Large-scale deployed cameras in the automated container terminal (ACT) area helps on-site staff better identify unexpected yet emergency events by monitoring port personnel trajectories. Rainy weather isacommon yet typical problem which may significantly deteriorate trajectory extraction performance. To tackle the problem, the study proposes an ensemble framework to extract personnel trajectory from port-like surveillance videos under varied rainy weather scenarios. Firstly, the proposed framework learns fine-grained personnel features with the help of the object query and transformer encoder-decoder module from the input port-like image sequences, and thus obtains port personnel locations from the input low-visibility images. Secondly, the personnel positions are further associated in a frame-by-frame manner with the help of neighboring kinematic movement information and feature information. Finally, a memory mechanism is introduced in the proposed framework to suppress personnel trajectory discontinuity outlier. In that manner, we can obtain accurate yet consistent personnel trajectories, and each person is assigned with a unique ID. We verified the proposed model performance on three port-like rainy videos involving with interferences of rain, rain streak and fog. Experimental results show that the proposed port personnel trajectory extraction framework can obtain satisfied performance considering that the average multi-target accuracy (MOTA), the average value of judging the same target (${\mathbf{IDF}}_{\mathbf{1}}$), average recall rate (IDR) and average precision (IDP) were larger than 92%.

Predicting the crowd flow in various areas of the city is of strategic importance for traffic control and public safety. In recent years, crowd flow prediction based on spatio-temporal data are gaining more and more attention. In order to better understand the current status of spatio-temporal crowd flow prediction research and global cooperation, we use scientometric methods, social network analysis, and Stochastic Actor-oriented Model (SAOM) to visualize and analyze the source journals, hotspot co-occurrence networks, and national cooperation networks based on the relevant literature included in the Web of Science database, so as to explore the current status and characteristics of related academic research. In addition, this paper constructs a technical framework based on Subject–Action–Object (SAO) structural information, and draws a technical roadmap containing five levels: data, technology, influence factors, objectives, and applications. The visual mapping of the evolutionary path of technology topics based on SAO structure information can assist in analyzing the evolutionary path of technology topics and their development trends. This study contributes to the existing knowledge system of spatio-temporal crowd flow prediction by proposing a new, integrated, and holistic knowledge map.

As a primary countermeasure to mitigate traffic congestion and air pollution, promoting public transit has become a global census. Designing a robust and reliable bus timetable is a pivotal step to increase ridership and reduce operating cost for transit authorities. However, most previous studies on bus timetabling rely on historical passenger count and travel time data to generate static schedules, which often yield biased results in these uncertain scenarios, such as demand surge or adverse weather. In addition, acquiring real-time passenger origin/destination from a limited number of running buses is not feasible. This article considers the multiline dynamic bus timetable optimization problem as a Markov decision process model to address the aforementioned issues, and proposes a multiagent deep reinforcement learning framework to ensure effective learning from the imperfect-information game, where the passenger demand and traffic condition are not always known in advance. Moreover, a distributed reinforcement learning algorithm is applied to overcome the limitation of high computational cost and low efficiency. A case study of multiple bus lines in Beijing, China, confirms the effectiveness and efficiency of the proposed model. The results demonstrate that our method outperforms heuristic and state-of-the-art reinforcement learning algorithms by reducing 20.30% of operating and passenger costs compared with actual timetables.

Automated container terminal (ACT) is considered as port industry development direction, and accurate kinematic data (speed, volume, etc.) is essential for enhancing ACT operation efficiency and safety. Port surveillance videos provide much useful spatial-temporal information with advantages of easy obtainable, large spatial coverage, etc. In that way, it is of great importance to analyze automated guided vehicle (AGV) trajectory movement from port surveillance videos. Motivated by the newly emerging computer vision and artificial intelligence (AI) techniques, we propose an ensemble framework for extracting vehicle speeds from port-like surveillance videos for the purpose of analyzing AGV moving trajectory. Firstly, the framework exploits vehicle position in each image via a feature-enhanced scale-aware descriptor. Secondly, we match vehicle position and trajectory data from the previous step output via Kalman filter and Hungarian algorithm, and thus we obtain the vehicular imaging trajectory in a frame-by-frame manner. Thirdly, we estimate the vehicular moving speed in real-world via the help of perspective projection theory. The experimental results suggest that our proposed framework can obtain accurate vehicle kinematic data under typical port traffic scenarios considering that the average measurement error of root mean square deviation is 0.675 km/h, the mean absolute deviation is 0.542 km/h, and the Pearson correlation coefficient is 0.9349. The research findings suggest that cutting-edge AI and computer vision techniques can accurately extract on-site vehicular trajectory related data from port videos, and thus help port traffic participants make more reasonable management decisions.

In recent years, unmanned aerial vehicle (UAV) has become an increasingly popular tool for traffic monitoring and data collection on highways due to its advantage of low cost, high resolution, good flexibility, and wide spatial coverage. Extracting high-resolution vehicle trajectory data from aerial videos taken by a UAV flying over target highway segment becomes a critical research task for traffic flow modeling and analysis. This study aims at proposing a novel methodological framework for automatic and accurate vehicle trajectory extraction from aerial videos. The method starts by developing an ensemble detector to detect vehicles in the target region. Then, the kernelized correlation filter is applied to track vehicles fast and accurately. After that, a mapping algorithm is proposed to transform vehicle positions from the Cartesian coordinates in image to the Frenet coordinates to extract raw vehicle trajectories along the roadway curves. The data denoising is then performed using a wavelet transform to eliminate the biased vehicle trajectory positions. Our method is tested on two aerial videos taken on different urban expressway segments in both peak and non-peak hours on weekdays. The extracted vehicle trajectories are compared with manual calibrated data to testify the framework performance. The experimental results show that the proposed method successfully extracts vehicle trajectories with a high accuracy: the measurement error of Mean Squared Deviation is 2.301 m, the Root-mean-square deviation is 0.175 m, and the Pearson correlation coefficient is 0.999. The video and trajectory data in this study are publicly accessible for serving as benchmark at https://seutraffic.com.

At present, most unsupervised abnormal behavior detection method only relies on powerful behavior detection classifiers, does not make full use of prior knowledge. This method often has the problem of a huge amount of calculation and affecting the detection speed. In view of the above problems, this paper proposes a weak anomalyreinforced autoencoder for unsupervised anomaly detection method, using U-Net to reconstruct video frames and generative adversarial network to learn the correlation between image entropy and abnormal behavior. Comprehensive experiments on the avenue data set and UCSD data sets verify the effectiveness of our method to detect abnormal events.