A Novel Acoustic Characteristic Extraction Algorithm for Traffic Volume Estimation

Zou, Zhengrong; Ma, Qinglu; Liu, Fengjie; Ullah, Saleem

doi:10.1109/access.2019.2954554

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ei=(ei1, ei2, …, eip, ) denote the unit orthogonal eigenvector. If Σ has been determined, then Yi can be calculated via formula (29), in addition, the variance of principal component and the covariance between principal components can be calculated by formula (30), where i≠j, meanwhile i,j=1, 2, …, p. (e1, e2, …, ep), then Y=P T X, and the covariance matrix of Y is shown in formula (31). The total variance of Yi is equal to the total variance of Xi, as shown in formula (32).…”

Section:  mentioning

confidence: 99%

“…Traffic noise analysis is also applied to traffic volume estimation. Literature [29] proposes a Triangular Wave Analysis (TWA) characteristic extraction algorithm for traffic volume estimation in order to solve the problem of intersectant Vehicle-Pass-Signals (VPSs) identification. Literature [30] uses traffic noise to study vehicle positioning so as to detect the existence of vehicle, and the number of vehicles finally can be converted into hourly traffic volume.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic State Evaluation Using Traffic Noise

Zou

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Traffic state information is widely applied into all aspects of Intelligent Transportation System (ITS), such as the macro-control of government departments, the implementation of traffic managers' plans, the decision-making of residents travel, and so on. At present, Mel Frequency Cepstrum Coefficient (MFCC) is generally used as characteristic of traffic noise to characterize different traffic states, and performs well in simple noise environment, but performs poorly in complex noise environment. Based on the analysis of traffic noise acquired from a roadside-installed acoustic acquisition equipment, the evaluation problem of traffic state in complex noise environment is considered in this paper. Traffic state is divided into three categories according to traffic speed in our work: free flow (40 km/h and above), saturated flow (10-40 km/h), and jammed flow (0-10 km/h). Teager Energy Operator (TEO) is introduced to improve the MFCC characteristic, thus a novel characteristic called T-MFCC is proposed. Principal Component Analysis (PCA) is introduced to reduce dimension of T-MFCC characteristic, thus a novel characteristic called PT-MFCC is proposed. Support Vector Machine (SVM) optimized by Particle Swarm Optimization (PSO) algorithm is applied as classifier to identify traffic state. Characterization capabilities of two modified characteristics and traditional MFCC characteristic for traffic state are compared in this paper. Experimental results demonstrate that the evaluation accuracy of traffic state based on T-MFCC characteristic is 3.685% higher than that based on MFCC characteristic, and the evaluation accuracy of traffic state based on PT-MFCC characteristic is 26.466% lower than that based on MFCC characteristic. Therefore, T-MFCC characteristic is superior to MFCC characteristic, while MFCC characteristic is superior to PT-MFCC characteristic, namely, T-MFCC characteristic can better characterize traffic state than MFCC characteristic, meanwhile, there are no redundancy attributes in T-MFCC characteristic, thus PCA is not needed to reduce the dimension of T-MFCC characteristic. INDEX TERMS traffic state, traffic noise, intelligent transportation systems, mel frequency cepstrum coefficient, teager energy operator, principal component analysis

show abstract

Section:  mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Traffic State Evaluation Using Traffic Noise

Zou

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The specific process includes two steps: data preprocessing and geometric correction. The data preprocessing stage mainly involves filtering and clustering edge points and internal points to obtain accurate data [27]. To reduce false positives in edge and internal point extraction, a validation method was adopted in the study.…”

mentioning

confidence: 99%

Traffic Marking Extraction Algorithm Based on Image and Point Cloud Data

Wu,

Mao

2024

IEEE Access

View full text Add to dashboard Cite

With the continuous development of urban traffic and the improvement of intelligent transportation systems, the accurate extraction and analysis of road traffic markings becomes more and more important. At present, road traffic marking is extracted by collecting dense point cloud data with highthread LiDAR. However, due to the high cost of the high-thread LiDAR and the large amount of point cloud data, the production efficiency of high-precision maps is low, and updating is complex and difficult. Therefore, a traffic marking extraction algorithm based on image and point cloud data fusion is proposed. The innovation of this study lies in the introduction of image processing for traffic marking edge detection, and the adaptive threshold segmentation of point cloud data using the maximum inter class variance method. The algorithm first uses an edge detection algorithm on the ground of the Canny operator to extract edge information of traffic markings from road images. Meanwhile, it uses the maximum inter class variance method to extract the internal point coordinate information of traffic markings from point cloud data. Subsequently, clustering segmentation, geometric correction and other techniques are used to process the fused data, thereby achieving automated extraction of road traffic markings. The results show that on the TuSimple dataset, the false detection rate and missed detection rate of the edge detection algorithm on the ground of the Canny operator are only 3.84% and 2.79%, respectively. Meanwhile, in the TuSimple dataset, the peak signal-to-noise ratio and structural similarity of the maximum inter class variance method were as high as 39.25% and 9.23%, respectively. In addition, the average time it takes for the algorithm proposed by the research institute to extract the edge points of a single road traffic marking is only 5.69ms. Especially, the proposed method achieved a maximum improvement of 14.07% in the accuracy of traffic marking edge detection. The method proposed by the research institute effectively reduces false positives and missed detections, and can accurately and efficiently extract the edges of road traffic markings, providing a new and reliable solution for the automated extraction of road traffic markings.

show abstract