Yingfeng Cai

Saliency-Based Pedestrian Detection in Far Infrared Images

Night time pedestrian detection is more and more important in advanced driver assistant systems (ADAS). Traditional pedestrian detection algorithms in far infrared (FIR) images lack accuracy and have long processing times. Focusing on this issue, in this paper, a visual saliency-based pedestrian detection algorithm is proposed. First, areas that contain suspected pedestrians are detected using a fusion saliency-based method. Then, the sub-image of the suspected pedestrian is used as an input to a histogram of local intensity difference feature and cross kernel-based support vector machine classifier to make a final determination. Experiments performed using a real FIR road image data set demonstrated that the proposed fusion saliency-based region of interest (ROI) detection method has the largest pedestrian inclusion rate and the smallest ROI proportion compared with three other methods. Besides, compared with existing state-of-the-art pedestrian detection algorithms, the proposed method demonstrates a much higher pedestrian detection rate with a comparably short processing time.

Ensemble correlation-based low-rank matrix completion with applications to traffic data imputation

Abstract Low-rank matrix completion (LRMC) is a recently emerging technique which has achieved promising performance in many real-world applications, such as traffic data imputation. In order to estimate missing values, the current LRMC based methods optimize the rank of the matrix comprising the whole traffic data, potentially assuming that all traffic data is equally important. As a result, it puts more emphasis on the commonality of traffic data while ignoring its subtle but crucial difference due to different locations of loop detectors as well as dates of sampling. To handle this problem and further improve imputation performance, a novel correlation-based LRMC method is proposed in this paper. Firstly, LRMC is applied to get initial estimations of missing values. Then, a distance matrix containing pairwise distance between samples is built based on a weighted Pearsons correlation which strikes a balance between observed values and imputed values. For a specific sample, its most similar samples based on the distance matrix constructed are chosen by using an adaptive K-nearest neighboring (KNN) search. LRMC is then applied on these samples with much stronger correlation to obtain refined estimations of missing values. Finally, we also propose a simple but effective ensemble learning strategy to integrate multiple imputed values for a specific sample for further improving imputation performance. Extensive numerical experiments are performed on both traffic flow volume data as well as standard benchmark datasets. The results confirm that the proposed correlation-based LRMC and its ensemble learning version achieve better imputation performance than competing methods.

Salient object detection based on multi-scale contrast

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks.

Spatiotemporal variable and parameter selection using sparse hybrid genetic algorithm for traffic flow forecasting

Short-term traffic flow forecasting is a difficult yet important problem in intelligent transportation systems. Complex spatiotemporal interactions between the target road segment and other road segments can provide important information for the accurate forecasting. Meanwhile, spatiotemporal variable selection and traffic flow prediction should be solved in a unified framework such that they can benefit from each other. In this article, we propose a novel sparse hybrid genetic algorithm by introducing sparsity constraint and real encoding scheme into genetic algorithm in order to optimize short-term traffic flow prediction model based on least squares support vector regression. This method can integrate spatiotemporal variable selection, parameter selection as well as traffic flow prediction in a unified framework, indicating that the “goodness,” that is, contribution, of selected spatiotemporal variables and optimized parameters directly depends on the final traffic flow prediction accuracy. The real-world traffic flow data are collected from 24 observation sites located around the intersection of Interstate 205 and Interstate 84 in Portland, OR, USA. The experimental results show that the proposed sparse hybrid genetic algorithm-least square support vector regression prediction model can produce better performance but with much fewer spatiotemporal variables in comparison with other related models.

Graph regularized local self-representation for missing value imputation with applications to on-road traffic sensor data

Abstract Recovering missing values (MVs) from incomplete data is an important problem for many real-world applications. Previous research efforts toward solving MVs problem primarily exploit the global and/or local structure of data. In this work, we propose a novel MVs imputation method by combing sample self-representation strategy and underlying local linear structure of data in a uniformed framework. Specifically, the proposed method consists of the following steps. First, an existing method is applied to obtain the first-round estimation of MVs. Then, a graph, characterizing local proximity structure of data, is constructed based on imputed data. Next, a novel model coined as graph regularized local self-representation (GRLSR) is proposed by integrating two crucial elements: local self-representation and graph regularization. The former assumes each sample can be well represented (reconstructed) by linearly combining the neighboring samples while the latter further requires the neighboring samples should not deviate too much from each other after reconstruction. By doing so, MVs can be more accurately restored due to the joint imputation as well as local linear reconstruction. We also develop an effective alternating optimization algorithm to solve GRLSR model, thereby achieving final imputation. The convergence and computational complexity analysis of our method are also presented. To evaluate our method, extensive experiments are conducted on both traffic flow dataset and UCI benchmark datasets. The results demonstrate the effectiveness of our proposed method compared with a set of widely-used competing methods.

