More robust and better: a multiple kernel support vector machine ensemble approach for traffic incident detection

Abstract

This paper presents a multiple kernel support vector machine (MKL-SVM) ensemble algorithm to detect traffic incidents. It uses resampling technology to generate training set, test set, and training subset firstly; then uses different training subsets to train individual MKL-SVM classifiers; and finally introduces ensemble methods to construct MKL-SVM ensemble to detect traffic incidents. Extensive experiments have been performed to evaluate the performances of the four algorithms: standard SVM, SVM ensemble, MKL-SVM, and the proposed algorithm (MKL-SVM ensemble). The experimental results show that the proposed algorithm has the best comprehensive performances in traffic incidents detection. To achieve better performances, the proposed algorithm needs less individual classifiers to construct the ensemble than SVM ensemble algorithm. Thus, compared with SVM ensemble algorithm, the complexity of the ensemble classifier of the proposed algorithm is reduced greatly. Conveniently, the proposed algorithm also avoids the burden of selecting the appropriate kernel function and parameters.(DR), false alarm rate (FAR), and detection time. Some techniques based on video processing have been adopted to detect traffic incidents. Trivedi et al. described a novel architecture for developing distributed video networks for incident detection and management [29]. Mak and Fan made a study on the detection of lane-blocking incidents on the basis of the traffic data provided by video-based detectors installed along Singapore's Central Expressway [15]. It is a meaningful attempt to use the video processing techniques to detect traffic incidents, but it is sensitive to the outdoor environmental factors, namely static shadows, snow, rain, and glare. Shehata et al. present a literature review of outdoor environment detection. Once the environmental conditions are detected, they can be compensated for, and hence, the accuracy of alarms detected by video-based AID systems will be enhanced [27]. But this compensation is not able to completely eliminate the impact produced by the outdoor environment.The inductive loop detector (ILD) is the most commonly used sensor in traffic surveillance and management applications, which can collect the traffic data stably and does not suffer the outdoor environment impact. There are a lot of advanced algorithms that focus on detecting traffic incidents using ILD data and have achieved good results. These advanced algorithms divide the traffic patterns into two groups-incident traffic pattern and incident-free traffic pattern-then, the traffic incident detection problem will be transformed into a binary classification problem based on ILD data. Qi et al. adopt the cumulative sum of log-likelihood ratio (CUSUM) algorithm to detect freeway incidents by integrating traffic measurements from two contiguous loop detectors and the non-stationarity of traffic flows [23]. In [8,1,25,26], Neural networks are proposed to detect traffic incidents. The conclusion of their papers is that artificial neural networks have ...

Traffic Peak Period Detection from an Image Processing View

“…The idea of TPPD is that the speed, flow, and density will achieve the peaks during the traffic peak periods [7][8][9]. As there are interrelated relations between speed, flow, and density, any one of them can be selected to detect the traffic peak periods.…”

Sensitivity Analysis Based SVM Application on Automatic Incident Detection of Rural Road in China

“…In 2013, Wang et al [17] developed a combination AID algorithm based on the time series method and machine learning methods, which expanded the input factors' volume and more precisely fed back the detection results. In 2014, Xiao et al [18] approved a new AID method based on the SVM, which together systematically integrated kernel functions, and made the usage of the AID technology in low traffic volume road section a feasible method. Liu et al [19] proposed an AID algorithm in 2014, which integrated several Bayesian classifiers, proven to obtain a better robustness.…”

Automated Incident Detection Using Real-Time Floating Car Data

“…This yields a trove of traffic data to be used in traffic state estimation, travel time measurements, and traffic management applications. While loops only monitor a single location, vehicle reidentification techniques can be applied to obtain vehicle trajectory information, allowing for various application, for example, estimating travel times [1,2], highway monitoring [3], and incident detection [4][5][6]. A complete system of connected measurement locations can be installed, allowing road operators to monitor traffic.…”