THE STUDY OF ACTIVATION FUNCTIONS IN DEEP LEARNING FOR PEDESTRIAN DETECTION AND TRACKING

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Favorskaya, M. N.^1¹ 

[1] Reshetnev Siberian State University of Science and Technology, Institute of Informatics and Telecommunications, 31, Krasnoyarsky Rabochy ave., Krasnoyarsk, 660037 Russian Federation^1

关键词: Deep Learning;    Activation Function;    Pedestrian Detection;    Feature Extraction;    Pedestrian Tracking;   

DOI  :  10.5194/isprs-archives-XLII-2-W12-53-2019

学科分类：地球科学(综合)

来源: Copernicus Publications

【 摘 要 】

Pedestrian detection and tracking remains a highlight research topic due to its paramount importance in the fields of video surveillance, human-machine interaction, and tracking analysis. At present time, pedestrian detection is still an open problem because of many challenges of image representation in the outdoor and indoor scenes. In recent years, deep learning, in particular Convolutional Neural Networks (CNNs) became the state-of-the-art in terms of accuracy in many computer vision tasks. The unsupervised learning of CNNs is still an open issue. In this paper, we study a matter of feature extraction using a special activation function. Most of CNNs share the same architecture, when each convolutional layer is followed by a nonlinear activation layer. The activation function Rectified Linear Unit (ReLU) is the most widely used as a fast alternative to sigmoid function. We propose a bounded randomized leaky ReLU working in such manner that the angle of linear part with the highest input values is tuned during learning stage, and this linear part can be directed not only upward but also downward using a variable bias for its starting point. The bounded randomized leaky ReLU was tested on Caltech Pedestrian Dataset with promising results.

【 授权许可】

CC BY