TY - GEN
T1 - Joint Pedestrian Detection and Risk-level Prediction with Motion-Representation-by-Detection
AU - Kataoka, Hirokatsu
AU - Suzuki, Teppei
AU - Nakashima, Kodai
AU - Satoh, Yutaka
AU - Aoki, Yoshimitsu
N1 - Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/5
Y1 - 2020/5
N2 - The paper presents a pedestrian near-miss detector with temporal analysis that provides both pedestrian detection and risk-level predictions which are demonstrated on a self-collected database. Our work makes three primary contributions: (i) The framework of pedestrian near-miss detection is proposed by providing both a pedestrian detection and risk-level assignment. Specifically, we have created a Pedestrian Near-Miss (PNM) dataset that categorizes traffic near-miss incidents based on their risk levels (high-, low-, and no-risk). Unlike existing databases, our dataset also includes manually localized pedestrian labels as well as a large number of incident-related videos. (ii) Single-Shot MultiBox Detector with Motion Representation (SSD-MR) is implemented to effectively extract motion-based features in a detected pedestrian. (iii) Using the self-collected PNM dataset and SSD-MR, our proposed method achieved +19.38% (on risk-level prediction) and +13.00% (on joint pedestrian detection and risk-level prediction) higher scores than that of the baseline SSD and LSTM. Additionally, the running time of our system is over 50 fps on a graphics processing unit (GPU).
AB - The paper presents a pedestrian near-miss detector with temporal analysis that provides both pedestrian detection and risk-level predictions which are demonstrated on a self-collected database. Our work makes three primary contributions: (i) The framework of pedestrian near-miss detection is proposed by providing both a pedestrian detection and risk-level assignment. Specifically, we have created a Pedestrian Near-Miss (PNM) dataset that categorizes traffic near-miss incidents based on their risk levels (high-, low-, and no-risk). Unlike existing databases, our dataset also includes manually localized pedestrian labels as well as a large number of incident-related videos. (ii) Single-Shot MultiBox Detector with Motion Representation (SSD-MR) is implemented to effectively extract motion-based features in a detected pedestrian. (iii) Using the self-collected PNM dataset and SSD-MR, our proposed method achieved +19.38% (on risk-level prediction) and +13.00% (on joint pedestrian detection and risk-level prediction) higher scores than that of the baseline SSD and LSTM. Additionally, the running time of our system is over 50 fps on a graphics processing unit (GPU).
UR - http://www.scopus.com/inward/record.url?scp=85092699286&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092699286&partnerID=8YFLogxK
U2 - 10.1109/ICRA40945.2020.9197399
DO - 10.1109/ICRA40945.2020.9197399
M3 - Conference contribution
AN - SCOPUS:85092699286
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 1021
EP - 1027
BT - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
Y2 - 31 May 2020 through 31 August 2020
ER -