In remote sensing images, there was a problem that similar segmentation targets often had different sizes. So the BiasCosionNet was proposed to solve the above problems from two aspects: one was to take the features generated by the input image when it changed between different scales as the main body; the other was to ensure that segmentation targets with different sizes had same scale features by breaking through the upper sampling limit. Experiments show that the BiasCosionNet realizes the semantic segmentation task only by relying on features generated when scales change. The mIoU and the mBF of the BiasCosionNet are better than those of existing classical networks by more than 0.2%. And the BiasCosionNet has more accurate segmentation ability for similar targets of different sizes.
RottensteinerF, SohnG, JungJ, et al. The ISPRS benchmark on urban object classification and 3D building reconstruction[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012, 13(1): 193-298.
[2]
VolpiM, FerrariV. Semantic segmentation of urban scenes by learning local class interactions[C]∥The IEEE Conference on Computer Vision and Pattern Recognition,Boston, MA, USA, 2015, 1: 1-9.
[3]
KampffmeyerM, SalbergA, JenssenR. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks[C]∥The IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2016: 680-688.
[4]
KemkerR, SalvaggioC, KananC. Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 145(11): 60-77.
[5]
DengZ, SunH, ZhouS, et al. Multi-scale object detection in remote sensing imagery with convolutional neural networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 145(1): 3-22.
[6]
XiaG S, BaiX, DingJ, et al. DOTA: a large-scale dataset for object detection in aerial images[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3974-3983.
[7]
ChenL, PapandreouG, KokkinosI, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[8]
ChenL, ZhuY, PapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]∥Proceedings of the European Conference on Computer Vision, Munich, Germany, 2018: 801-818.
[9]
YangM, YuK, ZhangC, et al. DenseASPP for semantic segmentation in street scenes[C]∥The IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3684-3692.
[10]
XiaoP, FengX, ZhaoS, et al. Segmentation of high-resolution remotely sensed imagery based on phase congruency[J]. Acta Geodaetica et Cartographica Sinica, 2007, 36(2): 146-151.
[11]
LiS, WuJ J, DiP. Panoramic sea-sky-line detection based on improved active contour model[J]. Acta Optica Sinica, 2016, 36(11): 189-196.
[12]
JunW, WangY, YueC, et al. Speckle reduction of ultrasound images with anisotropic diffusion based on homogeneous region automatic selection[J]. Optics and Precision Engineering, 2014, 22(5): 1312-1321.
YangA, BaiY, LiuH, et al. Application of SVM and its improved model in image segmentation[J]. Mobile Networks and Applications, 2021, 21(8): 1-11.
[15]
HintonG, SalakhutdinovR. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313: 504-507.
[16]
ZengN, ZhangH, SongB, et al. Facial expression recognition via learning deep sparse autoencoders[J]. Neurocomputing, 2018, 273(17): 643-649.
[17]
XuX, PanJ, ZhangY, et al. Motion blur kernel estimation via deep learning[J]. IEEE Transactions on Image Processing, 2018, 27(1): 194-205.
[18]
ShaoH, JiangH, ZhangH, et al. Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing[J]. Mechanical Systems and Signal Processing, 2018, 100(1): 743-765.
[19]
CiresanD, GiustiA, GambardellaL, et al. Deep neural networks segment neuronal membranes in electron microscopy images[J]. Advances in Neural Information Processing Systems, 2012, 25(1): 2843-2851.
[20]
FarabetC, CouprieC, NajmanL, et al. Learning hierarchical features for scene labeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(8): 1915-1929.
[21]
GuptaS, GirshickR, ArbeláezP, et al. Learning rich features from RGB-D images for object detection and segmentation[J]. Springer International Publishing, 2014(1): 345-360.
[22]
HariharanB, ArbeláezP, GirshickR, et al. Simultaneous detection and segmentation[C]∥Proceedings of the European Conference on Computer Vision,Zurich, Switzerland, 2014: 297-312.
[23]
ShuaiB, ZuoZ, WangG, et al. DAG-Recurrent neural networks for scene labeling[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 3620-3629.
[24]
LongJ, ShelhamerE, DarrellT. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[25]
ChenC, PapandreouG, KokkinosI, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. Computer Science, 2014, 1(4): 357-361.
[26]
ZhaoH, ShiJ, QiX, et al. Pyramid scene parsing network[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 6230-6239.
[27]
ChenC, PapandreouG, KokkinosI, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[28]
HeK, ZhangX, RenS, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[29]
RonnebergerO, FischerP, BroxT. U-Net: convolutional networks for biomedical image segmentation[J]. Medical Image Computing and Computer-Assisted Intervention, 2015(1): 234-241.
[30]
BadrinarayananV, KendallA, CipollaR. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(12): 2481-2495.
[31]
LinG, MilanA, ShenC, et al. Refinenet: multi-path refinement networks for high-resolution semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2020, 45(2): 1228-1242.
[32]
CholletF. Xception: deep learning with depthwise separable convolutions[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 1251-1258.
[33]
SunK, XiaoB, LiuD, et al. Deep high-resolution representation learning for human pose estimation[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 1-12.
[34]
ZhangC, SargentI, PanX, et al. An object-based convolutional neural network (ocnn) for urban land use classifification[J]. Remote Sensing of Environment, 2018, 216(1): 57-70.
[35]
BoH, BeiZ, SongY. Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery[J]. Remote Sensing of Environment, 2018, 214(1):73-86.
[36]
ZhangC, SargentI, XinP, et al. Joint deep learning for land cover and land use classification[J]. Remote Sensing of Environment, 2019, 221(1): 173-187.
[37]
DickensonM, GueguenL. Rotated rectangles for symbolized building footprint extraction[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 225-228.
[38]
JiS P, WeiS Q, LuM, et al. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1): 574-586.
[39]
XuY Y, WuL, XieZ, et al. Building extraction in very high resolution remote sensing imagery using deep learning and guided filters[J]. Remote Sensing, 2018, 10(1): 144-162.
[40]
YuanJ. Learning building extraction in aerial scenes with convolutional networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018, 40(11): 2793-2798.
ZhuBing, LiZi-wei, LiQi. Building segmentation method of remote sensing image based on improved SegNet[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(1): 248-254.
[43]
BastaniF, HeS, AbbarS, et al. Roadtracer: automatic extraction of road networks from aerial images[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 4720-4728.
[44]
BatraA, SinghS, PangG, et al. Improved road connectivity by joint learning of orientation and segmentation[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 10385-10393.
[45]
YiF, TeR, ZhaoY, et al. EUNetMTL: multitask joint learning for road extraction from high-resolution remote sensing images[J]. Remote Sensing Letters, 2022, 13(3): 258-268.
ChenHua, GuoWei, YanJing-wen, et al. A new deep learning method for roads recognition from SAR images[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(5): 1778-1787.
[48]
MouL, ZhuX X. Vehicle instance segmentation from aerial image and video using a multitask learning residual fully convolutional network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(11): 6699-6711.