Trajectory prediction is one of the core functions of autonomous driving. Modeling spatial-aware interactions and temporal motion patterns for observed vehicles are critical for accurate trajectory prediction. Most recent works on trajectory prediction utilize recurrent neural networks (RNNs) to model temporal patterns and usually need convolutional neural networks (CNNs) additionally to capture spatial interactions. Although Transformer, a multi-head attention-based network, has shown its notable ability in many sequence-modeling tasks (e.g., machine translation in natural language processing), it has not been explored much in trajectory prediction. This paper presents a Spatial Interaction-aware Transformer-based model, which uses the multi-head self-attention mechanism to capture both interactions of neighbor vehicles and temporal dependencies of trajectories. This model applies a GRU-based encoder-decoder module to make the prediction. Besides, different from methods considering the spatial interactions only among observed trajectories in both encoding and decoding stages, our model will also consider the potential spatial interactions between future trajectories in decoding. The proposed model was evaluated on the NGSIM dataset. Compared with other baselines, our model exhibited better prediction precision, especially for long-term prediction.

Change detection (CD) is vital in remote sensing (RS) image interpretation applications and has been well improved driven by deep learning (DL). However, existing DL-based methods have poor model robustness due to the effect of limited number of change samples in the existing public datasets, and on the other hand, existing most CD methods only process the input image in the spatial domain, and insufficiently process it at the frequency domain level, which leads to its ability to obtain only shallow semantic information of the image, and insufficient ability to deal with the high-frequency information (edges, details) in the RS. In order to address the issue, this paper proposed DSFI-CD, which generates part of the pseudo-images by using conditional DDPM. Furthermore, it suggests a module called Spatial Frequency Interaction (SFI), which combines the extraction and fusion of the corresponding spatial and frequency domain data with the intersection of the dual time-phase features prior to and following the change to give the model more reliable information. Additionally, we designed the Edge Enhanced (EE) Module to further decompose the extracted features in the SFI Module into boundary and body information for the change region edge information. We do this by using the concept of flow field, and we also use the Laplace pyramid and multilevel feature fusion to increase the sensitivity of the model to the boundary while reducing the impact of noise in the non-change region. Comprehensive experiments on four publicly accessible CD datasets show that DSFI-CD performs better than other state-of-the-art (SOTA) methods.

The relationship between commercial vehicle travel patterns and urban functional areas reveals potential connections between urban form and human geographic flows, which provides critical information for optimizing urban transportation systems. Benefiting from the large-scale trajectory datasets, it would be possible to investigate deeper research by modeling the implied urban travel patterns. This study designs a framework to reveal the collective movement patterns of commercial vehicle trajectories inside the urban environment, focusing on their spatiotemporal variations within functional areas. Stopping behaviors of trajectories were identified to construct spatiotemporal origin-destination (OD) matrices, representing time-varying human geographic flows. The singular value decomposition (SVD) method was employed to quantify spatio-temporal OD matrice to obtain time and space travel features. Travel patterns’ dynamics and spatial interactions within functional areas were then analyzed. The experimental results obtained with real-life datasets from Changsha, China, uncovered three typical travel patterns depicting commercial vehicle activities in urban environment shifts from work-related locations on weekdays to leisure destinations on weekends, with central areas experiencing more short and medium-range trips. The findings provide scientific references for optimizing spatio-temporal travel patterns and functional distribution to meet the demands of urban development and traffic management strategies.

The purpose of remote sensing image change detection (RSCD) is to detect differences between bitemporal images taken at the same place. Deep learning has been extensively used to RSCD tasks, yielding significant results in terms of result recognition. However, due to the shooting angle of the satellite, the impacts of thin clouds, and certain lighting conditions, the problem of fuzzy edges in the change region in some remote sensing photographs cannot be properly handled using current RSCD algorithms. To solve this issue, we proposed a body decouple multiscale by feature aggregation change detection , a novel model that collects both global and local feature map information in the channel and space dimensions of the feature map during the training and prediction phases. This approach allows us to successfully extract the change region's boundary information while also divorcing the change region's main body from its boundary. Numerous studies have shown that the assessment metrics and evaluation effects of the model described in this article on the publicly available datasets DSIFN-CD, S2Looking, and WHU-CD are the best when compared to other models.

Lane-level road information is especially crucial now that high-precision navigation maps are in more demand. Road information may be obtained rapidly and affordably by mining floating vehicle data (FCD). A method is proposed to extract the number of lanes on urban roads by combining deep learning and low-frequency FCD. Initially, the FCD is cleaned using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique. Then, the FCD is split into three categories based on the typical urban road types: one-way one-lane, one-way two-lane, and one-way three-lane, and the deep learning sample data is created using segmentation, rotation, and gridding. Lastly, the number of urban road lanes is obtained by training and predicting the sample data using the LeNet-5 model. The number of urban road lanes was effectively identified from the low-frequency FCD with a detection accuracy of 92.7% through the cleaning and classification of Wuhan FCD. Urban roads can be efficiently covered by the FCD on a regular basis, and lane information can be efficiently collected using deep learning techniques. This method can be used to generate and update lane number information for high-precision navigation maps.