Detecting regional dominant movement patterns in trajectory data with a convolutional neural network
Open Access
- 12 December 2019
- journal article
- research article
- Published by Taylor & Francis in International Journal of Geographical Information Science
- Vol. 34 (5) , 996-1021
Abstract
Detecting movement patterns with complicated spatial or temporal characteristics is a challenge. The past decade has witnessed the success of deep learning in processing image, voice and text data. However, its application in movement pattern detection is not fully exploited. To address the research gap, this paper develops a deep learning approach to detect regional dominant movement patterns (RDMP) in trajectory data. Specifically, a novel feature descriptor called directional flow image (DFI) is firstly proposed to store the local directional movement information in trajectory data. A DFI classification model called TRNet is designed based on convolutional neural network. The model is then trained with a synthetic trajectory dataset covering 11 classes of commonly encountered movement patterns in reality. Finally, a sliding window detector is built to detect RDMP at multiple scales and a clustering-based merging method is proposed to prune the redundant detection results. Training of TRNet on the synthetic dataset achieves considerably high accuracy. Experiments on a real-world taxi trajectory dataset further demonstrate the effectiveness and efficiency of the proposed approach in discovering complex movement patterns in trajectory data.Keywords
This publication has 31 references indexed in Scilit:
- First Report of the Cereal Cyst Nematode Heterodera latipons on Wheat in MoroccoPlant Disease, 2012
- Finding moving flock patterns among pedestrians through collective coherenceInternational Journal of Geographical Information Science, 2011
- A novel contour descriptor for 2D shape matching and its application to image retrievalImage and Vision Computing, 2011
- Space–time density of trajectories: exploring spatio-temporal patterns in movement dataInternational Journal of Geographical Information Science, 2010
- ST‐DMQL: A Semantic Trajectory Data Mining Query LanguageInternational Journal of Geographical Information Science, 2009
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Ultrasound-Guided Infraclavicular Versus Supraclavicular BlockAnesthesia & Analgesia, 2005
- Discovering relative motion patterns in groups of moving point objectsInternational Journal of Geographical Information Science, 2005
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998