Design of a hybrid model predictive controller for the vehicle height adjustment system of an electronic air suspension

The vehicle height adjustment system of an electronically controlled air suspension poses challenging hybrid control problems, since it can operate in several distinct discrete modes (the gas-charging mode, the gas-discharging mode and the no-action) by switching the on–off solenoid valves. This paper describes the development and experimental validation of a new vehicle height adjustment controller for an electronically controlled air suspension based on the theory of hybrid systems. The mixed logical dynamic modelling approach, which is an effective model structure for hybrid systems, is chosen to obtain the hybrid dynamic behaviours of the vehicle height adjustment system. On the basis of some reasonable assumptions and a linear approximation for the non-linearities of the components, the mixed logical dynamic model of the system is constructed by using the hybrid systems description language, which is a high-level hybrid modelling language. Using this model, a constrained optimal control problem is formulated and solved by tuning a hybrid model predictive controller, which can track the desired vehicle height through controlling the on–off statuses of the solenoid valves directly. Simulations and experimental results are presented finally to show how the hybrid framework and the optimization-based control strategy can be successfully applied to solve the vehicle height control problem of an electronically controlled air suspension in a systematic way.

Vehicle detection based on visual saliency and deep sparse convolution hierarchical model

Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification. These types of methods generally have high processing times and low vehicle detection performance. To address this issue, a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed. A visual saliency calculation is firstly used to generate a small vehicle candidate area. The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection. The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group, which outperforms the existing state-of-the-art algorithms. More importantly, high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.

Estimation of Longitudinal Force and Sideslip Angle for Intelligent Four-Wheel Independent Drive Electric Vehicles by Observer Iteration and Information Fusion

Exact estimation of longitudinal force and sideslip angle is important for lateral stability and path-following control of four-wheel independent driven electric vehicle. This paper presents an effective method for longitudinal force and sideslip angle estimation by observer iteration and information fusion for four-wheel independent drive electric vehicles. The electric driving wheel model is introduced into the vehicle modeling process and used for longitudinal force estimation, the longitudinal force reconstruction equation is obtained via model decoupling, the a Luenberger observer and high-order sliding mode observer are united for longitudinal force observer design, and the Kalman filter is applied to restrain the influence of noise. Via the estimated longitudinal force, an estimation strategy is then proposed based on observer iteration and information fusion, in which the Luenberger observer is applied to achieve the transcendental estimation utilizing less sensor measurements, the extended Kalman filter is used for a posteriori estimation with higher accuracy, and a fuzzy weight controller is used to enhance the adaptive ability of observer system. Simulations and experiments are carried out, and the effectiveness of proposed estimation method is verified.

Reliable Sideslip Angle Estimation of Four-Wheel Independent Drive Electric Vehicle by Information Iteration and Fusion

Accurate estimation of longitudinal force and sideslip angle is significant to stability control of four-wheel independent driven electric vehicle. The observer design problem for the longitudinal force and sideslip angle estimation is investigated in this work. The electric driving wheel model is introduced into the longitudinal force estimation, considering the longitudinal force is the unknown input of the system, the proportional integral observer is applied to restructure the differential equation of longitudinal force, and the extended Kalman filter is utilized to estimate the unbiased longitudinal force. Using the estimated longitudinal force, considering the unknown disturbances and uncertainties of vehicle model, the robust sideslip angle estimator is proposed based on vehicle dynamics model. Moreover, the recursive least squares algorithm with forgetting factor is applied to vehicle state estimation based on the vehicle kinematics model. In order to integrate the advantages of the dynamics-model-based observer and kinematics-model-based observer and improve adaptability of observer system in complex working conditions, a vehicle sideslip angle fusion estimation strategy is proposed. The simulations and experiments are implemented and the performance of proposed estimation method is validated.

Implementation and Development of a Trajectory Tracking Control System for Intelligent Vehicle

In this paper, a trajectory tracking control system, which consists of a model predictive control unit and an active safety steering control unit, has been developed. A nonlinear bicycle vehicle model, including the longitudinal, lateral, yaw, and quasi-static roll motions, was derived as a predictive model to simulate and test the proposed model predictive control (MPC) system. A 4-DOF vehicle model was used to reflect the characteristics of vehicle dynamics to avoid rollover accidents of automobiles. Simulation was performed and experiment results demonstrated good performance of both MPC unit and active safety steering control unit. Finally, it was proved that the proposed trajectory tracking control system is easy to realize with low cost.