Automatic vehicle detection and counting approach using low-rank representation and locality-constrained linear coding

2018 ◽  
Vol 35 (8) ◽  
pp. 2825-2843
Author(s):  
Qizi Huangpeng ◽  
Wenwei Huang ◽  
Hanyi Shi ◽  
Jun Fan
Keyword(s):  
Traffic Control ◽  
Moving Objects ◽  
Intelligent Transportation System ◽  
Vehicle Detection ◽  
Low Rank ◽  
Step Method ◽  
Lighting Condition ◽  
Content Type ◽  
Public Data ◽  
Low Rank Representation

Purpose Vehicles estimation can be used in evaluating traffic conditions and facilitating traffic control, which is an important task in intelligent transportation system. The paper aims to propose a vehicle-counting method based on the analysis of surveillance videos. Design/methodology/approach The paper proposes a novel two-step method using low-rank representation (LRR) detection and locality-constrained linear coding (LLC) classification to count the number of vehicles in traffic video sequences automatically. The proposed method is based on an offline training to understand an LLC-based classifier with extracted features for vehicle and pedestrian classification, followed by an online counting algorithm to count the number of vehicles detected from the image sequence. Findings The proposed method allows delivery estimation (counting the number of vehicles at each frame only) and total number estimation of vehicles shown in the scene. The paper compares the proposed method with other similar methods on three public data sets. The experimental results show that the proposed method is competitive and effective in terms of computational speed and evaluation accuracy. Research limitations/implications The proposed method does not consider illumination. Hence, the results might be unsatisfactory under low-lighting condition. Therefore, researchers are encouraged to add a term that controls the illumination changes into the energy function of vehicle detection in future work. Originality/value The paper bridges the gap between LRR detection and vehicle counting by taking advantage of existing LLC classification algorithm to distinguish different moving objects.

A hierarchical clustering of features approach for vehicle tracking in traffic environments

2016 ◽  
Vol 9 (4) ◽  
pp. 354-368 ◽  
Author(s):  
Anan Banharnsakun ◽  
Supannee Tanathong
Keyword(s):  
Hierarchical Clustering ◽  
Moving Objects ◽  
Vehicle Detection ◽  
Corner Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Night Time ◽  
Content Type ◽  
Traffic Conditions ◽  
Detection And Tracking

Purpose Developing algorithms for automated detection and tracking of multiple objects is one challenge in the field of object tracking. Especially in a traffic video monitoring system, vehicle detection is an essential and challenging task. In the previous studies, many vehicle detection methods have been presented. These proposed approaches mostly used either motion information or characteristic information to detect vehicles. Although these methods are effective in detecting vehicles, their detection accuracy still needs to be improved. Moreover, the headlights and windshields, which are used as the vehicle features for detection in these methods, are easily obscured in some traffic conditions. The paper aims to discuss these issues. Design/methodology/approach First, each frame will be captured from a video sequence and then the background subtraction is performed by using the Mixture-of-Gaussians background model. Next, the Shi-Tomasi corner detection method is employed to extract the feature points from objects of interest in each foreground scene and the hierarchical clustering approach is then applied to cluster and form them into feature blocks. These feature blocks will be used to track the moving objects frame by frame. Findings Using the proposed method, it is possible to detect the vehicles in both day-time and night-time scenarios with a 95 percent accuracy rate and can cope with irrelevant movement (waving trees), which has to be deemed as background. In addition, the proposed method is able to deal with different vehicle shapes such as cars, vans, and motorcycles. Originality/value This paper presents a hierarchical clustering of features approach for multiple vehicles tracking in traffic environments to improve the capability of detection and tracking in case that the vehicle features are obscured in some traffic conditions.

Detecting moving objects via the low-rank representation

2019 ◽  
Vol 13 (8) ◽  
pp. 1593-1601
Author(s):  
Yang Zhou ◽  
Bingo Wing-Kuen Ling
Keyword(s):  
Moving Objects ◽  
Low Rank ◽  
Low Rank Representation

Low rank representation and discriminant analysis-based models for peer-to-peer default risk assessment

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gui Yuan ◽  
Shali Huang ◽  
Jing Fu ◽  
Xinwei Jiang
Keyword(s):  
Risk Assessment ◽  
Discriminant Analysis ◽  
Default Risk ◽  
Assessment Model ◽  
Low Rank ◽  
Analysis Model ◽  
Content Type ◽  
Model Based ◽  
Low Rank Representation ◽  
Online Lending

