Name
Abstract | ||
|---|---|---|
Due to the multiplicity of rear-end collisions and the complexity of collision forensics, it is necessary to reconstruct and evaluate the accident. In this paper, we propose a rear-end forensics and liability determination scheme based on multi-access edge computing (MEC) to facilitate rapid smart forensics and determine the accident liability reasonably. Specifically, a rear-end accident forensics model for smart forensics is first developed to collect the information about road environments, vehicle information stored on edge infrastructures, and data logging within the accident scene. We then establish a data chain of rear-end incident (CREI) from the forensic information closely related to vehicles involved in the collision. The possible security state (PSS) of the rear vehicle can be obtained by decoding the actual state (AS) of the front vehicle in the CREI using the Hidden Markov Model (HMM). Accordingly, the rear-end collision evaluation metrics is set up, calculating the estimated liabilities (ELs) for each vehicle based on the driver's attention level (AL) deduced from the proposed model. Finally, the liability of involved vehicle can be determined by HMM-based driver's AL detection algorithm. The performance evaluations show that the proposed smart forensics and rear-end liability determination scheme can determine rear-end liability faster and more reasonably. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ICCChina.2019.8855835 | 2019 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA (ICCC) |
Keywords | Field | DocType |
MEC, Cyber forensics, Liability determination, HMM, Accident reconstruction | Edge computing,Data logger,Computer science,Rear-end collision,Liability,Collision,Real-time computing,Decoding methods,Hidden Markov model | Conference |
ISSN | Citations | PageRank |
2377-8644 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xianwei Wang | 1 | 0 | 0.34 |
| Yi Zhou | 2 | 51 | 5.38 |
| Xiaoyong Ma | 3 | 0 | 1.69 |
| Ning Lu | 4 | 727 | 37.36 |
| Nan Cheng | 5 | 970 | 81.34 |
| Kuan Zhang | 6 | 789 | 60.23 |