This paper describes a novel driving pattern recognition and status monitoring system based on the orientation information.
Two fixed cameras are used to capture the driver’s image and the front-road image. The driver’s sight line and the driving
lane path are found from these 2 captured images and are mapped into a global coordinate. Two correlation coefficients among
the driver’s sight line, the driving lane path and the car heading direction are calculated in the global coordinate to monitor
the driving status such as a safe driving status, a risky driving status and a dangerous driving status. The correlation coefficients
between the lane path and car heading direction in a fixed period are analyzed and recognized as one of 4 driving patterns
by HMM. Four driving patterns including the driving in a straight lane, the driving in a curve lane, the driving of changing
lanes, and the driving of making a turn are able to be recognized so far.
"The network can predict the future states of the vehicle based on both reliable and unreliable information but was unable to give information about current condition of the driver. Lee et al. , developed a system to map captured images to global co-ordinates to monitor driving behavior. Using a hidden Markov Model (HMM), they were able to deduce four driving forms. "
[Show abstract][Hide abstract] ABSTRACT: Advanced driver assistance systems are the newest addition to vehicular technology. Such systems use a wide array of sensors to provide a superior driving experience. Vehicle safety and driver alert are important parts of these system. This paper proposes a driver alert system to prevent and mitigate adjacent vehicle collisions by proving warning information of on-road vehicles and possible collisions. A dynamic Bayesian network (DBN) is utilized to fuse multiple sensors to provide driver awareness. It detects oncoming adjacent vehicles and gathers ego vehicle motion characteristics using an on-board camera and inertial measurement unit (IMU). A histogram of oriented gradient feature based classifier is used to detect any adjacent vehicles. Vehicles front-rear end and side faces were considered in training the classifier. Ego vehicles heading, speed and acceleration are captured from the IMU and feed into the DBN. The network parameters were learned from data via expectation maxi-mization(EM) algorithm. The DBN is designed to provide two type of warning to the driver, a cautionary warning and a brake alert for possible collision with other vehicles. Experiments were completed on multiple public databases, demonstrating successful warnings and brake alerts in most situations.
International conference on Multimodal interaction (ICMI 2015), Seattle, WA, USA; 11/2015
"The advances and improvements in sensing and computation technologies led to the emergence of driving monitoring system which fall into two major categories; monitoring of drivers vigilance systems and vehicle-human interactions systems. Driver's vigilance systems are used to measure the driver alertness by using visual observation of drivers   or by monitoring driver's physiological signals . On the other hand, vehicle-human interactions systems are used to identify and quantify the relationships between driver's behavioural indices and traffic safety. "
[Show abstract][Hide abstract] ABSTRACT: Driver behaviour recognition or driving style classification systems have become very important for reducing vehicle accidents and providing safety. Human driver behavior recognition systems are used to estimate human behaviour by observing driver interaction with the vehicle and environment. These systems goal is to infer the driver's behaviour by mapping some parameters that represent the driver interaction with control elements available in the vehicle, such as speed, accelerator, following distance, and etc. The driving style recognition approach developed in this paper is based on the theory of fuzzy logic, which provides a methodology for reasoning about the application area that approximates human reasoning. One key aspect of the method developed in this paper is the great reduction of the rules of the rule-base inference engine by using a decomposed fuzzy system. The method is based on introducing weighting factors for the sensor inputs, thus inferring the reflexive conclusions from each input to the system rather than putting all the possible states of all the inputs to infer a single conclusion. The effectiveness and reliability of the proposed method is evaluated and compared with data obtained from an expert judgment for a 25 driving styles.
"For example, Zhu et al.  used cameras to capture eyelid movement, head movement , and facial expression to predict driver fatigue based on probabilistic model. Lee et al.  used cameras to capture the driver's sight line and the driving path and calculated the correlation between them to monitor the driving status and patterns. Also, abnormal driving can be detected using physiological signals. "
[Show abstract][Hide abstract] ABSTRACT: Abstract—Safer driver behavior promoting is the main goal of
this paper. It is a fact that drivers behavior is relatively safer when
being monitored. Thus, in this paper, we propose a monitoring
system to report speciﬁc driving event as well as the potentially
aggressive events for estimation of the driving performance. Our
driving monitoring system is composed of two parts. The ﬁrst part
is the in-vehicle embedded system which is composed of a GPS
receiver, a two-axis accelerometer, radar sensor, OBD interface, and
GPRS modem. The design considerations that led to this architecture
is described in this paper. The second part is a web server where an
adaptive hierarchical fuzzy system is proposed to classify the driving
performance based on the data that is sent by the in-vehicle embedded
system and the data that is provided by the geographical information
system (GIS). Our system is robust, inexpensive and small enough
to ﬁt inside a vehicle without distracting the driver.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.