Intelligent vehicles and advanced driver assistance systems (ADAS) need to have proper awareness of the traffic context, as well as the driver status since ADAS share the vehicle control authorities with the human driver. This paper provides an overview of the ego-vehicle driver intention inference (DII), which mainly focuses on the lane change intention on highways. First, a human intention mechanism is discussed in the beginning to gain an overall understanding of the driver intention. Next, the ego-vehicle driver intention is classified into different categories based on various criteria. A complete DII system can be separated into different modules, which consist of traffic context awareness, driver states monitoring, and the vehicle dynamic measurement module. The relationship between these modules and the corresponding impacts on the DII are analyzed. Then, the lane change intention inference system is reviewed from the perspective of input signals, algorithms, and evaluation. Finally, future concerns and emerging trends in this area are highlighted.

/pdf/driver-lane-change-intention-inference-for-intelligent-4wcx2tetfv.pdf

Driver Lane Change Intention Inference for Intelligent Vehicles: Framework, Survey, and Challenges

Existing System: Driver monitoring has been a long standing research problem in computer vision and automotive driver monitoring system applications . Broadly speaking, there are two approaches to estimate gaze direction: one is Techniques that only use the head pose and the second is those that use the driver’s head pose and gaze. For systems that rely only on head pose estimation the processing complexicity increases in regard to the software requirement and for those that relay on head pose and gaze estimation are grouped into hardware and software based approaches Active Appearance Models (AAMs) for facial feature tracking and head pose estimation and 3D eye-model was used for accurate gaze estimation, both of theserelay on near-infrared (IR) illuminators to generate the bright pupil effect. This system is not person-independent and must be calibrated for every system configuration and driver. Besides their complexicity of integration and implementation these systems are too expensive to be installed in mass-produced cars and they require periodic re-calibration because vibrations cause the system calibration to drift over time.

/pdf/driver-gaze-tracking-and-eyes-off-the-road-detection-system-1wlwprqzx1.pdf

Driver Gaze Tracking And Eyes Off The Road Detection System

Due to advantages of handling problems with nonlinearity and uncertainty, Gaussian process regression (GPR) has been widely used in the area of driver behaviour modelling. However, traditional GPR lacks the ability of transferring knowledge from one driver to another, which limits the generalisation ability of GPR, especially when sufficient data for driver behaviour modelling are not available. To solve this limitation, in this paper, a novel GPR model, Importance Weighted Gaussian Process Regression (IWGPR) is proposed. The importance weight (IW) represents the probabilistic density ratio between two drivers and the unconstrained least-squares importance fitting (ULSIF) is applied to calculate IW. Meanwhile, an IW-based model selection (IWMS) method is proposed to help the model select optimal parameters. Using IWGPR, sufficient historical data collected from one driver can be used to model another driver with insufficient data, and thus improve the generalisation ability of GPR. To verify the proposed algorithm, a toy regression problem is used to illustrate the working mechanism of IWGPR. With simulated and naturalistic driving data, three experiments for driver behaviour modelling in the lane change scenario, are designed and carried out. Experimental results indicate that IWGPR performs better than GPR when sufficient data are not provided by the new driver, which proves the generalisation ability of IWGPR. Meanwhile, the comparative study between different transferable driver behaviour learning methods is detailed and analysed.

Importance Weighted Gaussian Process Regression for Transferable Driver Behaviour Learning in the Lane Change Scenario

Each year, millions of people lose their lives to fatal road accidents. An ever increasing proportion of these accidents is due to distracted driving caused by co-passengers and mobile devices. Thus, there is a growing need for a system which detects the distracted driver in real-time and raises a warning alarm. To this end, we present a simple and robust architecture using foreground extraction and a Convolutional Neural Network (CNN). Our ConvNet model has significantly fewer parameters (0.5M) than state-of-the-art models. Detailed experimental evaluation on two publicly available datasets, the State Farm Distracted Driver Detection dataset (SFD3) and the AUC Distracted Driver dataset (AUCD2), confirm that our model either outperforms or compares with the models proposed so far on both the datasets, with a test accuracy of 98.48% and 95.64%, respectively. Our experiments also suggest that incorporating additional features such as the posture of a driver through foreground extraction using GrabCut substantially improves the performance of our model. Furthermore, our ConvNet is capable of detecting real-time distractions without any parallel processing.

Are You Paying Attention? Detecting Distracted Driving in Real-Time

Towards Detection of Bus Driver Fatigue based on Robust Visual Analysis of Eye State

Drivers’ decision and their corresponding behaviors are important aspects that can affect the driving safety, and it is necessary to understand the driver behaviors in real-time. In this study, an end-to-end driving-related tasks recognition system is proposed. Specifically, seven common driving activities are identified, which are normal driving, right mirror checking, rear mirror checking, left mirror checking, using in-vehicle video device, texting, and answering mobile phone. Among these, the first four activities are regarded as normal driving tasks, while the rest three are divided into distraction group. The images are collected using a consumer range camera, namely, Kinect. In total, five drivers are involved in the naturalistic data collection. Before training the identification model, the raw images are first segmented using a Gaussian mixture model (GMM) to extract the driver region from the background. Then, a pre-trained deep convolutional neural network (CNN) model is trained to classify the behaviors, which directly takes the processed RGB images as the input and outputs the identified label. In this work, the AIexNet is selected as the pre-trained CNN model. Then, to reduce the training cost, the transfer learning mechanism is applied to the CNN model. An average of 79\% detection accuracy is achieved for the seven driving tasks. The proposed integration model can be used as a low-cost driver distraction and dangerous tasks recognition modeL.

End-to-End Driving Activities and Secondary Tasks Recognition Using Deep Convolutional Neural Network and Transfer Learning

Reconfigurable intelligent surfaces (RISs)-assisted Internet of Things (IoT) networks have attracted a great deal of interest due to the potential contributions to the next generation wireless networks. In this article, an adaptive RIS clustering system with weak channels or obstacles is investigated. Ideally, there is a suitable RIS that adopts the self-organized RIS-assisted (SORA) scheme between a base station (BS) and a user equipment (UE) for reflection transmission. However, due to the nonideal channel scenarios, a single RIS may not be capable of connecting the BS with the UE. To tackle these nonideal cases, we propose a complementary RIS-cluster-assisted (C-RCA) strategy by reflecting signals among clusters to improve the performance of the overall system. The performances of the two strategies in terms of outage probability (OP) and ergodic capacity (EC), derived using approximate closed-form expressions, are analyzed. By increasing the numbers of complementary RISs and the reflecting elements on each RIS simultaneously, these performance metrics as well as the effective throughput and energy efficiency (EE) are evaluated under different signal-to-noise ratios (SNRs). The obtained results demonstrated that, in contrast to the ideal case, the network EE of the proposed C-RCA strategy is higher than the SORA scheme under the larger target spectral efficiency (SE).

Hong Liu

Papers

End-to-End Driving Activities and Secondary Tasks Recognition Using Deep Convolutional Neural Network and Transfer Learning

Performance Analysis of Adaptive RIS-Assisted Clustering Strategies in Downlink Communication Systems