Current Issue : October-December Volume : 2024 Issue Number : 4 Articles : 5 Articles
This paper presents an enhanced ground vehicle localization method designed to address the challenges associated with state estimation for autonomous vehicles operating in diverse environments. The focus is specifically on the precise localization of position and orientation in both local and global coordinate systems. The proposed approach integrates local estimates generated by existing visual–inertial odometry (VIO) methods into global position information obtained from the Global Navigation Satellite System (GNSS). This integration is achieved through optimizing fusion in a pose graph, ensuring precise local estimation and drift-free global position estimation. Considering the inherent complexities in autonomous driving scenarios, such as the potential failures of a visual–inertial navigation system (VINS) and restrictions on GNSS signals in urban canyons, leading to disruptions in localization outcomes, we introduce an adaptive fusion mechanism. This mechanism allows seamless switching between three modes: utilizing only VINS, using only GNSS, and normal fusion. The effectiveness of the proposed algorithm is demonstrated through rigorous testing in the Carla simulation environment and challenging UrbanNav scenarios. The evaluation includes both qualitative and quantitative analyses, revealing that the method exhibits robustness and accuracy....
Timely and accurate monitoring is a prerequisite to survey the types, quantities, quality, and distribution of various natural resources. Currently, satellite remote sensing is the major observation method, which has advantages in observation scale, fast speed, and low cost. However, with the increasingly precise management of natural resource, satellite remote sensing faces some shortcomings in observation timeliness, dynamism, and accuracy. To solve these problems, combining space-based, air-based, and ground-based observation technologies can offer an effective approach by taking the advantages of each technology. This study focuses on development and applications of an integrated space-air-ground observation network to avoid the insufficiencies of individual monitoring method in natural resource monitoring and supervision. In this paper, we combined satellite remote sensing, drone photography, video surveillance, and field survey to establish an integrated space-air-ground observation network, proposed a cooperative observation mechanism in observation task, scale, and time. Then monitoring indicators and supervision process was established via indicator library and workflow engine, realizing closed-loop management of "discovery, analysis, verification, disposal, and cancellation" for natural resource monitoring and supervision. Afterward, by connecting the observation network and following the closed-loop management process, a cross terminal software was designed and developed to achieve process automation of natural resource monitoring and supervision. Finally, the observation network and software was put into practice, and the results indicate that the integrated space-air-ground observation network can effectively improve the efficiency and accuracy of natural resource of monitoring and supervision....
To explore the hydrochemical characteristics of underground fluid observation wells in the Shandong area, piper diagram and Na-K-Mg triangle diagram methods were used to analyze the hydrochemical types and water-rock chemistry of water samples from 18 underground fluid observation wells in the study area. The results show that the hydrochemical types of underground fluid observation wells in the Shandong area are mainly SO4ꞏCl-CaꞏMg type, HCO3-Na type, HCO3-CaꞏMg type, and SO4ꞏCl-Na type. The chemical composition of water is mainly affected by water-rock interaction, rock salt dissolution, ion exchange, and human activities. Hydrogen and oxygen isotope analysis results show that atmospheric precipitation is the main recharge source of fluid wells in this area, and deep water recharge also plays an important role in some observation wells. The research results determine the hydrogeochemical background and well water source of underground fluid wells in the Shandong area and provide the scientific basis for fluid observation environment analysis, seismic monitoring and prediction, and seismic anomaly verification in the area....
An observational methodology system has been designed which allows the observation and analysis of the technical-tactical behaviour and interaction of judokas during competition. The observation instrument (JUTACTIC) is composed of 8 fixed criteria that provide information related to the competition and the competitors and 13 variable criteria that, throughout the intrasessional monitoring of each combat, allow the behaviour displayed by both judokas and their interaction to be recorded. From an observational sample consisting of matches from the Rio 2016 Olympic champions and the corresponding samples made using the LINCE PLUS software, evidence of validity, reliability, generalizability and applicability of the observation system is provided. The content validity of the observation instrument has been endorsed by a panel of experts (n = 11). Intra and inter-observer reliability has been guaranteed from the results obtained in the Fleiss Kappa and the Krippendorff Alpha. The generalizability analysis with the design structure [Category] [Participants] / [Matches] has confirmed that around seven matches are needed to accurately analyse the behaviour of the competitor under study. The practical application possibilities of the observation instrument has been shown with an example of the results obtained and the regular behaviour structures detected (T-patterns) using the THEME software....
In this study, we enhanced odometry performance by integrating vision sensors with LiDAR sensors, which exhibit contrasting characteristics. Vision sensors provide extensive environmental information but are limited in precise distance measurement, whereas LiDAR offers high accuracy in distance metrics but lacks detailed environmental data. By utilizing data from vision sensors, this research compensates for the inadequate descriptors of LiDAR sensors, thereby improving LiDAR feature matching performance. Traditional fusion methods, which rely on extracting depth from image features, depend heavily on vision sensors and are vulnerable under challenging conditions such as rain, darkness, or light reflection. Utilizing vision sensors as primary sensors under such conditions can lead to significant mapping errors and, in the worst cases, system divergence. Conversely, our approach uses LiDAR as the primary sensor, mitigating the shortcomings of previous methods and enabling vision sensors to support LiDAR-based mapping. This maintains LiDAR Odometry performance even in environments where vision sensors are compromised, thus enhancing performance with the support of vision sensors. We adopted five prominent algorithms from the latest LiDAR SLAM open-source projects and conducted experiments on the KITTI odometry dataset. This research proposes a novel approach by integrating a vision support module into the top three LiDAR SLAM methods, thereby improving performance. By making the source code of VA-LOAM publicly available, this work enhances the accessibility of the technology, fostering reproducibility and transparency within the research community...
Loading....