Search Results

You are looking at 1 - 3 of 3 items for :

  • Author or Editor: Yang Cao x
  • Journal of Atmospheric and Oceanic Technology x
  • All content x
Clear All Modify Search
Wen Zhuo, Zhiguo Cao, and Yang Xiao

Abstract

Cloud classification of ground-based images is a challenging task. Recent research has focused on extracting discriminative image features, which are mainly divided into two categories: 1) choosing appropriate texture features and 2) constructing structure features. However, simply using texture or structure features separately may not produce a high performance for cloud classification. In this paper, an algorithm is proposed that can capture both texture and structure information from a color sky image. The algorithm comprises three main stages. First, a preprocessing color census transform (CCT) is applied. The CCT contains two steps: converting red, green, and blue (RGB) values to opponent color space and applying census transform to each component. The CCT can capture texture and local structure information. Second, a novel automatic block assignment method is proposed that can capture global rough structure information. A histogram and image statistics are computed in every block and are concatenated to form a feature vector. Third, the feature vector is fed into a trained support vector machine (SVM) classifier to obtain the cloud type. The results show that this approach outperforms other existing cloud classification methods. In addition, several different color spaces were tested and the results show that the opponent color space is most suitable for cloud classification. Another comparison experiment on classifiers shows that the SVM classifier is more accurate than the k–nearest neighbor (k-NN) and neural networks classifiers.

Full access
Yang Xiao, Zhiguo Cao, Wen Zhuo, Liang Ye, and Lei Zhu

Abstract

In this paper, a novel Multiview CLOUD (mCLOUD) visual feature extraction mechanism is proposed for the task of categorizing clouds based on ground-based images. To completely characterize the different types of clouds, mCLOUD first extracts the raw visual descriptors from the views of texture, structure, and color simultaneously, in a densely sampled way—specifically, the scale invariant feature transform (SIFT), the census transform histogram (CENTRIST), and the statistical color features are extracted, respectively. To obtain a more descriptive cloud representation, the feature encoding of the raw descriptors is realized by using the Fisher vector. This is followed by the feature aggregation procedure. A linear support vector machine (SVM) is employed as the classifier to yield the final cloud image categorization result. The experiments on a challenging cloud dataset termed the six-class Huazhong University of Science and Technology (HUST) cloud demonstrate that mCLOUD consistently outperforms the state-of-the-art cloud classification approaches by large margins (at least 6.9%) under all the different experimental settings. It has also been verified that, compared to the single view, the multiview cloud representation generally enhances the performance.

Full access
Chang Cao, Yichen Yang, Yang Lu, Natalie Schultze, Pingyue Gu, Qi Zhou, Jiaping Xu, and Xuhui Lee

Abstract

Heat stress caused by high air temperature and high humidity is a serious health concern for urban residents. Mobile measurement of these two parameters can complement weather station observations because of its ability to capture data at fine spatial scales and in places where people live and work. In this paper, we describe a smart temperature and humidity sensor (Smart-T) for use on bicycles to characterize intracity variations in human thermal conditions. The sensor has several key characteristics of internet of things (IoT) technology, including lightweight, low cost, low power consumption, ability to communicate and geolocate the data (via the cyclist’s smartphone), and the potential to be deployed in large quantities. The sensor has a reproducibility of 0.03°–0.05°C for temperature and of 0.18%–0.33% for relative humidity (one standard deviation of variation among multiple units). The time constant with a complete radiation shelter and moving at a normal cycling speed is 9.7 and 18.5 s for temperature and humidity, respectively, corresponding to a spatial resolution of 40 and 70 m. Measurements were made with the sensor on street transects in Nanjing, China. Results show that increasing vegetation fraction causes reduction in both air temperature and absolute humidity and that increasing impervious surface fraction has the opposite effect.

Restricted access