Analyzing sedentary behavior in life-logging images
Research output: Contribution to journal › Conference article › Research › peer-review
We describe a study that aims to understand physical activity and sedentary behavior in free-living settings. We employed a wearable camera to record 3 to 5 days of imaging data with 40 participants, resulting in over 360,000 images. These images were then fully annotated by experienced staff with a rigorous coding protocol. We designed a deep learning based classifier in which we adapted a model that was originally trained for ImageNet [1]. We then added a spatio-temporal pyramid to our deep learning based classifier. Our results show our proposed method performs better than the state-of-the-art visual classification methods on our dataset. For most of the labels our system achieves more than 90% average accuracy across different individuals for frequent labels and more than 80% average accuracy for rare labels.
Original language | English |
---|---|
Journal | 2014 IEEE International Conference on Image Processing, ICIP 2014 |
Pages (from-to) | 1011-1015 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 28 Jan 2014 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:
© 2014 IEEE.
- Deep Learning, Large Scale Image Analysis, Visual Classification, Wearable camera
Research areas
ID: 302043908