计算机科学
人工智能
卷积神经网络
人群
特征(语言学)
特征提取
模式识别(心理学)
回归
干扰(通信)
计算机视觉
频道(广播)
数学
统计
计算机网络
哲学
语言学
计算机安全
作者
Luyang Wang,Baoqun Yin,Xiao Tang,Yun Li
标识
DOI:10.1016/j.neucom.2018.12.047
摘要
Crowd counting is a challenging vision task which aims to accurately estimate the crowd count from a single image. To this end, we propose a novel architecture called De-background Detail Convolutional Network (DDCN) to learn a mapping from the input image to the corresponding crowd density map. DDCN focuses on removing the interference of background from crowds and reducing the mapping range from input to output. Such design optimizes the learning process to a large extent. The proposed DDCN is composed of three components: a decomposer, a feature extraction CNN and a regression CNN. Specifically, the decomposer produces a detail layer by subtracting the background interference from the crowd image. Feature extraction CNN works for extracting high level features and regression CNN is used to estimate the density map. In addition, a weighted Euclidean loss is designed to calculate the Euclidean distances of the crowd and the background separately with different loss weights, which further improves the counting performance. Extensive experiments were conducted on three crowd counting datasets to validate the performance of DCNN. And experimental results demonstrate that DDCN achieves performance improvements compared with the state-of-the-art.
科研通智能强力驱动
Strongly Powered by AbleSci AI