The RGB-D (Red, Green, Blue plus Depth) camera is a widely used onboard sensor for Simultaneous Localization and Mapping (SLAM), as it captures RGB images and depth information simultaneously. This capability has made RGB-D SLAM a topic of broad research interest. We present a comprehensive introduction to the framework of RGB-D SLAM and illustrate representative approaches in each component. Furthermore, we examine the conflicts among diverse performance metrics and discuss performance trade-offs in cutting-edge RGB-D SLAM from a requirement perspective, as achieving a SLAM system with perfect performance is challenging in the present landscape. This manuscript merges theory and practice, serving as a reference for the selection of RGB-D SLAM methods under various practical applications and offering a structured perspective for future development of RGB-D SLAM.

Finger vein recognition has emerged as a highly robust and intrinsically stable biometric technology, demonstrating great potential in identity authentication and intelligent security applications. However, conventional methods still suffer from constraints in feature representation and computational efficiency, particularly under challenging conditions such as illumination variation, pose deviation, and noise interference. To address these challenges, this study presents an efficient finger vein recognition approach based on a lightweight convolutional neural network (LCNN) architecture. The proposed framework integrates a multi-stage image preprocessing pipeline for automatic vein region detection, advanced denoising, and refined texture enhancement, which is subsequently followed by compact feature modeling within a lightweight deep network. Extensive experiments on the public Shandong University Machine Learning and Applications-Homologous Multi-Modal Traits (SDUMLA-HMT) dataset and a self-acquired Laboratory Finger-Vein (Lab-Vein) dataset validate the superiority of the proposed method, achieving recognition accuracies of 97.1% and 98.3%, respectively, surpassing existing benchmark models. Moreover, the model demonstrates notable reductions in parameter complexity and computational cost, achieving an average inference time of only 12.6 ms, which confirms its strong real-time capability and suitability for embedded deployment. Overall, the proposed approach attains a desirable trade-off between accuracy and efficiency, offering meaningful implications for the advancement of lightweight biometric recognition systems.