The accurate smartphone-based pedestrian navigation significantly depends on the precise heading estimation. However, heading estimation is still a challenging problem in most pedestrian navigation applications because of the bias of low-cost smartphone sensors, thermal drift with long-term operation, and the unexpected changes in the carrying mode of handheld devices. To address these challenges, many existing methods based on pervasive resources encounter severe errors. Conversely, auxiliary resources-based approaches may hinder ubiquitous and seamless indoor-outdoor navigation experiences. This research aims to enhance heading estimation by leveraging pervasive measurements such as LVGOs and straight-line features self-recognized from camera images. The proposed method mitigates the accumulated gyro drift using the absolute heading angle estimated by LVGOs. However, these absolute angles are highly prone to false estimation while navigating near areas with high electric and magnetic activities due to stable geomagnetism anomalies. Encouraged by the pervasiveness of straight-line features in indoor and outdoor environments, we developed a deep learning method-based visual tracking of these features to enhance the gyroscope and magnetic field fusion-based heading estimation. A convolutional neural network was developed using a U-Net network to accurately and quickly recognize these features, then leverage them as heading constraint to overcome long-term gyro drift and short-term compass heading bias. The proposed method superiorly ensured the balance between recognition time delay and precision, which enabled smooth real-time performance. The achieved results improved the heading estimation and could provide significant help, especially for visually impaired people, as they mostly track tactile paving. This encourages future tests and assessments using visually impaired people to reliably include the proposed method in their applications.

Recently, electric vertical take-off and landing (eVTOL) aircraft have become a top priority for urban air transportation due to their ability to overcome urban ground traffic congestion. In this research, a new type of scaled lift–cruise ‘Dragonfly’ has been designed. The ‘Dragonfly’ combines the characteristics of an octocopter and a fixed-wing aircraft. Compared with the same type of eVTOL aircraft, it has a longer wingspan and a more stable aircraft structure, it can not only take off and land vertically without the need for a runway, but also fly quickly in a straight line and hover in mid-air. In order to ensure the success of the flight test, it was also simulated in this paper. A simulation scenario highly fitting with the flight test environment of eVTOL is designed in the Gazebo simulation platform, and then combined with the PX4 flight control platform, the system SITL of the constructed aircraft simulation model is carried out on the Gazebo platform, Finally, simulation flight test data for accurate analysis are obtained, the accuracy and stability of the control algorithm are fed back, and scientific support for the follow-up ‘Dragonfly’ aircraft hardware-in-the-loop simulation and physical flight test is provided.

Hyperspectral and light detection and ranging (LiDAR) imaging instruments capture on-ground object information from diverse perspectives, reflecting spectral–spatial and elevation descriptions, respectively. Their complementary capturing feasibilities contribute to enhancing accurate landcover identification in multimodal data fusion tasks. However, their heterogeneous distributions always impede fusion and joint classification performance, leading to wrong classification phenomena. To solve this challenge, we proposed a deep multiscale cross-modal attention (DMSCA) network for hyperspectral and LiDAR data fusion and joint classification. Compared with existing methods, our primary motivation is to explore the intrinsic connection between these two specific remote sensing modalities and enhance their shared attributes through the implementation of various cross-modal attention mechanisms. The extracted modality features are cross-modally integrated and exchanged, thereby enhancing the overall consistency of the simulations. Specifically, these cross-modal attention mechanisms are capable of strengthening local considerable segments considering detailed hyperspectral and LiDAR geographical descriptions. The spatial-wise attention mechanism measures the contributions of neighboring samples to classification performance. The spectral-wise attention mechanism highlights the significant hyperspectral channels in terms of channel correlation. The elevation-wise attention mechanism highly connects the hyperspectral-related attention mechanisms to detailed LiDAR elevations for information fusion. Based on these mechanisms, an adaptive fusion and joint classification framework is constructed for balancing multimodal information. Multiple experiments are conducted on three widely used datasets to prove the effectiveness of DMSCA. Experimental results prove that DMSCA outperforms state-of-the-art techniques qualitatively and quantitatively.

1. The development of precision agriculture demands high accuracy and efficiency of farmland parcel information extraction. Farmland parcels are the basic units on which humans engage in agricultur...

Extracting buildings from high-resolution remote sensing images is currently a research hotspot in the field of remote sensing applications. Deep learning methods have significantly improved the accuracy of building extraction, but there are still deficiencies such as blurred edges, incomplete structures and loss of details in the extraction results. To obtain accurate contours and clear boundaries of buildings, this article proposes a novel building extraction method utilizing multi-scale attention gate and enhanced positional information. By employing U-Net as the main framework, this article introduces a multi-scale attention gate module in the encoder, which effectively improves the ability to capture multi-scale information, and designs a module in the decoder to enhance the positional information of the features, allowing for more precise localization and extraction of the shape and edge information of buildings. To validate the effectiveness of the proposed method, comprehensive evaluations were conducted on three benchmark datasets, Massachusetts, WHU, and Inria. The comparative analysis with six state-of-the-art models (SegNet, DeepLabv3+, U-Net, DSATNet, SDSC-Unet, and BuildFormer) demonstrates consistent performance improvements in intersection over union (IoU) metrics. Specifically, the proposed method achieves IoU increments of 2.19%, 3.31%, 3.10%, 2.00%, 3.35%, and 3.48% respectively on Massachusetts dataset, 1.26%, 4.18%, 1.18%, 2.01%, 2.03%, and 2.29% on WHU dataset, and 0.87%, 5.25%, 2.02%, 5.55%, 4.39%, and 1.18% on Inria dataset. The experimental results indicate that the proposed method can effectively integrate multi-scale features and optimize the extracted building edges, achieving superior performance compared to existing methodologies in building extraction tasks.

Recently, hyperspectral image (HSI) classification with limited training samples has been well studied, where the metric-based few-shot classification or cross-domain few-shot classification methods have shown good performance. However, overcoming the overlapping distribution of classes and outliers solely through limited labeled samples remains a challenging problem. Moreover, too few labeled samples may lead to susceptibility to intra-class variations during cross-domain classification, and over-reliance on HSI modality constrains the accuracy of prototype representations to a certain extent. As such, a language dynamic-guided spatial-spectral network (LDSNet) framework is proposed for cross-domain few-shot HSI classification. Firstly, a multibranch spatial-spectral feature dynamic extraction model is designed to explore the local fine details, global structures, and spectral correlations, where the class text information is considered as a guidance to drive the whole model to extract the class-wise spatial-spectral features. Then, a cross-model alignment module is introduced to improve the class prototypes from spatial-spectral features through image-text matching, increasing the inter-class distances. Finally, in response to the intra-class variations and interference caused by limited labeled samples, a combination method of integrating prompt consistency learning and self-similarity masking learning is further developed. Hence, stable feature representations that do not vary with sample distribution can be generated, which ensures the representation consistency between different samples, improving the classification performance of target domain. Extensive experiments conducted on four HSI datasets demonstrate the superiority of our LDSNet framework in comparison with other state-of-the-art methods for cross-domain few-shot HSI classification.