Purpose This study aims to assess the default risk of borrowers in peer-to-peer (P2P) online lending platforms. The authors propose a novel default risk classification model based on data cleaning and feature extraction, which increases risk assessment accuracy. Design/methodology/approach The authors use borrower data from the Lending Club and propose the risk assessment model based on low-rank representation (LRR) and discriminant analysis. Firstly, the authors use three LRR models to clean the high-dimensional borrower data by removing outliers and noise, and then the authors adopt a discriminant analysis algorithm to reduce the dimension of the cleaned data. In the dimension-reduced feature space, machine learning classifiers including the k-nearest neighbour, support vector machine and artificial neural network are used to assess and classify default risks. Findings The results reveal significant noise and redundancy in the borrower data. LRR models can effectively clean such data, particularly the two LRR models with local manifold regularisation. In addition, the supervised discriminant analysis model, termed the local Fisher discriminant analysis model, can extract low-dimensional and discriminative features, which further increases the accuracy of the final risk assessment models. Originality/value The originality of this study is that it proposes a novel default risk assessment model, based on data cleaning and feature extraction, for P2P online lending platforms. The proposed approach is innovative and efficient in the P2P online lending field.

scholarly journals Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function

2020 ◽  
Vol 10 ◽  
Author(s):  
Conghai Lu ◽  
Juan Wang ◽  
Jinxing Liu ◽  
Chunhou Zheng ◽  
Xiangzhen Kong ◽  
...  
Keyword(s):  
Score Function ◽  
Low Rank ◽  
Low Rank Representation ◽  
Regularized Method

scholarly journals Privacy-Preserving Smart Road-Pricing System with Trustworthiness Evaluation in VANETs

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3658
Author(s):  
Qingfeng Zhu ◽  
Sai Ji ◽  
Jian Shen ◽  
Yongjun Ren
Keyword(s):  
Traffic Control ◽  
Traffic Management ◽  
Location Privacy ◽  
Vehicular Ad Hoc Networks ◽  
Intelligent Transportation System ◽  
Smart Cities ◽  
Security Analysis ◽  
Geographical Location ◽  
Experimental Simulation ◽  
Control Center

With the advanced development of the intelligent transportation system, vehicular ad hoc networks have been observed as an excellent technology for the development of intelligent traffic management in smart cities. Recently, researchers and industries have paid great attention to the smart road-tolling system. However, it is still a challenging task to ensure geographical location privacy of vehicles and prevent improper behavior of drivers at the same time. In this paper, a reliable road-tolling system with trustworthiness evaluation is proposed, which guarantees that vehicle location privacy is secure and prevents malicious vehicles from tolling violations at the same time. Vehicle route privacy information is encrypted and uploaded to nearby roadside units, which then forward it to the traffic control center for tolling. The traffic control center can compare data collected by roadside units and video surveillance cameras to analyze whether malicious vehicles have behaved incorrectly. Moreover, a trustworthiness evaluation is applied to comprehensively evaluate the multiple attributes of the vehicle to prevent improper behavior. Finally, security analysis and experimental simulation results show that the proposed scheme has better robustness compared with existing approaches.

Computing Robust Principal Components by A* Search

2018 ◽  
Vol 27 (07) ◽  
pp. 1860013 ◽  
Author(s):  
Swair Shah ◽  
Baokun He ◽  
Crystal Maung ◽  
Haim Schweitzer
Keyword(s):  
State Of The Art ◽  
Principal Component ◽  
Low Rank ◽  
A Algorithm ◽  
Running Time ◽  
Current State ◽  
Dimensionality Reduction Technique ◽  
Related Variant ◽  
Low Rank Representation ◽  
The Cost

Principal Component Analysis (PCA) is a classical dimensionality reduction technique that computes a low rank representation of the data. Recent studies have shown how to compute this low rank representation from most of the data, excluding a small amount of outlier data. We show how to convert this problem into graph search, and describe an algorithm that solves this problem optimally by applying a variant of the A* algorithm to search for the outliers. The results obtained by our algorithm are optimal in terms of accuracy, and are shown to be more accurate than results obtained by the current state-of-the- art algorithms which are shown not to be optimal. This comes at the cost of running time, which is typically slower than the current state of the art. We also describe a related variant of the A* algorithm that runs much faster than the optimal variant and produces a solution that is guaranteed to be near the optimal. This variant is shown experimentally to be more accurate than the current state-of-the-art and has a comparable running time.

Sign in / Sign up

Export Citation Format

Share Document