Planes are essential features to describe the shapes of buildings. The segmentation of a plane is significant when reconstructing a building in three dimensions. However, there is a concern about the accuracy in segmenting plane from point cloud data. The objective of this paper was to develop an effective segmentation algorithm for building planes that combines the region growing algorithm with the distance algorithm based on boundary points. The method was tested on point cloud data from a cottage and pantry as scanned using a Faro Focus 3D laser range scanner and Matterport Camera, respectively. A coarse extraction of the building plane was obtained from the region growing algorithm. The coplanar points where two planes intersect were obtained from the distance algorithm. The building plane’s optimal segmentation was then obtained by combining the coarse extraction plane points and the corresponding coplanar points. The results show that the proposed method successfully segmented the plane points of the cottage and pantry. The optimal distance thresholds using the proposed method from the uncoarse extraction plane points to each plane boundary point of cottage and pantry were 0.025 m and 0.030 m, respectively. The highest correct rate and the highest error rate of the cottage’s (pantry’s) plane segmentations using the proposed method under the optimal distance threshold were 99.93% and 2.30% (98.55% and 2.44%), respectively. The F1 score value of the cottage’s and pantry’s plane segmentations using the proposed method under the optimal distance threshold reached 97.56% and 95.75%, respectively. This method can segment different objects on the same plane, while the random sample consensus (RANSAC) algorithm causes the plane to become over-segmented. The proposed method can also extract the coplanar points at the intersection of two planes, which cannot be separated using the region growing algorithm. Although the RANSAC-RG method combining the RANSAC algorithm and the region growing algorithm can optimize the segmentation results of the RANSAC (region growing) algorithm and has little difference in segmentation effect (especially for cottage data) with the proposed method, the method still loses coplanar points at some intersection of the two planes.
For geoscience text, rich domain corpora have become the basis of improving the model performance in word segmentation. However, the lack of domain-specific corpus with annotation labelled has become a major obstacle to professional information mining in geoscience fields. In this paper, we propose a corpus augmentation method based on Levenshtein distance. According to the technique, a geoscience dictionary of 20,137 words was collected and constructed by crawling the keywords from published papers in China National Knowledge Infrastructure (CNKI). The dictionary was further used as the main source of synonyms to enrich the geoscience corpus according to the Levenshtein distance between words. Finally, a Chinese word segmentation model combining the BERT, Bi-gated recurrent neural network (Bi-GRU), and conditional random fields (CRF) was implemented. Geoscience corpus composed of complex long specific vocabularies has been selected to test the proposed word segmentation framework. CNN-LSTM, Bi-LSTM-CRF, and Bi-GRU-CRF models were all selected to evaluate the effects of Levenshtein data augmentation technique. Experiments results prove that the proposed methods achieve a significant performance improvement of more than 10%. It has great potential for natural languages processing tasks like named entity recognition and relation extraction.
Vehicle trajectory prediction is a pivotal technology in intelligent transportation systems. Existing methods encounter challenges in effectively modeling lane topology and dynamic interaction relationships in complex traffic scenarios, limiting prediction accuracy and reliability. This paper presents Lane Interaction Transformer (LITransformer), a lane-informed trajectory prediction framework that builds on spatio–temporal graph attention networks and Transformer-based global aggregation. Rather than introducing entirely new network primitives, LITransformer focuses on two design aspects: (i) a lane topology encoder that fuses geometric and semantic lane features via direction-sensitive, multi-scale dilated graph convolutions, converting vectorized lane data into rich topology-aware representations; and (ii) an Interaction-Aware Graph Attention mechanism (IAGAT) that explicitly models four types of interactions between vehicles and lane infrastructure (V2V, V2N, N2V, N2N), with gating-based fusion of structured road constraints and dynamic spatio–temporal features. The overall architecture employs a Transformer module to aggregate global scene context and a multi-modal decoding head to generate diverse trajectory hypotheses with confidence estimation. Extensive experiments on the Argoverse dataset show that LITransformer achieves a minADE of 0.76 and a minFDE of 1.20, and significantly outperforms representative baselines such as LaneGCN and HiVT. These results demonstrate that explicitly incorporating lane topology and interaction-aware spatio-temporal modeling can significantly improve the accuracy and reliability of vehicle trajectory prediction in complex real-world traffic scenarios.
Efficient and convenient rock image classification methods are important for geological research. They help in identifying and categorizing rocks based on their physical and chemical properties, which can provide insights into their geological history, origin, and potential uses in various applications. The classification and identification of rocks often rely on experienced and knowledgeable professionals and are less efficient. Fine-grained rock image classification is a challenging task because of the inherent subtle differences between highly confusing categories, which require a large number of data samples and computational resources, resulting in low recognition accuracy, and are difficult to apply in mobile scenarios, requiring the design of a high-performance image processing classification architecture. In this paper we design a knowledge distillation and high-accuracy feature localization comparison network (FPCN)-based learning architecture for generating small high-performance rock image classification models. Specifically, for a pair of images, we interact with the feature vectors generated from the localized feature maps to capture common and unique features, let the network focus on more complementary information according to the different scales of the objects, and then the important features of the images learned in this way are made available for the micro-model to learn the critical information for discrimination via model distillation. The proposed method improves the accuracy of the micro-model by 3%.
Rock image classification represents a challenging fine-grained image classification task characterized by subtle differences among closely related rock categories. Current contrastive learning methods prevalently utilized in fine-grained image classification restrict the model’s capacity to discern critical features contrastively from image pairs, and are typically too large for deployment on mobile devices used for in situ rock identification. In this work, we introduce an innovative and compact model generation framework anchored by the design of a Feature Positioning Comparison Network (FPCN). The FPCN facilitates interaction between feature vectors from localized regions within image pairs, capturing both shared and distinctive features. Further, it accommodates the variable scales of objects depicted in images, which correspond to differing quantities of inherent object information, directing the network’s attention to additional contextual details based on object size variability. Leveraging knowledge distillation, the architecture is streamlined, with a focus on nuanced information at activation boundaries to master the precise fine-grained decision boundaries, thereby enhancing the small model’s accuracy. Empirical evidence demonstrates that our proposed method based on FPCN improves the classification accuracy mobile lightweight models by nearly 2% while maintaining the same time and space consumption.
Accurate prediction of urban grid-scale population inflow is crucial for smart city management and emergency response. However, existing methods struggle to model spatial heterogeneity and quantify prediction uncertainty, limiting their accuracy and decision-support capabilities. This paper proposes PDCDM (POI-enhanced Dual-Dimensional Conditional Diffusion Model), which integrates urban functional semantic awareness with conditional diffusion modeling. The model captures urban functional attributes through multi-scale Point of Interest (POI) feature representations and incorporates them into the diffusion generation process. A dual-dimensional Transformer architecture is employed to decouple the modeling of temporal dependencies and inter-grid interactions, enabling adaptive fusion of grid-level features with dynamic temporal patterns. Building upon this dual-dimensional modeling framework, the conditional diffusion mechanism generates probabilistic predictions with explicit uncertainty quantification. Real-world urban dataset validation demonstrates that PDCDM significantly outperforms existing state-of-the-art methods in prediction accuracy and uncertainty quantification. Comprehensive ablation studies validate the effectiveness of each component and confirm the model’s practicality in complex urban scenarios.