Abstract
Cylindrical panorama stitching is able to generate high resolution images of a scene with a wide field-of-view (FOV), making it a useful scene representation for applications like environmental sensing and robot localization. Traditional image stitching methods based on hand-crafted features are effective for constructing a cylindrical panorama from a sequence of images in the case when there are sufficient reliable features in the scene. However, these methods are unable to handle low-texture environments where no reliable feature correspondence can be established. This paper proposes a novel two-step image alignment method based on deep learning and iterative optimization to address the above issue. In particular, a light-weight end-to-end trainable convolutional neural network (CNN) architecture called ShiftNet is proposed to estimate the initial shifts between images, which is further optimized in a sub-pixel refinement procedure based on a specified camera motion model. Extensive experiments on a synthetic dataset, rendered photo-realistic images, and real images were carried out to evaluate the performance of our proposed method. Both qualitative and quantitative experimental results demonstrate that cylindrical panorama stitching based on our proposed image alignment method leads to significant improvements over traditional feature based methods and recent deep learning based methods for challenging low-texture environments.
Highlights
Panoramic images are able to provide a wide field-of-view (FOV) of a scene, which is demanded in a number of applications, such as remote sensing [1,2], environment monitoring [3,4], robot localization [5,6], autonomous transportation [7,8], etc
This paper proposes a novel end-to-end trainable light-weight convolutional neural network (CNN) architecture called ShiftNet to estimate the initial shifts between images, which is further optimized in a sub-pixel refinement procedure based on a specified camera motion model
Shiftvggsim, and shiftvggsim_ht are all able to produce results hard to compare from the global view, we present in Figure 15, a comparison of zoomed-in views corresponding to panoramas generated with different methods for the three highlighted regions as shown in the last row of Figure 14
Summary
Panoramic images are able to provide a wide field-of-view (FOV) of a scene, which is demanded in a number of applications, such as remote sensing [1,2], environment monitoring [3,4], robot localization [5,6], autonomous transportation [7,8], etc. Extensive experiments on a synthetic dataset rendered photo-realistic images, and real images were tested to throughly evaluate the performance of the proposed method and comparative methods Both qualitative and quantitative experimental results for challenging low-texture environments demonstrated significant improvements over traditional feature based methods and recent deep learning based methods. This remainder of this paper is structured as follows.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
