Deep background subtraction of thermal and visible imagery for redestrian detection in videos

Yan, Yijun and Zhao, Huimin and Kao, Fu-Jen and Vargas, Valentin Masero and Zhao, Sophia and Ren, Jinchang (2018) Deep background subtraction of thermal and visible imagery for redestrian detection in videos. In: 9th International Conference on Brain Inspired Cognitive Systems, 2018-07-07 - 2018-07-08.

[img]
Preview
Text (Yan-etal-BICS-2018-Deep-background-subtraction-of-thermal-and-visible-imagery)
Yan_etal_BICS_2018_Deep_background_subtraction_of_thermal_and_visible_imagery.pdf
Accepted Author Manuscript

Download (630kB)| Preview

    Abstract

    In this paper, we introduce an efficient framework to subtract the background from both visible and thermal imagery for pedestrians’ detection in the urban scene. We use a deep neural network (DNN) to train the background subtraction model. For the training of the DNN, we first generate an initial background map and then employ randomly 5% video frames, background map, and manually segmented ground truth. Then we apply a cognition-based post-processing to further smooth the foreground detection result. We evaluate our method against our previous work and 11 recently widely cited method on three challenge video series selected from a publicly available color-thermal benchmark dataset OCTBVS. Promising results have been shown that the proposed DNN-based approach can successfully detect the pedestrians with good shape in most scenes regardless of illuminate changes and occlusion problem.