Application of Computer Vision for Estimation of Moving Vehicle Weight

Feng, Maria Q.; Leung, Ryan Y.

doi:10.1109/jsen.2020.3038186

Cited by 30 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All this development provides a potentially useful tool that can automate bridge load classification. 43,45–47 Neuronal network is a mathematical model inspired by the neurophysiological patterns that describe human brain functions through billions of neurons arranged into a hierarchical structure of six different layers in the human cortex, connected with other neurons transmitting, processing, and storage by synapse connections in constant neuron plasticity processes for learning. The coding of synapse and neuron plasticity oversimplified processes are the base for the formulation of the mathematical model of the neuronal network, as expressed by equations (6) and (7) for each neuron, where x i = 1 : 1 : n is each of the n neuron inputs, w i = 1 : 1 : n is their corresponding synaptic weights, and ξ is the weighted sum of the neuron inputs.…”

Section: Computational Models As Blcs For Vbi Assessmentmentioning

confidence: 99%

A structural health monitoring method proposal based on optical scanning and computational models

Flores-Fuentes

Alba-Corpus

Sergiyenko

et al. 2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

This article proposes a method for continuous bridge displacement monitoring combining the dynamic triangulation scanning and load estimation by vehicle image recognition. The vehicle–bridge interaction is a non-stationary dynamic process parameter of high relevance to understanding the static instability behavior of bridges. The knowledge of the load on a bridge in the specific time when its structural spatial coordinates are measured allows correlating the bridge displacement with the effect of vehicle–bridge interaction. The evaluation of such correlation is mandatory in order to verify if the observed bridge displacement is due to the nature of its operation or due to it is presenting structural damage. The proposed method is continuous structural health monitoring method, based on the combination of three approaches evaluated at laboratory environment: (1) a three-dimensional optical scanning system for displacement measurement, (2) a load measurement system for vehicle–bridge interaction assessment, and (3) a two-measurement systems data correlation; to be implemented in bridges at a real environment to collect their historical behavior. Overall, for each approach, the measurement systems’ principles, the laboratory experimental methodology followed, and results obtained are presented.

show abstract

Section: Computational Models As Blcs For Vbi Assessmentmentioning

confidence: 99%

A structural health monitoring method proposal based on optical scanning and computational models

Flores-Fuentes

Alba-Corpus

Sergiyenko

et al. 2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNN) are a kind of Feedforward Neural Networks with deep structure and convolution calculation [4] [5]. It is one of the representative algorithms of deep learning [6].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Winograd convolution on GPUs via multithreaded communication

et al. 2023

Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023)

View full text Add to dashboard Cite

In advanced High-performance computing (HPC), convolution operations take a big proportion in convolutional neural networks, and convolutional neural networks very common in image and video based deep learning applications, because of which, this paper takes improving the performance of convolution operation as the research direction. Convolution can be performance in many ways, such as using mathematical definition to calculate, conversing to Fast Fourier Transform (FFT), conversing to batch matrix multiplication (im2col) or using Winograd algorithm. For small filter, Winograd has unique advantages. AMD based ROCm environment, the implementation of Winograd and an optimization method of Winograd based on multi-thread communication algorithm are introduced in this paper. For the Winograd convolution in ROCm 2.9.0, the speed of the algorithm was increased by more than 150% after optimization in this paper. Under some certain computing power ituations, the performance of the optimization algorithm approaches or even exceeds cuDNN and MIOpen.

show abstract

“…Currently, the traditional weigh station remains the most commonly used method for the ALD of vehicles. Astonishingly, statistics show that the average time lapse between a particular truck being selected for re-weighing enforcement is over 30 years [3]. Such low efficiency of the on-road vehicle overload inspection is due to the deficiencies of weigh stations: low accuracy for moving vehicles [4]; weak anti-cheating capability [5]; and above all insufficient number of stations [6].…”

Section: Introductionmentioning

confidence: 99%

“…According to the type of sensors used, it can be subdivided into the piezoelectric PWIM, fiber optic PWIM, sensor array PWIM, etc. All such PWIM systems, however, require costly hardware, installation, and maintenance [3]. In 1979, Moses [8] proposed the bridge-based WIM (BWIM) algorithm, which uses brides to weigh passing vehicles, and this approach has made considerable progress during the past decades [9,10].…”

Section: Introductionmentioning

confidence: 99%

“…With the development of computer vision and optical lenses, vision-based method has become a burgeoning alternative to the expensive traditional contact measurement equipment and sensors. To identify the axle loads of a moving vehicle, Feng and Leung [3] proposed a computer vision system to measure the deformation of the vehicle tires. To detect the gross vehicle weight, Kong et al [14] developed a computer vision-based method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of vehicle axle loads based on visual measurement

Liu¹,

Wang²,

Deng³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Monitoring vehicle axle loads is very important for preventing infrastructure degradation and traffic accidents. However, developing a cost-effective, flexible, and accurate axle load identification technology still remains challenging. In this study, a vehicle axle load identification method based on visual measurement is proposed. The principle of the method is that each axle load of the vehicle is determined based on the ratio of vehicular sprung mass to unsprung mass and the centroid position of the sprung mass, which can be predicted from the visually captured free decaying vibrations of the vehicle as it passes over a speed bump. To be more specific, the vibration responses of a vehicle passing over a speed bump is firstly measured by a camera, and the vehicle system matrix, which is composed of the mass matrix, stiffness matrix and damping matrix, can be obtained from the vehicle responses. The axle load can then be determined based on the element ratios in the system matrix of the vehicle whose unsprung masses are known. The performance of the proposed method is evaluated through numerical simulations and field tests. Results show that the identified axle loads agree well with the corresponding true values, proving the effectiveness and accuracy of the proposed method. This study has demonstrated a novel application of the computer vision technology to identify the axle loads of moving vehicles. The proposed method does not require the installation of sensors on the roadway or on the vehicle, making it a promising alternative for traditional weigh-in-motion systems.

show abstract

Application of Computer Vision for Estimation of Moving Vehicle Weight

Cited by 30 publications

References 23 publications

A structural health monitoring method proposal based on optical scanning and computational models

A structural health monitoring method proposal based on optical scanning and computational models

Optimizing Winograd convolution on GPUs via multithreaded communication

Identification of vehicle axle loads based on visual measurement

Contact Info

Product

Resources

About