| Paper Abstract and Keywords |
| Presentation |
2025-02-18 16:25
Trial for Recognizing Hazards in Traffic Scene Using a Vision-Language Model
Kazuma Nishimura, Kazuto Nakagawa, Temma Okamoto, Osamu Sugiyama, Masahiro Tada (Kindai Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
For the societal implementation of autonomous driving systems, it is essential that these systems understand collision risks caused by sudden deceleration of preceding vehicles or abrupt appearances of pedestrians and to minimize the associated accident risks. In traffic situations, humans collect information about objects and situations that may lead to accidents (hazards) and then use this information to comprehensively assess risk. Therefore, to properly assess the risks of a traffic situations, it is important to predict the hazards in traffic situations. This study therefore integrates image captioning technology, which represents the state and relative positions of surrounding traffic participants, semantic segmentation that can represent the type and position of obstructions, depth information that can represent the positional relationship between obstructions and the vehicle, and a Vision-Language Model(VLM) that processes multiple sequential images. Our system is designed to identify potentially hazardous traffic participants from external vehicle images including the possibility of traffic participants not visible in the image plane appearing and predict their near-future behaviors. Through experiments using hazard perception tests, which are widely used to measure drivers' risk predictive skills, the proposed method demonstrated an improvement in the accuracy of predicting the behavior of surrounding traffic participants by 18 points and the possibility of traffic participants not visible in the image plane appearing by 42 points compared to using the VLM alone, suggesting the effectiveness of the proposed approach. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Traffic scene recognition / Human behavior prediction / Vision-Language Model / Image captioning / / / / |
| Reference Info. |
ITE Tech. Rep., vol. 49, no. 4, ME2025-20, pp. 102-106, Feb. 2025. |
| Paper # |
ME2025-20 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
ME AIT MMS IEICE-IE IEICE-ITS SIP |
| Conference Date |
2025-02-18 - 2025-02-19 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Hokkaido Univ. |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Image Processing, etc. |
| Paper Information |
| Registration To |
ME |
| Conference Code |
2025-02-ME-AIT-MMS-IE-ITS-SIP |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
Trial for Recognizing Hazards in Traffic Scene Using a Vision-Language Model |
| Sub Title (in English) |
|
| Keyword(1) |
Traffic scene recognition |
| Keyword(2) |
Human behavior prediction |
| Keyword(3) |
Vision-Language Model |
| Keyword(4) |
Image captioning |
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Kazuma Nishimura |
| 1st Author's Affiliation |
Kindai University (Kindai Univ.) |
| 2nd Author's Name |
Kazuto Nakagawa |
| 2nd Author's Affiliation |
Kindai University (Kindai Univ.) |
| 3rd Author's Name |
Temma Okamoto |
| 3rd Author's Affiliation |
Kindai University (Kindai Univ.) |
| 4th Author's Name |
Osamu Sugiyama |
| 4th Author's Affiliation |
Kindai University (Kindai Univ.) |
| 5th Author's Name |
Masahiro Tada |
| 5th Author's Affiliation |
Kindai University (Kindai Univ.) |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| 21st Author's Name |
|
| 21st Author's Affiliation |
() |
| 22nd Author's Name |
|
| 22nd Author's Affiliation |
() |
| 23rd Author's Name |
|
| 23rd Author's Affiliation |
() |
| 24th Author's Name |
|
| 24th Author's Affiliation |
() |
| 25th Author's Name |
|
| 25th Author's Affiliation |
() |
| 26th Author's Name |
/ / |
| 26th Author's Affiliation |
()
() |
| 27th Author's Name |
/ / |
| 27th Author's Affiliation |
()
() |
| 28th Author's Name |
/ / |
| 28th Author's Affiliation |
()
() |
| 29th Author's Name |
/ / |
| 29th Author's Affiliation |
()
() |
| 30th Author's Name |
/ / |
| 30th Author's Affiliation |
()
() |
| 31st Author's Name |
/ / |
| 31st Author's Affiliation |
()
() |
| 32nd Author's Name |
/ / |
| 32nd Author's Affiliation |
()
() |
| 33rd Author's Name |
/ / |
| 33rd Author's Affiliation |
()
() |
| 34th Author's Name |
/ / |
| 34th Author's Affiliation |
()
() |
| 35th Author's Name |
/ / |
| 35th Author's Affiliation |
()
() |
| 36th Author's Name |
/ / |
| 36th Author's Affiliation |
()
() |
| Speaker |
Author-1 |
| Date Time |
2025-02-18 16:25:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2025-20, ME2025-20, AIT2025-20, SIP2025-20 |
| Volume (vol) |
vol.49 |
| Number (no) |
no.4 |
| Page |
pp.102-106 |
| #Pages |
5 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |