Frequent and dramatic viewpoint changes make loop closure detection of hybrid ground/aerial vehicles extremely challenging. To address this issue, we present a robust and efficient loop closure detection approach based on the state-of-the-art simultaneous localization and mapping (SLAM) framework and pre-trained deep learning models. First, the outputs of the SuperPoint network are processed to extract both tracking features and additional features used in loop closure. Next, binary-encoded SuperPoint descriptors are applied with a method based on Bag of VisualWords (BoVW) to detect loop candidates efficiently. Finally, the combination of SuperGlue and SuperPointdescriptors provides correspondences of keypoints to verify loop candidates and calculate relative poses. The system is evaluated on the public datasets and a real-world hybrid ground/aerial vehicles dataset. The proposed approach enables reliable loop detection, even when the relative translation between two viewpoints exceeds 7m or one of the Euler angles is above 50°.
Polyacrylonitrile/Soy protein isolate/polyurethane (PAN/SPI/PU) blends were prepared in dimethylsulfoxide (DMSO). The compatibility and interactive properties of PAN/SPI, SPI/PU, and PAN/PU blend systems were studied using dilute solution viscometry and phase contrast microscopy. It was found that PAN/SPI and PAN/PU were immiscible systems, but that there was an attractive interaction between them. However, the SPI/PU was an almost miscible system. To improve compatibility, the main product of graft copolymerization of acrylonitrile and SPI (AN-g-SPI) and the alkaline hydrolysis polyacrylonitrile (HPAN) were used as compatibilizers. The results showed that the mechanical properties of both the PAN/SPI and PAN/SPI/PU systems were significantly improved.
A novel air leak diagnosis and localization method for vessels is proposed. The tempreture field around the leak changes during air inflation and deflation.The changing phenomenon is acquired by thermal camera and the best detecting time is confirmed by temperature curves.Then a local gray-entropy difference algorithm is used to identify the leak area from infrared images captured during inflation and deflation. The gray information of local gray-entropy enhances the difference between leak area and non-leak area largely meanwhile the entropy information of local gray-entropy improves robustness performance.Experiments verify that the leak localization method is effective and sensitive.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.