DeepCrash: A Deep Learning-Based Internet of Vehicles System for Head-On and Single-Vehicle Accident Detection With Emergency Notification

Abstract

Most individuals involved in traffic accidents receive assistance from drivers, passengers, or other people. However, when a traffic accident occurs in a sparsely populated area or the driver is the only person in the vehicle and the crash results in loss of consciousness, no one will be available to send a distress message to the proper authorities within the golden window for medical treatment. Considering these issues, a method for detecting high-speed head-on and single-vehicle collisions, analyzing the situation, and raising an alarm is needed. To address such issues, this paper proposes a deep learning-based Internet of Vehicles (IoV) system called DeepCrash, which includes an in-vehicle infotainment (IVI) telematics platform with a vehicle self-collision detection sensor and a front camera, a cloud-based deep learning server, and a cloud-based management platform. When a head-on or single-vehicle collision is detected, accident detection information is uploaded to the cloud-based database server for self-collision vehicle accident recognition, and a related emergency notification is provided. The experimental results show that the accuracy of traffic collision detection can reach 96% and that the average response time for emergencyrelated announcements is approximately 7 s. INDEX TERMS Advanced driver assistance system (ADAS), artificial intelligence over Internet of Things (AIoT), automotive, deep learning, Internet of Vehicles (IoV), head-on and single-vehicle accident detection.

An Artificial Intelligence of Things-Based Picking Algorithm for Online Shop in the Society 5.0’s Context

“…The minimum matching error (MME) then calculates how close the pair image values in the left image (x,y) are to and in the right image with disparity (x + d,y) to the identical points. The MME is known to be (14).…”

“…In Figure 9a, the image looks shaded because it is a composite view between the left and right images with a baseline of 50 mm. Meanwhile, Figure 9b showed the result from the disparity map in Figure 9a by applying block matching Equations ( 11)- (14). When capturing pairs of objects, the image is separately used as YOLOv2 input for detection purposes, and the detection results are shown in Figure 9c.…”

“…Including further research, MedGlasses helps visually impaired patients to take medication easily [ 13 ]. Still, [ 14 ] used deep learning and IoT to detect traffic accidents within 7 s detection response. Another implementation was offered by [ 15 ] to recognize the emotional expression of students on campus to be emotionally aware, humanist, and as personal assistants.…”

A Novel Extension for e-Safety Initiative Based on Developed Fusion of Biometric Traits

“…The paper [15] proposes a deep learning based Internet of Vehicles (IoV) system called DeepCrash, which includes a collision detection sensor consisting of an accelerometer and a gyroscope, a camera, a cloud-based deep learning server and management platform. When a vehicle collision is detected, an information with visual data is transmitted to the cloud-based database server for vehicle accident recognition and a related emergency notification is provided.…”

“…The data on the first three devices is based on [43] describing two commercially available solutions and a deeplearning based emergency detection of possible commercial employment. Dashcam is the commercially available driving recorder that additionally provides collision detection based, most probably, on an internal accelerometer.…”