Name
Abstract | ||
|---|---|---|
Vision-based methods for detecting the status of traffic lights used in autonomous vehicles may be unreliable due to occluded views, poor lighting conditions, or a dependence on unavailable high-precision meta-data, which is troublesome in such a safety-critical application. This paper proposes a complementary detection approach based on an entirely new source of information: the movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real and simulated data sets, resulting in up to 97% accuracy in each set. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/ITSC.2016.7795568 | 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) |
Keywords | Field | DocType |
traffic light status based inference,classification models,supplemental detection method,complementary detection,safety critical application,autonomous vehicles,vehicle movement patterns,traffic light status detection | Computer vision,Time series,Data set,Traffic signal,Situation awareness,Simulation,Recurrent neural network,Artificial intelligence,Engineering,Perception | Conference |
ISBN | Citations | PageRank |
978-1-5090-1890-1 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| joseph p campbell | 1 | 36 | 6.76 |
| Heni Ben Amor | 2 | 359 | 35.77 |
| Marcelo H. Ang | 3 | 775 | 98.60 |
| Georgios E. Fainekos | 4 | 804 | 52.65 |