papers AI Learner
The Github is limit! Click to go to the new site.

DENet: A Universal Network for Counting Crowd with Varying Densities and Scales

2019-04-17
Lei Liu, Jie Jiang, Wenjing Jia, Saeed Amirgholipour, Michelle Zeibots, Xiangjian He

Abstract

Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem. In this paper, we propose a simple but an efficient and effective network, named DENet, which is composed of two components, i.e., a detection network (DNet) and an encoder-decoder estimation network (ENet). We first run DNet on an input image to detect and count individuals who can be segmented clearly. Then, ENet is utilized to estimate the density maps of the remaining areas, where the numbers of individuals cannot be detected. We propose a modified Xception as an encoder for feature extraction and a combination of dilated convolution and transposed convolution as a decoder. In the ShanghaiTech Part A, UCF and WorldExpo’10 datasets, our DENet achieves lower Mean Absolute Error (MAE) than those of the state-of-the-art methods.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08056

PDF

http://arxiv.org/pdf/1904.08056


Similar Posts

Comments