On-Board Pedestrian Trajectory Prediction Using Behavioral Features. Czech, P., Braun, M., Kreßel, U., & Yang, B. In Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022, pages 437-443, 2022. Institute of Electrical and Electronics Engineers Inc.. ![On-Board Pedestrian Trajectory Prediction Using Behavioral Features [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image.In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.
@inproceedings{
title = {On-Board Pedestrian Trajectory Prediction Using Behavioral Features},
type = {inproceedings},
year = {2022},
pages = {437-443},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
id = {9b3724d1-625a-3625-8129-1794d8f44a5e},
created = {2024-11-06T13:04:00.806Z},
file_attached = {true},
profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2024-11-07T10:52:44.352Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
folder_uuids = {4cda9297-f98e-4246-88d6-ffeeade205c3},
private_publication = {false},
abstract = {This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image.In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.},
bibtype = {inproceedings},
author = {Czech, Phillip and Braun, Markus and Kreßel, Ulrich and Yang, Bin},
doi = {10.1109/ICMLA55696.2022.00070},
booktitle = {Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022}
}
Downloads: 0
{"_id":"s9ycYauqG5TKF2L6b","bibbaseid":"czech-braun-kreel-yang-onboardpedestriantrajectorypredictionusingbehavioralfeatures-2022","author_short":["Czech, P.","Braun, M.","Kreßel, U.","Yang, B."],"bibdata":{"title":"On-Board Pedestrian Trajectory Prediction Using Behavioral Features","type":"inproceedings","year":"2022","pages":"437-443","publisher":"Institute of Electrical and Electronics Engineers Inc.","id":"9b3724d1-625a-3625-8129-1794d8f44a5e","created":"2024-11-06T13:04:00.806Z","file_attached":"true","profile_id":"f1f70cad-e32d-3de2-a3c0-be1736cb88be","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2024-11-07T10:52:44.352Z","read":"true","starred":false,"authored":false,"confirmed":false,"hidden":false,"folder_uuids":"4cda9297-f98e-4246-88d6-ffeeade205c3","private_publication":false,"abstract":"This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image.In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.","bibtype":"inproceedings","author":"Czech, Phillip and Braun, Markus and Kreßel, Ulrich and Yang, Bin","doi":"10.1109/ICMLA55696.2022.00070","booktitle":"Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022","bibtex":"@inproceedings{\n title = {On-Board Pedestrian Trajectory Prediction Using Behavioral Features},\n type = {inproceedings},\n year = {2022},\n pages = {437-443},\n publisher = {Institute of Electrical and Electronics Engineers Inc.},\n id = {9b3724d1-625a-3625-8129-1794d8f44a5e},\n created = {2024-11-06T13:04:00.806Z},\n file_attached = {true},\n profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2024-11-07T10:52:44.352Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {4cda9297-f98e-4246-88d6-ffeeade205c3},\n private_publication = {false},\n abstract = {This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image.In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.},\n bibtype = {inproceedings},\n author = {Czech, Phillip and Braun, Markus and Kreßel, Ulrich and Yang, Bin},\n doi = {10.1109/ICMLA55696.2022.00070},\n booktitle = {Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022}\n}","author_short":["Czech, P.","Braun, M.","Kreßel, U.","Yang, B."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/085b338d-df76-6145-7e4b-8c64633f9302/On_Board_Pedestrian_Trajectory_Prediction_Using_Behavioral_Features.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"czech-braun-kreel-yang-onboardpedestriantrajectorypredictionusingbehavioralfeatures-2022","role":"author","metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["moGHosEp2wsfFe7LR","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["board","pedestrian","trajectory","prediction","using","behavioral","features","czech","braun","kreßel","yang"],"title":"On-Board Pedestrian Trajectory Prediction Using Behavioral Features","year":2022}