Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections

Abstract

We propose a system for monitoring the driving maneuver at road intersections using rule-based reasoning and deep learning-based computer vision techniques. Along with detecting and classifying turning movements online, the system also detects violations such as ignoring STOP signs and failing to yield the right-of-way to other drivers. There is no distinction between temporarily and permanently stopped vehicles in the majority of frameworks proposed in the literature. Therefore, to conduct an accurate right-of-way study, permanently stopped vehicles should be excluded not to confound the results. Moreover, we also propose in this work a low-cost Convolutional Neural Network (CNN)-based object detection framework able to detect moving and temporally stopped vehicles. The detection framework combines the reasoning system with background subtraction and a CNN-based object detector. The obtained results are promising. Compared to the conventional CNN-based methods, the detection framework reduces the execution time of the object detection module by about 30% (i.e., 54.1 instead of 75ms/image) while preserving the same detection reliability. The accuracy of trajectory recognition is 95.32%, that of the zero-speed detection is 96.67%, and the right-of-way detection was perfect.

Driver Behaviour at Signalized Intersection Literature Review

“…Drivers behave differently at intersections. When driving a vehicle, the driver makes his driving intention and chooses a set of operating behaviors that best suit the driving conditions at the time [5]. Driver behavior is a complex thing that can arise intentionally or not.…”

“…So, by analyzing driver behavior can improve driving safety. Studies show that drivers with long red lights become impatient and try to cross intersections [5], [6].…”

“…Michon in Shinar et al [4] states that driver behavior does not occur in a vacuum, but has "environmental input". In driving a vehicle, the driver makes his driving intention and chooses a set of operating behaviors that best suit the driving conditions at the time [5]. It is widely accepted that driver behavior varies between drivers according to age [6], gender [6], ethnicity [5], driving experience, emotions [7], and so on.…”

“…In driving a vehicle, the driver makes his driving intention and chooses a set of operating behaviors that best suit the driving conditions at the time [5]. It is widely accepted that driver behavior varies between drivers according to age [6], gender [6], ethnicity [5], driving experience, emotions [7], and so on. Even for the same driver, driving behavior can change from situation to situation as an adjustment to the driving environment [4].…”