Global Positioning System (GPS) has been used in many aerial and terrestrial high precision positioning applications. Multipath affects positioning and navigation performance. This paper proposes a convolutional neural network based carrier-phase multipath detection method. The method is based on the fact that the features of multipath characteristics in multipath contaminated data can be learned and identified by a convolutional neural network. The proposed method is validated with simulated and real GPS data and compared with existing multipath mitigation methods in position domain. The results show the proposed method can detect about 80% multipath errors (i.e., recall) in both simulated and real data. The impact of the proposed method on positioning accuracy improvement is demonstrated with two datasets, 18–30% improvement is obtained by down-weighting the detected multipath measurements. The focus of this paper is on the development and test of the proposed convolutional neural network based multipath detection algorithm.

Video summarization has been extensively studied in the past decades. However, user-generated video summarization is much less explored since there lack large-scale video datasets within which human-generated video summaries are unambiguously defined and annotated. Toward this end, we propose a user-generated video summarization dataset - UGSum52 - that consists of 52 videos (207 minutes). In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries. To the best of our knowledge, it is currently the largest dataset for user-generated video summarization. Based on this dataset, we present FrameRank, an unsupervised video summarization method that employs a frame-to-frame level affinity graph to identify coherent and informative frames to summarize a video. We use the Kullback-Leibler(KL)-divergence-based graph to rank temporal segments according to the amount of semantic information contained in their frames. We illustrate the effectiveness of our method by applying it to three datasets SumMe, TVSum and UGSum52 and show it achieves state-of-the-art results.

Purpose: The purpose of the work is to provide a comprehensive review of the digital image correlation (DIC) technique for those who are interested in performing the DIC technique in the area of manufacturing.Design/methodology/approach: No methodology was used because the paper is a review article.Findings: no fundings.Originality/value: Herein, the historical development, main strengths and measurement setup of DIC are introduced. Subsequently, the basic principles of the DIC technique are outlined in detail. The analysis of measurement accuracy associated with experimental factors and correlation algorithms is discussed and some useful recommendations for reducing measurement errors are also offered. Then, the utilization of DIC in different manufacturing fields (e.g. cutting, welding, forming and additive manufacturing) is summarized. Finally, the current challenges and prospects of DIC in intelligent manufacturing are discussed.

Salient Object Detection (SOD) is one significant research area which is closely correlated to the attention of human beings. Most of the nowadays CNN-based approaches for SOD are based on an U-Net architecture. In this paper, we propose a novel capsule-based salient object detection framework by integrating the novel capsule blocks into both the generator and discriminator of GAN architecture. The experimental result showed that our approach is able to generate accurate saliency maps, which also highlighted the effectiveness of the capsule blocks. We also provide a challenging dataset that contains 3,299 images for SOD with difficult foreground objects and complex background contents.

Precise determination of the astronomical azimuth using the local hour angle (LHA) of Polaris is only applicable in northern middle latitudes. Therefore, to achieve fast and precise astronomical orientation in any part of the world, this study proposes continuous observations from the same station of multiple north stars and south stars at their culminating positions, thereby reducing the impact of errors in observation station longitude and time measurement. This method, which uses the regression model, determines the astronomical azimuth from the observation station to the ground target. Model validity is affected by various factors including sample size, data distribution, and data quality; therefore, suitable model conditions and individual characteristics of parametric and nonparametric regression are analyzed. Then, a two-step regression method comprising data binning followed by linear regression is proposed. Experimental data are subjected to direct linear regression, the summation of north and south star data followed by linear regression, nonparametric regression of summed data, and two-step regression of summed data. The two-step regression method produces the most accurate results that agree with those of the LHA method within a range of ±1.2120 × 10⁻⁶ rad (0.25″). Compared to the LHA method, the proposed method extends the geographical application range and eliminates the need for precise astronomical positioning prior to determining the orientation.

Video foreground segmentation is one of the key problems in video processing. In this paper, we proposed a novel and fully unsupervised approach for foreground object co-localization and segmentation of unconstrained videos. We firstly compute both the actual edges and motion boundaries of the video frames, and then align them by their HOG feature maps. Then, by filling the occlusions generated by the aligned edges, we obtained more precise masks about the foreground object. Such motion-based masks could be derived as the motion-based likelihood. Moreover, the color-base likelihood is adopted for the segmentation process. Experimental Results show that our approach outperforms most of the State-of-the-art algorithms.