Semantic segmentation of remote sensing data using Gaussian processes and higher-order CRFs. Liu, Y., Monteiro, S. T., & Saber, E. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2017. abstract bibtex Automatic recognition for complex scenes from aerial images and other sensors data (e.g. LiDAR) has become a central interest in the remote sensing community. In this paper, we proposed a novel framework that utilizes higher order CRFs(HCRFs) to capture the spatial context for the RGB aerial images along with their co-registered LiDAR point clouds(DSMs). Our proposed CRFs framework exploits the spatial context in two levels. The first level encourages harmonic label co-existence within one segment generated by an unsupervised super-pixel algorithm. The second level takes into account the local object co-occurrence among neighboring segments. We then show that how to apply the move making graph cuts algorithm to perform effective inference for our proposed CRFs framework. Based on the experiments on a set of challenging images, our proposed higher order CRFs framework generated state-of-the-art semantic segmentation results for the aerial images.
@InProceedings{Liu2017a,
author = {Liu, Yansong and Monteiro, Sildomar T. and Saber, Eli},
title = {{Semantic segmentation of remote sensing data using Gaussian processes and higher-order CRFs}},
booktitle = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
year = {2017},
abstract = {Automatic recognition for complex scenes from aerial images and other sensors data (e.g. LiDAR) has become a central interest in the remote sensing community. In this paper, we proposed a novel framework that utilizes higher order CRFs(HCRFs) to capture the spatial context for the RGB aerial images along with their co-registered LiDAR point clouds(DSMs). Our proposed CRFs framework exploits the spatial context in two levels. The first level encourages harmonic label co-existence within one segment generated by an unsupervised super-pixel algorithm. The second level takes into account the local object co-occurrence among neighboring segments. We then show that how to apply the move making graph cuts algorithm to perform effective inference for our proposed CRFs framework. Based on the experiments on a set of challenging images, our proposed higher order CRFs framework generated state-of-the-art semantic segmentation results for the aerial images.},
}
Downloads: 0
{"_id":"qraRkkHbi3jj82HTg","bibbaseid":"liu-monteiro-saber-semanticsegmentationofremotesensingdatausinggaussianprocessesandhigherordercrfs-2017","author_short":["Liu, Y.","Monteiro, S. T.","Saber, E."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["Yansong"],"suffixes":[]},{"propositions":[],"lastnames":["Monteiro"],"firstnames":["Sildomar","T."],"suffixes":[]},{"propositions":[],"lastnames":["Saber"],"firstnames":["Eli"],"suffixes":[]}],"title":"Semantic segmentation of remote sensing data using Gaussian processes and higher-order CRFs","booktitle":"IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","year":"2017","abstract":"Automatic recognition for complex scenes from aerial images and other sensors data (e.g. LiDAR) has become a central interest in the remote sensing community. In this paper, we proposed a novel framework that utilizes higher order CRFs(HCRFs) to capture the spatial context for the RGB aerial images along with their co-registered LiDAR point clouds(DSMs). Our proposed CRFs framework exploits the spatial context in two levels. The first level encourages harmonic label co-existence within one segment generated by an unsupervised super-pixel algorithm. The second level takes into account the local object co-occurrence among neighboring segments. We then show that how to apply the move making graph cuts algorithm to perform effective inference for our proposed CRFs framework. Based on the experiments on a set of challenging images, our proposed higher order CRFs framework generated state-of-the-art semantic segmentation results for the aerial images.","bibtex":"@InProceedings{Liu2017a,\n author = {Liu, Yansong and Monteiro, Sildomar T. and Saber, Eli},\n title = {{Semantic segmentation of remote sensing data using Gaussian processes and higher-order CRFs}},\n booktitle = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},\n year = {2017},\n abstract = {Automatic recognition for complex scenes from aerial images and other sensors data (e.g. LiDAR) has become a central interest in the remote sensing community. In this paper, we proposed a novel framework that utilizes higher order CRFs(HCRFs) to capture the spatial context for the RGB aerial images along with their co-registered LiDAR point clouds(DSMs). Our proposed CRFs framework exploits the spatial context in two levels. The first level encourages harmonic label co-existence within one segment generated by an unsupervised super-pixel algorithm. The second level takes into account the local object co-occurrence among neighboring segments. We then show that how to apply the move making graph cuts algorithm to perform effective inference for our proposed CRFs framework. Based on the experiments on a set of challenging images, our proposed higher order CRFs framework generated state-of-the-art semantic segmentation results for the aerial images.},\n}\n\n","author_short":["Liu, Y.","Monteiro, S. T.","Saber, E."],"key":"Liu2017a","id":"Liu2017a","bibbaseid":"liu-monteiro-saber-semanticsegmentationofremotesensingdatausinggaussianprocessesandhigherordercrfs-2017","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/sildomar/sildomar.github.io/master/files/mypapers.bib","dataSources":["9pKPXHaxkKcJ5Habx"],"keywords":[],"search_terms":["semantic","segmentation","remote","sensing","data","using","gaussian","processes","higher","order","crfs","liu","monteiro","saber"],"title":"Semantic segmentation of remote sensing data using Gaussian processes and higher-order CRFs","year":2017}