Human fall detection using segment-level CNN features and sparse dictionary learning
Paper in proceeding, 2017

This paper addresses issues in human fall detection from videos. Unlike using handcrafted features in the conventional machine learning, we extract features from Convolutional Neural Networks (CNNs) for human fall detection. Similar to many existing work using two stream inputs, we use a spatial CNN stream with raw image difference and a temporal CNN stream with optical flow as the inputs of CNN. Different from conventional two stream action recognition work, we exploit sparse representation with residual-based pooling on the CNN extracted features, for obtaining more discriminative feature codes. For characterizing the sequential information in video activity, we use the code vector from long-range dynamic feature representation by concatenating codes in segment-levels as the input to a SVM classifier. Experiments have been conducted on two public video databases for fall detection. Comparisons with six existing methods show the effectiveness of the proposed method.

E-healthcare

Deep learning

sparse dictionary learning

human fall detection

residual-based pooling

assisted living.

Convolutional Network

automatic feature learning

Author

Chenjie Ge

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Irene Yu-Hua Gu

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Jie Yang

IEEE International Workshop on Machine Learning for Signal Processing, MLSP

21610363 (ISSN) 21610371 (eISSN)

Vol. 2017-September 6-

Areas of Advance

Transport

Life Science Engineering (2010-2018)

Subject Categories

Human Computer Interaction

Signal Processing

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/MLSP.2017.8168185

More information

Latest update

7/12/2024