GPS trajectories generated by moving objects provide researchers with an excellent resource for revealing patterns of human activities. Relevant research based on GPS trajectories includes the fields of location-based services, transportation science, and urban studies among others. Research relating to how to obtain GPS data (e.g., GPS data acquisition, GPS data processing) is receiving significant attention because of the availability of GPS data collecting platforms. One such problem is the GPS data classification based on transportation mode. The challenge of classifying trajectories by transportation mode has approached detecting different modes of movement through the application of several strategies. From a GPS data acquisition point of view, this paper macroscopically classifies the transportation mode of GPS data into single-mode and mixed-mode. That means GPS trajectories collected based on one type of transportation mode are regarded as single-mode data; otherwise it is considered as mixed-mode data. The one big difference of classification strategy between single-mode and mixed-mode GPS data is whether we need to recognize the transition points or activity episodes first. Based on this, we systematically review existing classification methods for single-mode and mixed-mode GPS data and introduce the contributions of these methods as well as discuss their unresolved issues to provide directions for future studies in this field. Based on this review and the transportation application at hand, researchers can select the most appropriate method and endeavor to improve them.

Short-term traffic prediction is of great importance to the management of traffic congestion, a pervasive and difficult-to-solve problem in many metropolises all over the world. However, existing studies on traffic prediction contain rough traffic information at the carriageway level that ignore the distinction between different turns in one intersection. With the aim of predicting traffic at road intersections from big trace data on a finer scale, this study proposes a novel method, the fine-grained traffic prediction method (FTPG) with a graph attention network (GAT), which predicts traffic information, including traffic flow speeds, traffic states, and average queue lengths, at the turn level. In the FTPG, a method for estimation of the queue starting point is proposed to improve the accuracy of traffic information detection. Furthermore, the topology is constructed under turn-level conditions, and a GAT-based method, the spatio-temporal residual graph attention network (ST-RGAN), is proposed to improve the prediction accuracy. Experiments are performed using taxi GPS trace data collected in the city of Wuhan and show that the proposed FTPG method can make predictions with fine-grained traffic information for road intersections accurately and robustly.

In this paper, we propose a novel approach for mining lane-level road network information from low-precision vehicle GPS trajectories (MLIT), which includes the number and turn rules of traffic lanes based on naïve Bayesian classification. First, the proposed method (MLIT) uses an adaptive density optimization method to remove outliers from the raw GPS trajectories based on their space-time distribution and density clustering. Second, MLIT acquires the number of lanes in two steps. The first step establishes a naïve Bayesian classifier according to the trace features of the road plane and road profiles and the real number of lanes, as found in the training samples. The second step confirms the number of lanes using test samples in reference to the naïve Bayesian classifier using the known trace features of test sample. Third, MLIT infers the turn rules of each lane through tracking GPS trajectories. Experiments were conducted using the GPS trajectories of taxis in Wuhan, China. Compared with human-interpreted results, the automatically generated lane-level road network information was demonstrated to be of higher quality in terms of displaying detailed road networks with the number of lanes and turn rules of each lane.

Semantic segmentation for remote sensing images faces challenges of unbalanced category weight, rich context causing difficulties of recognition, blurred boundaries of multi-scale objects, and so on. To address these problems, we propose a new model by combining HRNet with attention mechanisms and dilated convolution, denoted as: AD-HRNet for the semantic segmentation of remote sensing images. In the framework of AD-HRNet, we obtained the weight value of each category based on an improved weighted cross-entropy function by introducing the median frequency balance method to solve the issue of class weight imbalance. The Shuffle-CBAM module with channel attention and spatial attention in AD-HRNet framework was applied to extract more global context information of images through slightly increasing the amount of computation. To address the problem of blurred boundaries caused by multi-scale object segmentation and edge segmentation, we developed an MDC-DUC module in AD-HRNet framework to capture the context information of multi-scale objects and the edge information of many irregular objects. Taking Postdam, Vaihingen, and SAMA-VTOL datasets as materials, we verified the performance of AD-HRNet by comparing with eight typical semantic segmentation models. Experimental results shown that AD-HRNet increases the mIoUs to 75.59% and 71.58% based on the Postdam and Vaihingen datasets, respectively.

The design of urban clusters has played an important role in urban planning, but realizing the construction of these urban plans is quite a long process. Hence, how the progress is evaluated is significant for urban managers in the process of urban construction. Traditional methods for detecting urban clusters are inaccurate since the raw data is generally collected from small sample questionnaires of resident trips rather than large-scale studies. Spatiotemporal big data provides a new lens for understanding urban clusters in a natural and fine-grained way. In this article, we propose a novel method for Detecting and Evaluating Urban Clusters (DEUC) with taxi trajectories and Sina Weibo check-in data. Firstly, DEUC applies an agglomerative hierarchical clustering method to detect urban clusters based on the similarities in the daily travel space of urban residents. Secondly, DEUC infers resident demands for land-use functions using a naïve Bayes’ theorem, and three indicators are adopted to assess the rationality of land-use functions in the detected clusters—namely, cross-regional travel index, commuting direction index, and fulfilled demand index. Thirdly, DEUC evaluates the progress of urban cluster construction by calculating a proposed conformance indicator. In the case study, we applied our method to detect and analyze urban clusters in Wuhan, China in the years 2009, 2014, and 2015. The results suggest the effectiveness of the proposed method, which can provide a scientific basis for urban construction.

This paper introduces a number of innovative no-reference algorithms to assess the perceived quality of realtime analog and digital television and video streams. A prototype system is developed to locate and measure the impact of three types of impairments that commonly impair television and video signals. Analog sequences are tested for the presence of random noise. In the case of digital signals, two fundamental types of errors are of interest. The first is the blocking artifact that is so pervasive among DCT-based compression schemes such as MPEG. The second category includes errors caused by random changes to the bit stream of a signal. Of the various forms that these distortions may take on, only those that appear as "colored blocks" are detected by this system. Ideas to address the remaining issues are discussed.