On Estimating Air Pollution from Photos Using Convolutional Neural Network
On Estimating Air Pollution from Photos Using Convolutional Neural Network
复制标题
DOI：
10.1145/2964284.2967230
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Chao Zhang;Junchi Yan;Changsheng Li;Xiaoguang Rui;Liang Liu;R. Bie
中科院分区：
文献类型：
--
作者：
Chao Zhang;Junchi Yan;Changsheng Li;Xiaoguang Rui;Liang Liu;R. Bie
空气污染已经引起了人们的强烈关注，特别是在中国和印度等发展中国家。与基于传感器或社交网络等昂贵或不可靠的方法不同，基于照片的空气污染估计是一个很有前途的方向，但到目前为止，工作还很少。针对这一迫切问题，本文设计了一种有效的卷积神经网络来估计基于照片的空气质量。我们的方法由两个部分组成：第一，在网络的最后一层设计了一个负对数-对数序分类器，它可以提高模型的序判别能力。其次，作为修正线性单元（ReLU）的一种变体，开发了一种改进的激活函数用于基于照片的空气污染估计。该函数已被证明可以有效地缓解消失梯度问题。我们收集了一组户外照片，并将官方机构的污染水平作为地面事实。在真实数据集上进行的实验表明了该方法的有效性。
Air pollution has raised people's intensive concerns especially in developing countries such as China and India. Different from using expensive or unreliable methods like sensor-based or social network based one, photo based air pollution estimation is a promising direction, while little work has been done up to now. Focusing on this immediate problem, this paper devises an effective convolutional neural network to estimate air's quality based on photos. Our method is comprised of two ingredients: first a negative log-log ordinal classifier is devised in the last layer of the network, which can improve the ordinal discriminative ability of the model. Second, as a variant of the Rectified Linear Units (ReLU), a modified activation function is developed for photo based air pollution estimation. This function has been shown it can alleviate the vanishing gradient issue effectively. We collect a set of outdoor photos and associate the pollution levels from official agency as the ground truth. Empirical experiments are conducted on this real-world dataset which shows the capability of our method.