Detecting partially occluded vehicles with geometric and likelihood reasoning
In real‐world scenes, vehicles are frequently overlapped by other objects and various backgrounds. In this study, an effective method to detect such vehicles, especially those partially occluded by nearby vehicles or other objects is presented. The authors have developed a statistical approach to ge...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2015-04-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2013.0334 |
_version_ | 1797684789990391808 |
---|---|
author | Teng Yu Hyunchul Shin |
author_facet | Teng Yu Hyunchul Shin |
author_sort | Teng Yu |
collection | DOAJ |
description | In real‐world scenes, vehicles are frequently overlapped by other objects and various backgrounds. In this study, an effective method to detect such vehicles, especially those partially occluded by nearby vehicles or other objects is presented. The authors have developed a statistical approach to generate occlusion hypothesis and a new hypothesis verification method. To verify occlusion hypothesis, the verification method utilises geometric and likelihood information. In this way, both vehicle–background and vehicle–vehicle occlusions can be detected. No additional occlusion‐specific training is required. In addition, a median filter is applied to eliminate the noise in the patch scoring, and a union‐find algorithm is used to find the connected positive region in the binary map. A synthesised occlusion dataset is created to test the performance, and the experimental results on popular benchmarks indicate that the proposed method is effective and robust in recognising partially occluded vehicles. |
first_indexed | 2024-03-12T00:35:49Z |
format | Article |
id | doaj.art-23366d77346c409797636d5136c5361b |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:35:49Z |
publishDate | 2015-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-23366d77346c409797636d5136c5361b2023-09-15T09:37:33ZengWileyIET Computer Vision1751-96321751-96402015-04-019217418310.1049/iet-cvi.2013.0334Detecting partially occluded vehicles with geometric and likelihood reasoningTeng Yu0Hyunchul Shin1School of Electronics and Communication EngineeringHanyang UniversityAnsanRepublic of KoreaSchool of Electronics and Communication EngineeringHanyang UniversityAnsanRepublic of KoreaIn real‐world scenes, vehicles are frequently overlapped by other objects and various backgrounds. In this study, an effective method to detect such vehicles, especially those partially occluded by nearby vehicles or other objects is presented. The authors have developed a statistical approach to generate occlusion hypothesis and a new hypothesis verification method. To verify occlusion hypothesis, the verification method utilises geometric and likelihood information. In this way, both vehicle–background and vehicle–vehicle occlusions can be detected. No additional occlusion‐specific training is required. In addition, a median filter is applied to eliminate the noise in the patch scoring, and a union‐find algorithm is used to find the connected positive region in the binary map. A synthesised occlusion dataset is created to test the performance, and the experimental results on popular benchmarks indicate that the proposed method is effective and robust in recognising partially occluded vehicles.https://doi.org/10.1049/iet-cvi.2013.0334occlusion dataset synthesisbinary mappositive regionunion-flnd algorithmpatch scoringnoise elimination |
spellingShingle | Teng Yu Hyunchul Shin Detecting partially occluded vehicles with geometric and likelihood reasoning IET Computer Vision occlusion dataset synthesis binary map positive region union-flnd algorithm patch scoring noise elimination |
title | Detecting partially occluded vehicles with geometric and likelihood reasoning |
title_full | Detecting partially occluded vehicles with geometric and likelihood reasoning |
title_fullStr | Detecting partially occluded vehicles with geometric and likelihood reasoning |
title_full_unstemmed | Detecting partially occluded vehicles with geometric and likelihood reasoning |
title_short | Detecting partially occluded vehicles with geometric and likelihood reasoning |
title_sort | detecting partially occluded vehicles with geometric and likelihood reasoning |
topic | occlusion dataset synthesis binary map positive region union-flnd algorithm patch scoring noise elimination |
url | https://doi.org/10.1049/iet-cvi.2013.0334 |
work_keys_str_mv | AT tengyu detectingpartiallyoccludedvehicleswithgeometricandlikelihoodreasoning AT hyunchulshin detectingpartiallyoccludedvehicleswithgeometricandlikelihoodreasoning |