Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments
In this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points extracted during a predetermined time interval. The f...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/1/92 |
| _version_ | 1811302128555130880 |
|---|---|
| author | Keon-woo Park Yoo-Jeong Shim Myeong-jin Lee Heejune Ahn |
| author_facet | Keon-woo Park Yoo-Jeong Shim Myeong-jin Lee Heejune Ahn |
| author_sort | Keon-woo Park |
| collection | DOAJ |
| description | In this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points extracted during a predetermined time interval. The feature point with the largest blob response in each quantized location bin, a representative feature point, is used for matching a pair of video sequences. After matching representative feature points from each camera, the homography for the interval is estimated by random sample consensus (RANSAC) on the matched representative feature points, with their chances of being sampled proportional to their numbers of occurrences in the interval. The performance of the proposed method is compared with that of the per-frame method by investigating alignment distortion and stitching scores for daytime and noisy video sequence pairs. It is shown that alignment distortion in overlapping regions is reduced and the stitching score is improved by the proposed method. The proposed method can be used for panoramic video stitching with static video cameras and for panoramic image stitching with less alignment distortion. |
| first_indexed | 2024-04-13T07:22:32Z |
| format | Article |
| id | doaj.art-8eff667904ef4b48a9540b761ad41d4a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:22:32Z |
| publishDate | 2019-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8eff667904ef4b48a9540b761ad41d4a2022-12-22T02:56:35ZengMDPI AGSensors1424-82202019-12-012019210.3390/s20010092s20010092Multi-Frame Based Homography Estimation for Video Stitching in Static Camera EnvironmentsKeon-woo Park0Yoo-Jeong Shim1Myeong-jin Lee2Heejune Ahn3The Information Technology & Mobile Communications Biz., Samsung Electronics, Suwon-si, Gyeonggi-do 16677, KoreaSchool of Electronics and Information Engineering, Korea Aerospace University, Goyang-si, Gyeonggi-do 10540, KoreaSchool of Electronics and Information Engineering, Korea Aerospace University, Goyang-si, Gyeonggi-do 10540, KoreaDept of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul 01811, KoreaIn this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points extracted during a predetermined time interval. The feature point with the largest blob response in each quantized location bin, a representative feature point, is used for matching a pair of video sequences. After matching representative feature points from each camera, the homography for the interval is estimated by random sample consensus (RANSAC) on the matched representative feature points, with their chances of being sampled proportional to their numbers of occurrences in the interval. The performance of the proposed method is compared with that of the per-frame method by investigating alignment distortion and stitching scores for daytime and noisy video sequence pairs. It is shown that alignment distortion in overlapping regions is reduced and the stitching score is improved by the proposed method. The proposed method can be used for panoramic video stitching with static video cameras and for panoramic image stitching with less alignment distortion.https://www.mdpi.com/1424-8220/20/1/92homography estimationvideo stitchingmulti-frame based homographyrepresentative feature pointvideo alignment |
| spellingShingle | Keon-woo Park Yoo-Jeong Shim Myeong-jin Lee Heejune Ahn Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments Sensors homography estimation video stitching multi-frame based homography representative feature point video alignment |
| title | Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments |
| title_full | Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments |
| title_fullStr | Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments |
| title_full_unstemmed | Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments |
| title_short | Multi-Frame Based Homography Estimation for Video Stitching in Static Camera Environments |
| title_sort | multi frame based homography estimation for video stitching in static camera environments |
| topic | homography estimation video stitching multi-frame based homography representative feature point video alignment |
| url | https://www.mdpi.com/1424-8220/20/1/92 |
| work_keys_str_mv | AT keonwoopark multiframebasedhomographyestimationforvideostitchinginstaticcameraenvironments AT yoojeongshim multiframebasedhomographyestimationforvideostitchinginstaticcameraenvironments AT myeongjinlee multiframebasedhomographyestimationforvideostitchinginstaticcameraenvironments AT heejuneahn multiframebasedhomographyestimationforvideostitchinginstaticcameraenvironments |