文献类型： 外文期刊
作者： Dong, Luan 1 ; Yan, Qin 1 ; Zheng, Fengling 3 ;
作者机构： 1.Hohai Univ, Coll Comp & Informat, Nanjing, Jiangsu, Peoples R China
2.Xinjiang Agr Univ, Coll Comp & Informat Engn, Urumqi, Peoples R China
3.Xinjiang Agr Univ, Coll Prataculturae & Environm Sci, Urumqi, Peoples R China
4.Xinjiang Acad Anim Sci, Grassland Res Inst, Urumqi, Peoples R China
关键词： Topographic maps; Graticule intersections; Object detection; Convolutional neural networks; Geometric calibration
期刊名称：MACHINE VISION AND APPLICATIONS （ 影响因子：2.012； 五年影响因子：1.975 ）
ISSN： 0932-8092
年卷期： 2019 年 30 卷 4 期
页码：
收录情况： SCI
摘要： Graticule intersections in topographic maps are usually considered to be suitable candidates for reference points in geometric calibration because the corresponding geographical information can be directly retrieved from the maps or derived from sheet numbers. Previous research on automatic corner point detection relies on the assumption that scanned maps are not rotated, which is rarely practical. To address this issue, a semantic segmentation approach for accurate graticule intersection localization is proposed in this paper. A fully convolutional network is utilized to provide pixel level information about the locations of specific rectangular objects at the corners of map frames by dense classification in regions of interest. The globally optimal segmentation of the foreground rotated object is obtained by the graph cuts technique. The bounding box of the rotated object is further retrieved with the minimum-area enclosing rectangle algorithm. Finally, the coordinates of graticule intersections are derived in accordance with the positions of the sliding windows and the relative locations of the vertices of the objects. The proposed method reduces the average localization error to 1.5 pixels, which is 32.4% lower than that of the baseline model. The standard deviation of localization error is 0.91 pixels, which aligns with an average of 52% improvements to the baseline model in the location variance metric.
- 相关文献
作者其他论文 更多>>
-
Infrared and visible image fusion algorithm based on spatial domain and image features
作者：Zhao, Liangjun;Zhang, Yun;Dong, Linlu;Zheng, Fengling;Zhao, Liangjun;Zhang, Yun;Dong, Linlu
关键词：
-
Monitoring and analysing grassland ecosystem service values in response to grassland area changes - an example from northwest China
作者：Sawut, Rukeya;Manlike, Asiya;Zheng, Fengling;Li, Xuesen;Abudukelimu, Rena;Sawut, Rukeya
关键词：driving factors; ecosystem services; ecosystem service values; ESV; grassland degradation; grid cell analysis; overgrazing; remote sensing; special autocorrelation
-
Comparative study of remote sensing estimation methods for grassland fractional vegetation coverage - a grassland case study performed in Ili prefecture, Xinjiang, China
作者：Zhang, Wenbo;Yang, Xiuchun;Jin, Yunxiang;Guo, Jian;Shen, Ge;Zhang, Yujing;Xu, Bin;Manlike, Asiya;Zheng, Fengling;Xu, Bin
关键词：
-
Corner points localization in electronic topographic maps with deep neural networks
作者：Dong, Luan;Chang, Hongxia;Yan, Qin;Dong, Luan;Zheng, Fengling;Zheng, Fengling
关键词：Topographic map;Computer vision;Deep neural networks;Object detection;Geometric calibration
-
MMFuse: A multi-scale infrared and visible images fusion algorithm based on morphological reconstruction and membership filtering
作者：Zhao, Liangjun;Yang, Hao;Zheng, Liping;Dong, Linlu;Asiya, Manlike;Zheng, Fengling;Zhao, Liangjun
关键词：Image fusion; Multi-scale transformation; Fuzzy c-means clustering(FCM); Morphological reconstruction (MR)
-
Estimation of chlorophyll content in mountain steppe using in situ hyperspectral measurements
作者：Zheng, Fengling;An, Shazhou;Zheng, Fengling;Xu, Bin;Manlike, Asiya;Li, Chao;Xu, Bin;Jin, Yun-Xiang;Xiao, Pengfeng;Zhang, Xueliang;Feng, Xuezhi
关键词：Canopy spectral reflectance; chlorophyll content; hyperspectral vegetation indices; mountain steppe; red edge
