標題: IUML: INCEPTION U-NET BASED MULTI-TASK LEARNING FOR DENSITY LEVEL CLASSIFICATION AND CROWD DENSITY ESTIMATION
作者: Huynh, Van-Su
Vu-Hoang Tran
Huang, Ching-Chun
交大名義發表
National Chiao Tung University
關鍵字: Crowd counting;Deep Learning;Multi-task learning;Inception module;Density level classification
公開日期: 1-Jan-2019
摘要: Nowadays, image-based people counting is an essential technique for public safety management. However, this work is still extremely challenging due to many kinds of scale issues caused by different congested scenes, different viewing points, different image sizes, and different density levels. In this paper, we proposed a CNNs-based framework for people counting and crowd density map estimation with the consideration of the scale problems. First, we introduced an encoder-decoder architecture, which is composed of Inception modules to learn the multi-scale feature representations. Besides, to be adaptive to image resolution, a multi-loss setting over different resolutions of density maps is designed for network training. Second, we apply multi-task learning to learn the joint features for the density map estimation task and the density level classification task. This helps to enhance the feature generality under different scenes. Finally, by adopting the U-net architecture, the encoder and decoder features are then fused to generate high-resolution density maps. The efficacy of the proposed method is evaluated in the extensive experiments by quantifying the counting performance through multiple evaluation criteria.
URI: http://hdl.handle.net/11536/154027
ISBN: 978-1-7281-4569-3
ISSN: 1062-922X
期刊: 2019 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC)
起始頁: 3019
結束頁: 3024
Appears in Collections:Conferences Paper