborhood could balance the diversity and convergence of population further. Finally, comprehensive comparison experiments are conducted on synthetic and real data sets, which verify the theoretical advantages and effectiveness of the proposed GMoSU even under heavy noise.

Blind image quality assessment (BIQA), which aims to estimate the perceptual quality of images without any reference information, is a very important yet challenging task. Although human visual system is sensitive to degradations on both spatial contrast and spatial distribution, most of the existing structural degradation based BIQA models consider only one of them. This study introduces a novel BIQA model by taking into account degradations on both contrast and spatial distribution. First, the authors construct a multi‐threshold local tetra pattern (MTLTrP) instead of local binary pattern to measure the changes on spatial distribution. Second, Weber–Laplacian of Gaussian (WLOG) operator, which responds to intensity contrast in a small spatial neighbourhood, is proposed to extract local contrast features. Finally, the joint statistics of MTLTrP and WLOG are utilised for BIQA model learning. Experimental results on three large benchmark databases demonstrate that the proposed model outperforms state‐of‐the‐art BIQA models, as well as with several well‐known full reference quality assessment methods.

Plant recognition recently becomes more and more attractive in computer vision and pattern recognition. Although some researchers have proposed several methods, their accuracy is not satisfactory. Therefore, a novel method of plant recognition based on leaf image is proposed in the paper. Both shape and texture features are employed in the proposed method Texture feature is extracted by intersecting cortical model, and shape feature is obtained by the representation of center distance sequence. Support vector machine is employed for the classifier. The leaf image is preprocessed to get better quality for extracting features, and then entropy sequence and center distance sequence are obtained by intersecting cortical model and center distance transform, respectively. Redundant data of entropy sequence vector and center distance are reduced by principal component analysis. Finally, feature vector is imported into the classifier for classification. In order to evaluate the performance, several existing methods are used to compare with the proposed method and three leaf image datasets are taken as test samples. The experimental result shows the proposed method gets the better accuracy of recognition than other methods.

Data assimilation (DA), an effective approach to merge dynamic model and observations to improve states estimation accuracy, has been a hot topic in the earth science and lots of efforts have been devoted to the DA algorithms. In this paper, an improved residual resampling particle filtering (improved RR-PF) is proposed. Compared with the generic residual resampling particle filtering (generic RR-PF), the improved RR-PF not only solves the degradation of particles, but also maintains the diversity of particles. Besides, sensitivity analysis is carried out to analyze the impact of some parameters to assimilation and to determine the optimal parameters. These parameters are of significant importance to DA but cannot be determined easily. Finally, soil moisture from Soil Moisture Experiment 2003 and VIC model simulations were assimilated with the improved RR-PF with parameters determined by the sensitivity analysis. The result shows that the accuracy of soil moisture greatly improves after DA. Compared with generic RR-PF, the performance of improved RR-PF is superior in accuracy and diversity of particles.

Based on the studies of existing local-connected neural network models, in this brief, we present a new spiking cortical neural networks model and find that time matrix of the model can be recognized as a human subjective sense of stimulus intensity. The series of output pulse images of a proposed model represents the segment, edge, and texture features of the original image, and can be calculated based on several efficient measures and forms a sequence as the feature of the original image. We characterize texture images by the sequence for an invariant texture retrieval. The experimental results show that the retrieval scheme is effective in extracting the rotation and scale invariant features. The new model can also obtain good results when it is used in other image processing applications.