5. 危険な状況の認識
以下の論文について解説します。
[Mogelmose2015] Mogelmose,A.,Trivedi, M. M., & Moeslund,T. B. (2015).
Trajectory analysis and prediction for improved pedestrian safety:
Integrated framework and evaluations.IEEE IntelligentVehicles Symposium,
Proceedings
[Chan2016] Chan, F. H., Chen,Y.T., Xiang,Y., & Sun, M. (2016).Anticipating
accidents in dashcam videos. Asian Conference on ComputerVision.
[Suzuki2017] Suzuki,T.,Aoki,Y., & Kataoka, H. (2017). Pedestrian Near-Miss
Analysis onVehicle-Mounted Driving Recorders. MachineVision and
Applications.
[Ke2017] Ke, R., Lutin, J., Spears, J., &Wang,Y. (2017).A Cost-Effective
Framework for AutomatedVehicle-Pedestrian Near-Miss Detection
Through Onboard MonocularVision.2017 IEEE Conference on Computer
Vision and Pattern RecognitionWorkshops (CVPRW)
[Zeng2017] Zeng, K.-H., Chou, S.-H., Chan, F.-H., Niebles, J. C., & Sun, M.
(2017).Agent-Centric Risk Assessment:Accident Anticipation and Risky
Region Localization. In Conference on ComputerVision and Pattern Recognition.
5
21. 群衆を考慮した行動予測
[Choi2008] Choi,W., Savarese, S., & Khuram, S. (2008).
What are they doing ? : Collective Activity Classification
Using Spatio-Temporal Relationship Among People. ICCV,
24, 2008.
25. 経路/意図の予測
[Kooij2014]Kooij, J. F. P., Schneider, N., Flohr, F., & Gavrila,
D. M. (2014). Context-Based Pedestrian Path Prediction.
European Conference on ComputerVision, (June),
29. 行動認識
[Kataoka2016]Kataoka, H., Miyashita,Y., Hayashi, M., Iwata,
K., & Satoh,Y. (2016). Recognition of Transitional Action
for Short-Term Action Prediction using Discriminative
Temporal CNN Feature. British MachineVision Conference.