Most of the existing methods for indoor point cloud semantic segmentation employ sophisticated structures to obtain local features, leading to high complexity. In addition, the current prevailing networks focus less on the extraction of global features of point clouds, which may damage the performance of the networks. Moreover, there are few networks that achieve the balance between accuracy and efficiency. To solve the above problems, we propose an improved network architecture based on anisotropic separable set abstraction network. It is more accurate and more efficient. First, we introduce an improved ASSA module to comprehensively consider the influence of the distance between the neighbor and the centroid on the neighborhood features, to better obtain the local features of the point clouds. Later, we design an inverse residual module, which optimizes the backbone network by scaling the receptive field to improve the extraction ability of the global features of the point clouds. Then we use a mixed pooling method to solve the disorder of point clouds and fuse both the coarse-grained and fine-grained features. Evaluated on the stanford large-scale 3D indoor spaces dataset, the experiment results illustrate that our method not only improves the extraction of global features and local features effectively, but also achieves an advanced performance among several mainstream point cloud semantic segmentation methods. Overall accuracy is 89.7%, mean class accuracy is 75.6%, mean intersection over union is 69.5%, and floating point operations are 15.9G.
A fiber-based non-contact scheme of the time-domain diffuse fluorescence yield and lifetime tomography is described
that combines the time-correlated single photon counting technique for high-sensitive, time-resolved detection and
CT-analogous configuration for high throughput data collection. A pilot validation of the methodology is performed for
two-dimensional scenarios using simulated and experimental data. The results demonstrated the potential of the proposed
scheme in improving the image quality.
Traditionally, volume based finite element method (FEM) or finite difference method (FDM) are applied to the forward
problem of the time-domain diffuse fluorescence tomography (DFT), this paper presents a new numerical method for
solving the problem: the boundary element method (BEM). Using BEM forward solver is explored as an alternative to
the FEM or FDM solution methodology for the elliptic equations used to model the generation and transport of
fluorescent light in highly scattering media. In contrast to the FEM or FDM, the boundary integral method requires only
representation of the surface meshes, thus requires many fewer nodes and elements than the FEM and FDM. By using
BEM forward solver for time-domain DFT, we can simultaneously reconstruct both fluorescent yield and lifetime images.
The results have demonstrated that the BEM is suitable for solving the forward problem of time-domain DFT.
This paper presents an improved fractional divider used in 1.8~2GHz fractional-N frequency synthesizers. A new clock
setting for delta-sigma modulator (DSM) is proposed to prevent the potential problems of traditional fractional dividers:
the DSM output would be wrongly loaded and the action of DSM circuit may affect the phase-detection of
phase-frequency-detector (PFD). Simulation result shows the effectiveness of this improvement.
Proceedings Volume Editor (1)
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.