A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation
Perceiving self-vehicle state based on vehicle information can provide key information for unmanned driving and improve vehicle safety monitoring ability. However, existing studies mainly perceive the vehicle state using out-of-vehicle sensors, positioning systems and in-vehicle sensors, and these m...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9805821/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846128487704821760 |
|---|---|
| author | Shize Huang Jinzhe Qin Ting Tao Lingyu Yang Xiaowen Liu |
| author_facet | Shize Huang Jinzhe Qin Ting Tao Lingyu Yang Xiaowen Liu |
| author_sort | Shize Huang |
| collection | DOAJ |
| description | Perceiving self-vehicle state based on vehicle information can provide key information for unmanned driving and improve vehicle safety monitoring ability. However, existing studies mainly perceive the vehicle state using out-of-vehicle sensors, positioning systems and in-vehicle sensors, and these methods have their own limitations. In recent years, video image processing has been introduced to transportation research. Despite this and the popularity of vehicle videos, self-vehicle state perception based on vehicle videos captured by the drive recorder remains an unworked area. Therefore, this paper proposed a novel method to perceive self-vehicle state which contains “move” and “stop” by calculating the image similarity of the static region between two adjacent video frames. The static region extraction is based on You Only Look At CoefficenTs (YOLACT) instance segmentation model, which can avoid the interference of surroundings like cars and pedestrians. We acquired actual tram vehicle videos to validate our method which can accurately perceive the state and state transition continuously and real-timely in different complex scenes at any time, even if it stops and restarts within only 3 seconds. The approach gives a new thought and inspiration for studies of videos and illustrates that based on vehicle videos we can not only obtain the vehicle’s environment information but also perceive the self-vehicle state. And the proposed approach can be an alternative for estimating self-vehicle state when traditional methods are not available. |
| format | Article |
| id | doaj-art-a4ed0433ba9a44d19021a45d08c469f1 |
| institution | Kabale University |
| issn | 2768-7236 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-a4ed0433ba9a44d19021a45d08c469f12024-12-11T00:07:14ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362022-01-01111110.1109/OJIM.2022.31860519805821A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity CalculationShize Huang0https://orcid.org/0000-0003-3217-7452Jinzhe Qin1https://orcid.org/0000-0002-5116-1483Ting Tao2https://orcid.org/0000-0002-5309-0666Lingyu Yang3https://orcid.org/0000-0001-5536-1880Xiaowen Liu4https://orcid.org/0000-0002-4652-9044Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University, Shanghai, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, ChinaAdministration Office, Cuizhu Sub-District Office of Luohu District, Shenzhen, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, ChinaPerceiving self-vehicle state based on vehicle information can provide key information for unmanned driving and improve vehicle safety monitoring ability. However, existing studies mainly perceive the vehicle state using out-of-vehicle sensors, positioning systems and in-vehicle sensors, and these methods have their own limitations. In recent years, video image processing has been introduced to transportation research. Despite this and the popularity of vehicle videos, self-vehicle state perception based on vehicle videos captured by the drive recorder remains an unworked area. Therefore, this paper proposed a novel method to perceive self-vehicle state which contains “move” and “stop” by calculating the image similarity of the static region between two adjacent video frames. The static region extraction is based on You Only Look At CoefficenTs (YOLACT) instance segmentation model, which can avoid the interference of surroundings like cars and pedestrians. We acquired actual tram vehicle videos to validate our method which can accurately perceive the state and state transition continuously and real-timely in different complex scenes at any time, even if it stops and restarts within only 3 seconds. The approach gives a new thought and inspiration for studies of videos and illustrates that based on vehicle videos we can not only obtain the vehicle’s environment information but also perceive the self-vehicle state. And the proposed approach can be an alternative for estimating self-vehicle state when traditional methods are not available.https://ieeexplore.ieee.org/document/9805821/Image similarityinstance segmentationself-vehiclestate perceptionvehicle~video |
| spellingShingle | Shize Huang Jinzhe Qin Ting Tao Lingyu Yang Xiaowen Liu A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation IEEE Open Journal of Instrumentation and Measurement Image similarity instance segmentation self-vehicle state perception vehicle~video |
| title | A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation |
| title_full | A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation |
| title_fullStr | A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation |
| title_full_unstemmed | A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation |
| title_short | A Novel Method to Perceive Self-Vehicle State Based on Vehicle Video by Image Similarity Calculation |
| title_sort | novel method to perceive self vehicle state based on vehicle video by image similarity calculation |
| topic | Image similarity instance segmentation self-vehicle state perception vehicle~video |
| url | https://ieeexplore.ieee.org/document/9805821/ |
| work_keys_str_mv | AT shizehuang anovelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT jinzheqin anovelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT tingtao anovelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT lingyuyang anovelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT xiaowenliu anovelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT shizehuang novelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT jinzheqin novelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT tingtao novelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT lingyuyang novelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation AT xiaowenliu novelmethodtoperceiveselfvehiclestatebasedonvehiclevideobyimagesimilaritycalculation |