Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework

The moving trajectory of the pipe-jacking machine(PJM),which primarily determines the end quality of jacked tunnels,must be controlled strictly during the entire jacking process.Developing prediction models to support drivers in performing rectifications in advance can effectively avoid considerable trajectory deviations from the designed jacking axis.Hence,a gated recurrent unit(GRU)-based deep learning framework is proposed herein to dynamically predict the moving trajectory of the PJM.In this framework,operational data are first extracted from a data acquisition system;subsequently,they are preprocessed and used to establish GRU-based multivariate multistep-ahead direct prediction models.To verify the performance of the proposed framework,a case study of a large pipe-jacking project in Shanghai and comparisons with other conventional models(i.e.,long short-term memory(LSTM)network and recurrent neural network(RNN))are conducted.In addition,the effects of the activation function and input time-step length on the prediction performance of the proposed framework are investigated and discussed.The results show that the proposed framework can dynamically and precisely predict the PJM moving trajectory during the pipe-jacking process,with a minimum mean absolute error and root mean squared error(RMSE)of 0.1904 and 0.5011 mm,respectively.The RMSE of the GRU-based models is lower than those of the LSTM-and RNN-based models by 21.46%and 46.40%at the maximum,respectively.The proposed framework is expected to provide an effective decision support for moving trajectory control and serve as a foundation for the application of deep learning in the automatic control of pipe jacking.

SOINN-Based Abnormal Trajectory Detection for Efficient Video Condensation

With the evolution of video surveillance systems,the requirement of video storage grows rapidly;in addition,safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events.As most of the scene in the surveillance video are redundant and contains no information needs attention,we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly.Our goal is to improve the condensation rate to reduce more storage size,and increase the accuracy in abnormal detection.As the trajectory feature is the key to both goals,in this paper,a new method for feature extraction of moving object trajectory is proposed,and we use the SOINN(Self-Organizing Incremental Neural Network)method to accomplish a high accuracy abnormal detection.In the results,our method is able to shirk the video size to 10%storage size of the original video,and achieves 95%accuracy of abnormal event detection,which shows our method is useful and applicable to the surveillance industry.

Monocular Visual-Inertial and Robotic-Arm Calibration in a Unifying Framework

Reliable and accurate calibration for camera,inertial measurement unit(IMU)and robot is a critical prerequisite for visual-inertial based robot pose estimation and surrounding environment perception.However,traditional calibrations suffer inaccuracy and inconsistency.To address these problems,this paper proposes a monocular visual-inertial and robotic-arm calibration in a unifying framework.In our method,the spatial relationship is geometrically correlated between the sensing units and robotic arm.The decoupled estimations on rotation and translation could reduce the coupled errors during the optimization.Additionally,the robotic calibration moving trajectory has been designed in a spiral pattern that enables full excitations on 6 DOF motions repeatably and consistently.The calibration has been evaluated on our developed platform.In the experiments,the calibration achieves the accuracy with rotation and translation RMSEs less than 0.7°and 0.01 m,respectively.The comparisons with state-of-the-art results prove our calibration consistency,accuracy and effectiveness.

Context-Based Moving Object Trajectory Uncertainty Reduction and Ranking in Road Network

To support a large amount of GPS data generated from various moving objects, the back-end servers usually store low-sampling-rate trajectories. Therefore, no precise position information can be obtained directly from the back-end servers and uncertainty is an inherent characteristic of the spatio-temporal data. How to deal with the uncertainty thus becomes a basic and challenging problem. A lot of researches have been rigidly conducted on the uncertainty of a moving object itself and isolated from the context where it is derived. However, we discover that the uncertainty of moving objects can be efficiently reduced and effectively ranked using the context-aware information. In this paper, we focus on context- aware information and propose an integrated framework, Context-Based Uncertainty Reduction and Ranking （CURR）, to reduce and rank the uncertainty of trajectories. Specifically, given two consecutive samplings, we aim to infer and rank the possible trajectories in accordance with the information extracted from context. Since some context-aware information can be used to reduce the uncertainty while some context-aware information can be used to rank the uncertainty, to leverage them accordingly, CURR naturally consists of two stages： reduction stage and ranking stage which complement each other. We also implement a prototype system to validate the effectiveness of our solution. Extensive experiments are conducted and the evaluation results demonstrate the efficiency and high accuracy of CURR.

Efficient κ-Nearest-Neighbor Search Algorithms for Historical Moving Object Trajectories

Nearest Neighbor （κNN） search is one of the most important operations in spatial and spatio-temporal databases. Although it has received considerable attention in the database literature, there is little prior work on κNN retrieval for moving object trajectories. Motivated by this observation, this paper studies the problem of efficiently processing κNN （κ≥ 1） search on R-tree-like structures storing historical information about moving object trajectories. Two algorithms are developed based on best-first traversal paradigm, called BFPκNN and BFTκNN, which handle the κNN retrieval with respect to the static query point and the moving query trajectory, respectively. Both algorithms minimize the number of node access, that is, they perform a single access only to those qualifying nodes that may contain the final result. Aiming at saving main-memory consumption and reducing CPU cost further, several effective pruning heuristics are also presented. Extensive experiments with synthetic and real datasets confirm that the proposed algorithms in this paper outperform their competitors significantly in both efficiency and scalability.