Mr. Hai-Bin Ai Profile

Hai-Bin Ai

at Chinese Academy of Surveying and Mapping

SPIE Involvement:

Author

Publications (5)

SPIE Journal Paper | 21 July 2022

Matching wide-baseline stereo images with weak texture using the perspective invariant local feature transformer

Guobiao Yao, Pengfei Huang, Haibin Ai, Chuanhui Zhang, Jin Zhang, Chengcheng Zhang, Fuyao Wang

JARS, Vol. 16, Issue 03, 036502, (July 2022) https://doi.org/10.1117/12.10.1117/1.JRS.16.036502

KEYWORDS: Transformers, Computer programming, Feature extraction, Remote sensing, Unmanned aerial vehicles, Satellites, Satellite imaging, Neural networks, Earth observing sensors, Convolution

Read Abstract +

The development of remote sensing sensor techniques allows us to now readily capture many types of indoor and outdoor scene images, which often include many weak texture regions with notable geometric distortions. Obtaining qualified matches from these difficult stereo images using existing methods is challenging. The recent achievements of deep-learning models have shown that the convolutional neural network (CNN) is adept at the image matching task. However, in practical applications, the following challenges remain: first, it is difficult to detect features in the weak texture regions of an image, and existing CNNs fail to extract discriminative image information from the quantized features of weak texture; second, as a result of the complex distortion across wide-baseline stereo images, it is difficult to match feature primitives detected in the image pair. To solve these problems, we propose the perspective invariant local feature transformer (PILFT) algorithm. Our method includes four main steps. (1) The affine scale-invariant feature transform is proposed to automatically extract the corresponding features from images, and then the perspective of the matched image is corrected to eliminate as much geometric deformation as possible. (2) The residual network is used to extract potential features from stereo images to obtain coarse and fine feature maps at different scales. (3) Using an attention mechanism, location and context information are added to the coarse level features, which are predicted by a dual-softmax function layer. (4) The features are precisely predicted on the fine feature map using the coarse reference, and the final matching results are determined by calculating the matching probability. A large number of experiments on wide-baseline weak texture images demonstrate that the proposed method has advantages over the existing algorithms in the number of matches, correct match rate, and matching accuracy. The pseudocodes of PILFT are available at https://github.com/KiltAB/PILFT.

SPIE Journal Paper | 10 July 2014

Robust perspective invariant quasidense matching across large oblique images

Guo-Biao Yao, Ka-Zhong Deng, Li Zhang, Hai-Bin Ai

JEI, Vol. 23, Issue 04, 043005, (July 2014) https://doi.org/10.1117/12.10.1117/1.JEI.23.4.043005

KEYWORDS: Affine motion model, 3D image processing, Reconstruction algorithms, 3D image reconstruction, Feature extraction, Evolutionary algorithms, Image processing, Roads, Cameras, 3D modeling

Read Abstract +

Proceedings Article | 5 December 2011 Paper

Automatic mosaicking method for large block of orthophotos

Haibin Ai, Li Zhang, Lin Wang

Proceedings Volume 8005, 800504 (2011) https://doi.org/10.1117/12.899370

KEYWORDS: Orthophoto maps, Image processing, Unmanned aerial vehicles, Roads, Evolutionary algorithms, Detection and tracking algorithms, Image segmentation, Photography, Medical imaging, Computer programming

Read Abstract +

Proceedings Article | 30 October 2009 Paper

A distributed parallel processing method for ortho-rectifying satellite imagery

Haibin Ai, Yinxia Yu

Proceedings Volume 7497, 749709 (2009) https://doi.org/10.1117/12.832462

KEYWORDS: Computing systems, Parallel processing, Satellites, Earth observing sensors, Distributed computing, Satellite imaging, Data processing, Image resolution, Digital photography, Photogrammetry

Read Abstract +

Proceedings Article | 14 November 2007 Paper

Parallel processing for fusing SPOT5 satellite images

Haibin Ai, Yong Zhang

Proceedings Volume 6790, 67900X (2007) https://doi.org/10.1117/12.748064

KEYWORDS: Image fusion, Image filtering, Multispectral imaging, Parallel processing, Image processing, Linear filtering, Earth observing sensors, Satellites, Satellite imaging, RGB color model

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years