Litao Zhu

Lane-level road inventory aims to jointly extract direction-consistent lane areas and visible lane counts from street-view images. However, existing line-based methods do not directly recover complete lane regions, whereas area-based methods may include irrelevant pavement. To address these challenges, we propose adaptive structural line–instance fusion (ASLIF), a prediction-level framework that combines structural line predictions with instance-level area predictions. ASLIF converts O2SFormer line predictions into regional masks and fuses them with the continuous regional response produced by Mask R-CNN. An image-level fusion coefficient adjusts the relative contributions of the two branches according to scene complexity, estimated lane density, and the difference in branch confidence. Experiments on a test set from Nanjing, China, show that ASLIF achieves a precision of 0.92, a micro-F1 of 0.90, a mean-F1 of 0.90, and a mean-IoU of 0.82, with the highest precision among the evaluated baseline semantic-segmentation methods. These results indicate that ASLIF provides a precision-oriented operating point that suppresses false-positive lane regions while retaining substantial regional coverage.

Precise object detection is fundamental to robust indoor navigation and localization. However, the practical deployment of deep learning-based detectors on mobile platforms is frequently impeded by their extensive parameter counts, substantial computational overhead, and prolonged inference latency, rendering them impractical for real-time and GPU-independent applications. To overcome these limitations, this paper presents Nav-YOLO, a highly optimized and lightweight architecture derived from YOLOv8n, specifically engineered for navigational tasks. The model’s efficiency stems from several key improvements: a ShuffleNetv2-based backbone significantly reduces model parameters; a Slim-Neck structure incorporating GSConv and GSbottleneck modules streamlines the feature fusion process; the VoV-GSCSP hierarchical network aggregates features with minimal computational cost; and a compact detection head is designed using Hybrid Convolutional Transformer Architecture Search (HyCTAS). Furthermore, the adoption of Inner-IoU as the bounding box regression loss accelerates the convergence of the training process. The model’s efficacy is demonstrated through a purpose-built Android application. Experimental evaluations on the VOC2007 and VOC2012 datasets reveal that Nav-YOLO substantially outperforms the baseline YOLOv8n, achieving mAP50 improvements of 10.3% and 5.0%, respectively, while maintaining a comparable parameter footprint. Consequently, Nav-YOLO demonstrates a superior balance of accuracy, model compactness, and inference speed, presenting a compelling alternative to existing object detection algorithms for mobile systems.

Landmark‐based pedestrian navigation can assist pedestrians in navigating successfully. Previous studies have investigated the factors affecting the cognitive efficiency of landmark visualization in terms of both the visual salience of landmarks and the personal characteristics of users. However, empirical studies and applications that consider the influence of spatial familiarity on landmark representation are limited. In this article, we propose a personalized landmark adaptive visualization method for pedestrian navigation maps considering user familiarity. We first explore the influence of spatial familiarity on landmark salience and symbols using cognitive experiments. The results showed that unfamiliar people preferred strong visual salience landmarks and image‐based symbols, while familiar people preferred strong semantic salience landmarks and text‐based symbols. Based on these results, a mathematical model of landmark salience for selecting personalized landmarks is proposed, and association rules between landmark salience and symbols are mined. Finally, the framework of a landmark visualization method is proposed based on the rules. To verify the effectiveness of the proposed method, a prototype system is developed, and a comparative experiment is conducted with a Baidu map. Experimental results showed that the proposed method has direct practical implications for the development of pedestrian navigation systems, depending on different target users.