Chinese is the most widely used language in the world. Algorithms that read Chinese text in natural images facilitate applications of various kinds. Despite the large potential value, datasets and competitions in the past primarily focus on English, which bares very different characteristics than Chinese. This report introduces RCTW, a new competition that focuses on Chinese text reading. The competition features a largescale dataset with 12,263 annotated images. Two tasks, namely text localization and end-to-end recognition, are set up. The competition took place from January 20 to May 31, 2017. 23 valid submissions were received from 19 teams. This report includes dataset description, task definitions, evaluation protocols, and results summaries and analysis. Through this competition, we call for more future research on the Chinese text reading problem. The official website for the competition is http://rctw.vlrlab.net

Simultaneous Localization and Mapping (SLAM) plays an important role in the computer vision and robotics field. The traditional SLAM framework adopts a strong static world assumption for analysis convenience. How to cope with dynamic environments is of vital importance and attracts more attentions. Existing SLAM systems toward dynamic scenes either solely utilize semantic information, solely utilize geometry information, or naively combine the results from them in a loosely coupled way. In this paper, we present SOF-SLAM: Semantic Optical Flow SLAM, a visual semantic SLAM system toward dynamic environments, which is built on RGB-D mode of ORB-SLAM2. A new dynamic features detection approach called semantic optical flow is proposed, which is a kind of tightly coupled way and can fully take advantage of feature's dynamic characteristic hidden in semantic and geometry information to remove dynamic features effectively and reasonably. The pixel-wise semantic segmentation results generated by SegNet serve as mask in the proposed semantic optical flow to get a reliable fundamental matrix, which is then used to filter out the truly dynamic features. Only the remaining static features are reserved in the tracking and optimization module to achieve accurate camera pose estimation in dynamic environments. Experiments on public TUM RGB-D dataset and in real-world environment are conducted. Compared with ORB-SLAM2, the proposed SOF-SLAM achieves averagely 96.73% improvements in high-dynamic scenarios. It also outperforms the other four state-of-the-art SLAM systems which cope with the dynamic environments.

A new atmospheric spectral model and expressions of irradiance scintillation index are derived theoretically for optical wave propagating through moderate-to-strong non-Kolmogorov turbulence. They are developed under Andrews' assumption that small-scale irradiance fluctuations are modulated by large-scale irradiance fluctuations of the wave, and the geometrical optics approximation is adopted for mathematical development. A wide range of turbulence strength is considered instead of a limited range for weak turbulence. The atmospheric spectral model has a spectral power law value in the range of 3 to 4 instead of the standard power law value of 11/3. Numerical calculations are conducted to analyze the influences of spectral power law and turbulence strength.

Analytical expressions for the variance of angle of arrival (AOA) fluctuations based on the Rytov approximation theory are derived for plane and spherical waves' propagation through weak anisotropic non-Kolmogorov turbulence atmosphere. The anisotropic spectrum model based on the assumption of circular symmetry in the orthogonal plane throughout the path is adopted and it includes the same degree of anisotropy along the direction of propagation for all the turbulence cells size in the inertial sub-range. The derived expressions consider a single anisotropic coefficient describing the turbulence anisotropic property and a general spectral power law value in the range 3 to 4. They reduce correctly to the previously published analytic expressions for the cases of plane and spherical waves' propagation through weak isotropic non-Kolmogorov turbulence for the special case of anisotropic factor equaling one. To reduce the complexity of the analytical results, the asymptotic-fit expressions are also derived and they fit well with the close-form ones. These results are useful for understanding the potential impact of deviations from the standard isotropic non-Kolmogorov turbulence atmosphere.

A method based on the transport of intensity equation (TIE) for phase retrieval is presented, which can retrieve the optical phase from intensity measurements in multiple unequally-spaced planes in the near-field region. In this method, the intensity derivative in the TIE is represented by a linear combination of intensity measurements, and the coefficient of the combination can be expressed by explicitly analytical form related to the defocused distances. The proposed formula is a generalization of the TIE with high order intensity derivatives. The numerical experiments demonstrate that the proposed method can improve the accuracy of phase retrieval with higher-order intensity derivatives and is more convenient for practical application.