1. Indoor Pedestrian Trajectory Detection with LSTM Network
- Author
-
Qiang Li, Jin Li, Nanxi Chen, and Yingguan Wang
- Subjects
Computer science ,business.industry ,020209 energy ,Deep learning ,Detector ,02 engineering and technology ,Pedestrian ,Recurrent neural network ,Handwriting recognition ,0202 electrical engineering, electronic engineering, information engineering ,Trajectory ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,business - Abstract
This paper proposes a novel technique to detect the main moving trajectory of indoor pedestrians. Based on Long Short- Term Memory(LSTM) Network, this deep learning network is capable of learning the trajectory of human beings using indoor Wi-Fi positioning data. The data is collected by Wi-Fi detectors densely installed in a public building in the urban area, which can ensure the detection of any portable devices as long as the Wi-Fi module is turned on. Then the model works in the form of sequence modeling to learn the trajectory of the main stream extracted from massive pedestrian positioning data. In compare with methods like Recurrent Neural Network (RNN) and Gated Recurrent Unit(GRU), there is an obvious performance improvement of this method.
- Published
- 2017