Zhejiang University

Tao Jin

Xiaowei Ye

Zhexun Li

Pengyu Chen

Pengpeng Ang

The present invention proposes a method for identifying the spatial-temporal distribution of the vehicle loads on a bridge based on the DenseNet. The method includes five steps: firstly, mounting a plurality of cameras in different positions of a bridge, acquiring images of the bridge from different directions, and outputting video images with time tags; secondly, acquiring multichannel characteristics of vehicles on the bridge by using DenseNet, including color characteristics, shape characteristics and position characteristics; thirdly, analyzing the data and characteristics of the vehicles from different cameras at a same moment to obtain vehicle distribution on the bridge at any time; fourthly, continuously monitoring the vehicle distribution in a time period to obtain a vehicle load situation on any section of the bridge; and finally, integrating the time and space distribution of the vehicles to obtain spatial-temporal distribution of the bridge.

Method for identifying spatial-temporal distribution of vehicle loads on bridge based on densely connected convolutional networks

A structural vibration monitoring method based on computer vision and motion compensation provided in the present disclosure adopts a dual-camera system for self-motion compensation. The dual-camera system consists of a primary camera and a secondary camera rigidly connected to each other. The primary camera directly measures a structure displacement. This method inevitably includes an error generated due to motion of the primary camera. Meanwhile, the secondary camera measures displacements of translation and rotation, so as to estimate a measurement error caused by the motion of the primary camera. Then, with the displacement directly measured by the main camera minus the measurement error, a corrected structure displacement is obtained, thereby truthfully and accurately monitoring vibrations of a bridge structure.

Structural vibration monitoring method based on computer vision and motion compensation

Disclosed is a method for monitoring ground settlement based on computer vision. Before monitoring starts, the first image frame is captured. For one measuring point, the area of the top LED lamp is defined as a tracking template, its pixel center is the reference point for settlement calculation, and a monitoring area is defined by an estimated range. After monitoring starts, the best matched of the lamp template is searched for in the monitoring area of a second image frame. When the best matched area is obtained, its pixel center is obtained as the new lamp position, and it is selected as the new template; the pixel displacement between two adjacent image frames can be obtained by comparison. The total pixel displacement of multiple points during the monitoring period is calculated through the accumulated displacement, and the actual settlement is calculated through a pixel-physical ratio.

Method for monitoring ground settlement based on computer vision

A method for modal analysis of bridge structures based on surveillance videos is provided. A plurality of continuous cameras are utilized for realizing high-precision surveillance for the structure of the bridge. Firstly, a plurality of regions are selected in the viewing angle of each of the cameras, and a conversion relation between images of the regions and actual displacements is calculated; next, displacements on the images shot by the cameras are converted into actual displacements of targets, so as to obtain displacements of the targets relative to the cameras; displacements of the adjacent cameras are sequentially passed according to a difference value from the ground of an abutment, so as to obtain displacements of all camera bodies; and finally, the displacements of all the targets relative to the ground of the abutment are calculated, and the structural mode of the bridge is calculated.

Method for modal analysis of bridge structures based on surveillance videos

A method for detecting structural surface cracks based on image features, support vector machines and Bayesian data fusion, including: 1) acquisition of a video of a structural surface and establishment of an image library; 2) calculation of texture features of the image frames by local binary patterns; 3) scanning and grouping for image patches of cracks on the image frames using two-stage support vector machine; 4) Bayesian data fusion and decision. The video image detection acquires images of many areas where human beings are difficult to reach; computers are adopted to identify cracks on surfaces of the structural elements, which can greatly reduce the identification workload and labor cost, and increase the crack detection rate. The invention has a better adaptability to the light strength on the structural surface, thus providing better identification for cracks.

Growing community of inventors

Hangzhou, China

Tao Jin