chonghuai yao

Prof. chonghuai yao


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
ZHZemin Han
Zemin Han
yuanyong dianyuanyong dian
yuanyong dian
HXHao Xia
Hao Xia
JZJing-Jing Zhou
Jing-Jing Zhou
YJYongfeng Jian
Yongfeng Jian
YLYuan Li
Yuan Li
Land cover is an important variable of the terrestrial ecosystem that provides information for natural resources management, urban sprawl detection, and environment research. To classify land cover with high-spatial-resolution multispectral remote sensing imagery is a difficult problem due to heterogeneous spectral values of the same object on the ground. Fully convolutional networks (FCNs) are a state-of-the-art method that has been increasingly used in image segmentation and classification. However, a systematic quantitative comparison of FCNs on high-spatial-multispectral remote imagery was not yet performed. In this paper, we adopted the three FCNs (FCN-8s, Segnet, and Unet) for Gaofen-2 (GF2) satellite imagery classification. Two scenes of GF2 with a total of 3329 polygon samples were used in the study area and a systematic quantitative comparison of FCNs was conducted with red, green, blue (RGB) and RGB+near infrared (NIR) inputs for GF2 satellite imagery. The results showed that: (1) The FCN methods perform well in land cover classification with GF2 imagery, and yet, different FCNs architectures exhibited different results in mapping accuracy. The FCN-8s model performed best among the Segnet and Unet architectures due to the multiscale feature channels in the upsampling stage. Averaged across the models, the overall accuracy (OA) and Kappa coefficient (Kappa) were 5% and 0.06 higher, respectively, in FCN-8s when compared with the other two models. (2) High-spatial-resolution remote sensing imagery with RGB+NIR bands performed better than RGB input at mapping land cover, and yet the advantage was limited; the OA and Kappa only increased an average of 0.4% and 0.01 in the RGB+NIR bands. (3) The GF2 imagery provided an encouraging result in estimating land cover based on the FCN-8s method, which can be exploited for large-scale land cover mapping in the future.

5 April 2020 in Forests
Verified
Journal Article
Open access
PDF file
JZJing-Jing Zhou
Jing-Jing Zhou
yuanyong dianyuanyong dian
yuanyong dian
XWXiong Wang
Xiong Wang
CYchonghuai yao
chonghuai yao
YJYongfeng Jian
Yongfeng Jian
PWPengcheng Wang
Pengcheng Wang
Canopy cover is an important vegetation attribute used for many environmental applications such as defining management objectives, thinning and ecological modeling. However, the estimation of canopy cover from high spatial resolution imagery is still a difficult task due to limited spectral information and the heterogeneous pixel values of the same canopy. In this paper, we compared the capacity of two high spatial resolution sensors (SPOT6 and GF2) using three ensemble learning models (Adaptive Boosting (AdaBoost), Gradient Boosting (GDBoost), and random forest (RF)), to estimate canopy cover (CC) in a Chinese northern subtropics forest. Canopy cover across 97 plots was measured across 41 needle forest plots, 24 broadleaf forest plots, and 32 mixed forest plots. Results showed that (1) the textural features performed more importantly than spectral variables according to the number of variables in the top ten predictors in estimating canopy cover (CC) in both SPOT6 and GF2. Moreover, the vegetation indices in spectral variables had a lower relative importance value than the band reflectance variables. (2) GF2 imagery outperformed SPOT6 imagery in estimating CC when using the ensemble learning model in our data. On average across the models, the R2 was almost 0.08 higher for GF2 over SPOT6. Likewise, the average RMSE and average MAE were 0.002 and 0.01 lower in GF2 than in SPOT6. (3) The ensemble learning model showed good results in estimating CC, yet the different models performed a little differently in the results. Additionally, the GDBoost model performed the best of all the ensemble learning models with R2 = 0.92, root mean square error (RMSE) = 0.001 and mean absolute error (MAE) = 0.022.

12 October 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YZYuying Zheng
Yuying Zheng
yuanyong dianyuanyong dian
yuanyong dian
ZGZhiqiang Guo
Zhiqiang Guo
CYchonghuai yao
chonghuai yao
XWXuefei Wu
Xuefei Wu
Mapping functional zones for rural landscapes is the foundational work for rural land use planning and plays a very important role in the economic development and resource management utilization of rural areas. However, the traditional manual delineation of functional zone boundaries empirically in rural areas is labor-intensive, time-consuming, and lacks the consideration of spatial landscape patterns. The emergence of high-resolution remote sensing imagery and image segmentation has facilitated the analysis of ground landscape information and patterns, but there is still a lack of functional zone boundary mapping methods applicable to rural landscapes. To address this, we propose a functional zoning method called multiscale merging of landscape contextual and shape characteristics with heterogeneity indices (M2LHI) for mapping geographic boundaries for rural landscapes based on high-resolution remote sensing imagery. The landscape contextual features were first constructed based on the geospatial distances of landscape types, and then, the dominance index and shape index were introduced to quantify the landscape heterogeneity by object-oriented image analysis. Then, the automated merging of adjacent landscape units based on the thresholds of the landscape heterogeneity indices was performed to map the initial zones. The final rural functional zones were defined based on the main function in the zone. The study was carried out in three typical rural landscapes (hilly countryside, flat countryside, and grassland countryside) located in Fujian, Xinjiang, and Inner Mongolia, China, and the freely available Gaofen-2 (GF-2) satellite imagery was used as the data source. We compared the boundaries of mapped functional zones and reference functional zones, and the matching and inclusion ratios of the final functional zones mapped in each case were bigger than 78%, indicating that the M2LHI method has a high ability to map the functional spatial patterns. The overall accuracies of mapping functional zones with different functions were 95.9%, 89.0%, and 92.1% for the respective cases. The results demonstrated that the M2LHI method effectively quantifies landscape heterogeneity and accurately delineates functional zones with different landscape patterns. It can provide a scientific basis for rural planning and management and efficiently draw reasonable geographic boundaries for rural functional zones.