Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder
Authors:
- L. MaczytaLML. Maczyta
- P. BouthemyPBP. Bouthemy
- O. Le MeurOMO. Le Meur
Preprint
Abstract
In this paper, we are concerned with the detection of progressive dynamic saliency from video sequences. More precisely, we are interested in saliency related to motion and likely to appear progressively over time. It can be relevant to trigger alarms, to dedicate additional processing or to detect specific events. Trajectories represent the best way to support progressive dynamic saliency detection. Accordingly, we will talk about trajectory saliency. A trajectory will be qualified as salient if it deviates from normal trajectories that share a common motion pattern related to a given context. First, we need a compact while discriminative representation of trajectories. We adopt a (nearly) unsupervised learning-based approach. The latent code estimated by a recurrent auto-encoder provides the desired representation. In addition, we enforce consistency for normal (similar) trajectories through the auto-encoder loss function. The distance of the trajectory code to a prototype code accounting for normality is the means to detect salient trajectories. We validate our trajectory saliency detection method on synthetic and real trajectory datasets, and highlight the contributions of its different components. We show that our method outperforms existing methods on several scenarios drawn from the publicly available dataset of pedestrian trajectories acquired in a railway station (Alahi 2014).Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy dataApplied Energy, 2018
- Classifying spatial trajectories using representation learningInternational Journal of Data Science and Analytics, 2016
- Contrast Based Hierarchical Spatial-Temporal Saliency for Video2016
- Consistent Video Saliency Using Local Gradient Flow Optimization and Global RefinementIEEE Transactions on Image Processing, 2015
- Superpixel-Based Spatiotemporal Saliency DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Video Saliency Map Detection by Dominant Camera Motion RemovalIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Spatiotemporal Saliency Detection Using Textural Contrast and Its ApplicationsIEEE Transactions on Circuits and Systems for Video Technology, 2013
- Forecasting with Recurrent Neural Networks: 12 Tricks2012
- A Statistical Video Content Recognition Method Using Invariant Features on Object TrajectoriesIEEE Transactions on Circuits and Systems for Video Technology, 2008
- Trajectory-Based Anomalous Event DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2008