The availability of the Global Positioning System (GPS) trajectory data is
increasing along with the availability of different GPS receivers and with the
increasing use of various mobility services. GPS trajectory is an important
data source which is used in traffic density detection, transport mode
detection, mapping data inferences with the use of different methods such as
image processing and machine learning methods. While the data size increases,
efficient representation of this type of data is becoming difficult to be used
in these methods. A common approach is the representation of GPS trajectory
information such as average speed, bearing, etc. in raster image form and
applying analysis methods. In this study, we evaluate GPS trajectory data
rasterization using the spatial join functions of QGIS, PostGIS+QGIS, and our
iterative spatial structured grid aggregation implementation coded in the
Python programming language. Our implementation is also parallelizable, and
this parallelization is also included as the fourth method. According to the
results of experiment carried out with an example GPS trajectory dataset, QGIS
method and PostGIS+QGIS method showed relatively low performance with respect
to our method using the metric of total processing time. PostGIS+QGIS method
achieved the best results for spatial join though its total performance
decreased quickly while test area size increases. On the other hand, both of
our methods' performances decrease directly proportional to GPS point. And our
methods' performance can be increased proportional to the increase with the
number of processor cores and/or with multiple computing clusters.

GPS 轨迹数据的栅格化在 QGIS 和 PostGIS+QGIS 方法中相对性能较低，而我们的方法能够根据处理时间指标获得最好的结果，其性能直接与 GPS 点的数量成比例并可通过增加处理器核心数量和 / 或多个计算集群进行提高。

GPS 轨迹栅格化方法的性能评估

Performance Evaluation of GPS Trajectory Rasterization Methods

This study presents an innovative approach for automatic road detection with
deep learning, by employing fusion strategies for utilizing both
lower-resolution satellite imagery and GPS trajectory data, a concept never
explored before. We rigorously investigate both early and late fusion
strategies, and assess deep learning based road detection performance using
different fusion settings. Our extensive ablation studies assess the efficacy
of our framework under diverse model architectures, loss functions, and
geographic domains (Istanbul and Montreal). For an unbiased and complete
evaluation of road detection results, we use both region-based and
boundary-based evaluation metrics for road segmentation. The outcomes reveal
that the ResUnet model outperforms U-Net and D-Linknet in road extraction
tasks, achieving superior results over the benchmark study using low-resolution
Sentinel-2 data. This research not only contributes to the field of automatic
road detection but also offers novel insights into the utilization of data
fusion methods in diverse applications.

本研究提出了一种创新的深度学习自动道路检测方法，通过融合低分辨率卫星图像和 GPS 轨迹数据的策略，对早期和后期融合进行深入研究，并使用不同的融合设置评估基于深度学习的道路检测性能。研究结果显示，ResUnet 模型在道路提取任务中优于 U-Net 和 D-Linknet，以及使用低分辨率 Sentinel-2 数据的基准研究，从而为自动道路检测领域作出贡献，并为各种应用中的数据融合方法提供了新的见解。

使用多模态数据的人工智能驱动的道路网络预测

AI Powered Road Network Prediction with Multi-Modal Data

Identifying travelers' transportation modes is important in transportation
science and location-based services. It's appealing for researchers to leverage
GPS trajectory data to infer transportation modes with the popularity of
GPS-enabled devices, e.g., smart phones. Existing studies frame this problem as
classification task. The dominant two-stage studies divide the trip into
single-one mode segments first and then categorize these segments. The over
segmentation strategy and inevitable error propagation bring difficulties to
classification stage and make optimizing the whole system hard. The recent
one-stage works throw out trajectory segmentation entirely to avoid these by
directly conducting point-wise classification for the trip, whereas leaving
predictions dis-continuous. To solve above-mentioned problems, inspired by YOLO
and SSD in object detection, we propose to reframe change point detection and
segment classification as a unified regression task instead of the existing
classification task. We directly regress coordinates of change points and
classify associated segments. In this way, our method divides the trip into
segments under a supervised manner and leverage more contextual information,
obtaining predictions with high accuracy and continuity. Two frameworks,
TrajYOLO and TrajSSD, are proposed to solve the regression task and various
feature extraction backbones are exploited. Exhaustive experiments on GeoLife
dataset show that the proposed method has competitive overall identification
accuracy of 0.853 when distinguishing five modes: walk, bike, bus, car, train.
As for change point detection, our method increases precision at the cost of
drop in recall. All codes are available at
this https URL

使用 GPS 轨迹数据通过一种统一回归任务的方法，将旅行划分为具有监督方式的段落，并利用更多上下文信息，以高准确性和连续性得出五种交通方式的预测。

在回归任务中将变点检测和段分类统一，用于交通方式识别

Unify Change Point Detection and Segment Classification in a Regression  Task for Transportation Mode Identification

With the deployment of GPS-enabled devices and data acquisition technology,
the massively generated GPS trajectory data provide a core support for
advancing spatial-temporal data mining research. Nonetheless, GPS trajectories
comprise personal geo-location information, rendering inevitable privacy
concerns on plain data. One promising solution to this problem is trajectory
generation, replacing the original data with the generated privacy-free ones.
However, owing to the complex and stochastic behavior of human activities,
generating high-quality trajectories is still in its infancy. To achieve the
objective, we propose a diffusion-based trajectory generation (Diff-Traj)
framework, effectively integrating the generation capability of the diffusion
model and learning from the spatial-temporal features of trajectories.
Specifically, we gradually convert real trajectories to noise through a forward
trajectory noising process. Then, Diff-Traj reconstructs forged trajectories
from the noise by a reverse trajectory denoising process. In addition, we
design a trajectory UNet (Traj-UNet) structure to extract trajectory features
for noise level prediction during the reverse process. Experiments on two
real-world datasets show that Diff-Traj can be intuitively applied to generate
high-quality trajectories while retaining the original distribution.

本文提出基于扩散模型的轨迹生成框架 Diff-Traj，并通过轨迹 UNet (Traj-UNet) 结构提取轨迹特征，使其能视为高质量的轨迹生成应用程序，并保留原始分布。