arXiv subjects

Yafei Song

Publications and source records attributed to Yafei Song.

22 records · Page 2Linked to original sources

arXiv2019

2D LiDAR Map Prediction via Estimating Motion Flow with GRU

It is a significant problem to predict the 2D LiDAR map at next moment for robotics navigation and path-planning. To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing. However, unlike video, which contains abundant visual features in each frame, a 2D LiDAR map lacks distinctive local features. To alleviate this challenge, we propose to estimate the motion flow based on deep neural networks inspired by its powerful representation learning ability in estimating the optical flow of the video. To this end, we design a recurrent neural network based on gated recurrent unit, which is named LiDAR-FlowNet. As a recurrent neural network can encode the temporal dynamic information, our LiDAR-FlowNet can estimate motion flow between the current map and the unknown next map only from the current frame and previous frames. A self-supervised strategy is further designed to train the LiDAR-FlowNet model effectively, while no training data need to be manually annotated. With the estimated motion flow, it is straightforward to predict the 2D LiDAR map at the next moment. Experimental results verify the effectiveness of our LiDAR-FlowNet as well as the proposed training strategy. The results of the predicted LiDAR map also show the advantages of our motion flow based method.

cs.RO↗

arXiv2018

Complementary Segmentation of Primary Video Objects with Reversible Flows

Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting foreground and background context as well as their complementary constraint. Under this formulation, a unified objective function is further defined to encode each cue. For implementation, we design a Complementary Segmentation Network (CSNet) with two separate branches, which can simultaneously encode the foreground and background information along with joint spatial constraints. The CSNet is trained on massive images with manually annotated salient objects in an end-to-end manner. By applying CSNet on each video frame, the spatial foreground and background maps can be initialized. To enforce temporal consistency effectively and efficiently, we divide each frame into superpixels and construct neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. With such flow, the initialized foregroundness and backgroundness can be propagated along the temporal dimension so that primary video objects gradually pop-out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 18 state-of-the-art models.

cs.CV↗

arXiv2016

One-dimensional hard-core anyon gas in a harmonic trap at finite temperature

We investigate the strongly interacting hard-core anyon gases in a one dimensional harmonic potential at finite temperature by extending thermal Bose-Fermi mapping method to thermal anyon-ferimon mapping method. With thermal anyon-fermion mapping method we obtain the reduced one-body density matrix and therefore the momentum distribution for different statistical parameters and temperatures. At low temperature hard-core anyon gases exhibit the similar properties as those of ground state, which interpolate between Bose-like and Fermi-like continuously with the evolution of statistical properties. At high temperature hard-core anyon gases of different statistical properties display the same reduced one-body density matrix and momentum distribution as those of spin-polarized fermions. The Tan's contact of hard-core anyon gas at finite temperature is also evaluated, which take the simple relation with that of Tonks-Girardeau gas $C_b$ as $C=\frac12(1-cosχπ)C_b$.

cond-mat.quant-gas↗

arXiv2015

The properties of Tonk-Girardeau Gas at Finite Temperature and Comparison with Polarized Free Fermions

In the present paper we investigate the Tonks-Girardeau gas confined in a harmonic trap at finite temperature with thermal Bose-Fermi mapping method. The pair distribution, density distribution, reduced one-body density matrix, the occupations number of natural orbitals, and momentum distribution are evaluated. In the whole temperature regime the pair distribution and density distribution exhibit the same properties as those of polarized free Fermions because both of them depend on the modulus of wavefunction rather than wavefunction. While the reduced one-body density matrix, the natural orbital occupation, momentum distribution, which depend on wavefunction, of Tonks gas displays Bose properties different from polarized free Fermions at low temperature. At high temperature we can not distinguish Tonks gas from the polarized free Fermi gas by all properties qualitatively.

cond-mat.quant-gas↗