Li Shaofu

Bio: Li Shaofu is an academic researcher from Beijing University of Civil Engineering and Architecture. The author has contributed to research in topics: Inertial navigation system & Green roof. The author has an hindex of 1, co-authored 3 publications receiving 5 citations.

A rainwater control optimization design approach for airports based on a self-organizing feature map neural network model.

Abstract: To address the problems of high overflow rate of pipe network inspection well and low drainage efficiency, a rainwater control optimization design approach based on a self-organizing feature map neural network model (SOFM) was proposed in this paper. These problems are caused by low precision parameter design in various rainwater control measures such as the diameter of the rainwater pipe network and the green roof area ratio. This system is to be combined with the newly built rainwater pipe control optimization design project of China International Airport in Daxing District of Beijing, China. Through the optimization adjustment of the pipe network parameters such as the diameter of the rainwater pipe network, the slope of the pipeline, and the green infrastructure (GI) parameters such as the sinking green area and the green roof area, reasonable control of airport rainfall and the construction of sustainable drainage systems can be achieved. This research indicates that compared with the result of the drainage design under the initial value of the parameter, the green roof model and the conceptual model of the mesoscale sustainable drainage system, in the case of a hundred-year torrential rainstorm, the overflow rate of pipe network inspection wells has reduced by 36% to 67.5%, the efficiency of drainage has increased by 26.3% to 61.7%, which achieves the requirements for reasonable control of airport rainwater and building a sponge airport and a sustainable drainage system.

Multi-view stereo vision and inertial navigation system and relative pose parameter determining method

Abstract: The invention relates to a multi-view stereo vision and inertial navigation system and a relative pose parameter determining method. The relative pose parameter determining method comprises the following steps that: through a plurality of cameras of a multi-view stereo vision system, obtaining the measurement pixel coordinates of a plurality of calibration points, and through the inertial navigation system, obtaining the measurement inertial coordinate of the plurality of calibration points; using the measurement inertial coordinates of the plurality of calibration points to determine the correction camera coordinates of the plurality of calibration points on the basis of the camera distortion coefficient and the depth measurement error constraint of the multi-view stereo vision system; onthe basis of the measurement inertial coordinates of the plurality of calibration points of the inertial navigation system, obtaining the correction inertial coordinates of the plurality of calibration points; and on the basis of the correction inertial coordinates and the correction camera coordinates of the plurality of calibration points, determining the relative pose parameter of the multi-view stereo vision and inertial navigation system. By use of the method, the problems that spatial point accuracy distribution is even and the inertial navigation system lacks independent error compensation are solved, and a calibration result of the relative pose parameter is optimized.

Marker-Based Structural Displacement Measurement Models with Camera Movement Error Correction Using Image Matching and Anomaly Detection.

Abstract: To prevent collapse accidents at construction sites, the marker-based displacement measurement method was developed. However, it has difficulty in obtaining accurate measurements at long distances (>50 m) in an outdoor environment because of camera movements. To overcome this problem, marker-based structural displacement measurement models using image matching and anomaly detection were designed in this study. Then, the performance of each model in terms of camera movement error correction was verified through comparison with that of a conventional model. The results show that the systematic errors due to camera movements (<1.7°) were corrected. The detection rate of markers with displacement reached 95%, and the probability that the error size would be less than 10 mm was ≥ 95% with a 95% confidence interval at a distance of more than 100 m. Moreover, the normalized mean square error was less than 0.1. The models developed in this study can measure the pure displacement of an object without the systematic errors caused by camera movements. Furthermore, these models can be used to measure the displacements of distant structures using closed-circuit television cameras and markers in an outdoor environment with high accuracy.

A Novel Transformer-Based IMU Self-Calibration Approach through On-Board RGB Camera for UAV Flight Stabilization

Abstract: During flight, unmanned aerial vehicles (UAVs) need several sensors to follow a predefined path and reach a specific destination. To this aim, they generally exploit an inertial measurement unit (IMU) for pose estimation. Usually, in the UAV context, an IMU entails a three-axis accelerometer and a three-axis gyroscope. However, as happens for many physical devices, they can present some misalignment between the real value and the registered one. These systematic or occasional errors can derive from different sources and could be related to the sensor itself or to external noise due to the place where it is located. Hardware calibration requires special equipment, which is not always available. In any case, even if possible, it can be used to solve the physical problem and sometimes requires removing the sensor from its location, which is not always feasible. At the same time, solving the problem of external noise usually requires software procedures. Moreover, as reported in the literature, even two IMUs from the same brand and the same production chain could produce different measurements under identical conditions. This paper proposes a soft calibration procedure to reduce the misalignment created by systematic errors and noise based on the grayscale or RGB camera built-in on the drone. Based on the transformer neural network architecture trained in a supervised learning fashion on pairs of short videos shot by the UAV’s camera and the correspondent UAV measurements, the strategy does not require any special equipment. It is easily reproducible and could be used to increase the trajectory accuracy of the UAV during the flight.