Name
Abstract | ||
|---|---|---|
Large amounts of data on accidents are continually being collected by dashboard cameras (dashcams). In this paper, we address the problem of predicting the occurrence of accidents: Our goal is to predict when accidents will occur based on stored dashcam data and analysis of live video streams. We propose a survival analysis model for predicting the event occurrence time. The occurrence of accidents involves changes in the situation of own car and surroundings. Therefore, the hazard function of the proposed model is modeled by a convolutional recurrent neural network that can capture it from high-dimensional time-series information, i.e., video. Another characteristic of our model is its incorporation of location data because how likely the events are to occur strongly depends on location. Our model can predict accidents by simultaneously considering video and location data. Experiments on real-world event recorder data show that our model can more accurately predict accident occurrences than baseline models.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3356995.3364535 | PredictGIS@SIGSPATIAL |
Keywords | Field | DocType |
event recorder data, traffic accident, survival analysis, recurrent neural network | Computer science,Real-time computing | Conference |
ISBN | Citations | PageRank |
978-1-4503-6964-0 | 1 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yoshiaki Takimoto | 1 | 1 | 0.34 |
| Yusuke Tanaka | 2 | 10 | 5.57 |
| Takeshi Kurashima | 3 | 315 | 24.21 |
| Shuhei Yamamoto | 4 | 1 | 0.34 |
| Maya Okawa | 5 | 10 | 3.23 |
| Hiroyuki Toda | 6 | 58 | 14.72 |