Diverse Scene Stitching from a Large-Scale Aerial Video Dataset
Diverse scene stitching is a challenging task in aerial video surveillance. This paper presents a hybrid stitching method based on the observation that aerial videos captured in real surveillance settings are neither totally ordered nor completely unordered. Often, human operators apply continuous m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/7/6/6932 |
| _version_ | 1818960255120310272 |
|---|---|
| author | Tao Yang Jing Li Jingyi Yu Sibing Wang Yanning Zhang |
| author_facet | Tao Yang Jing Li Jingyi Yu Sibing Wang Yanning Zhang |
| author_sort | Tao Yang |
| collection | DOAJ |
| description | Diverse scene stitching is a challenging task in aerial video surveillance. This paper presents a hybrid stitching method based on the observation that aerial videos captured in real surveillance settings are neither totally ordered nor completely unordered. Often, human operators apply continuous monitoring of the drone to revisit the same area of interest. This monitoring mechanism yields to multiple short, successive video clips that overlap in either time or space. We exploit this property and treat the aerial image stitching problem as temporal sequential grouping and spatial cross-group retrieval. We develop an effective graph-based framework that can robustly conduct the grouping, retrieval and stitching tasks. To evaluate the proposed approach, we experiment on the large-scale VIRATaerial surveillance dataset, which is challenging for its heterogeneity in image quality and diversity of the scene. Quantitative and qualitative comparisons with state-of-the-art algorithms show the efficiency and robustness of our technique. |
| first_indexed | 2024-12-20T11:54:37Z |
| format | Article |
| id | doaj.art-f6f4ec4d50c84532b75b00fdeb77b156 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T11:54:37Z |
| publishDate | 2015-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f6f4ec4d50c84532b75b00fdeb77b1562022-12-21T19:41:41ZengMDPI AGRemote Sensing2072-42922015-05-01766932694910.3390/rs70606932rs70606932Diverse Scene Stitching from a Large-Scale Aerial Video DatasetTao Yang0Jing Li1Jingyi Yu2Sibing Wang3Yanning Zhang4Shaanxi Provincial Key Lab of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, ChinaSchool of Telecommunications Engineering, Xidian University, Xi'an, ChinaNewark, NJ 19711, USA" to "Newark, DE 19711, USAShaanxi Provincial Key Lab of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, ChinaShaanxi Provincial Key Lab of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, ChinaDiverse scene stitching is a challenging task in aerial video surveillance. This paper presents a hybrid stitching method based on the observation that aerial videos captured in real surveillance settings are neither totally ordered nor completely unordered. Often, human operators apply continuous monitoring of the drone to revisit the same area of interest. This monitoring mechanism yields to multiple short, successive video clips that overlap in either time or space. We exploit this property and treat the aerial image stitching problem as temporal sequential grouping and spatial cross-group retrieval. We develop an effective graph-based framework that can robustly conduct the grouping, retrieval and stitching tasks. To evaluate the proposed approach, we experiment on the large-scale VIRATaerial surveillance dataset, which is challenging for its heterogeneity in image quality and diversity of the scene. Quantitative and qualitative comparisons with state-of-the-art algorithms show the efficiency and robustness of our technique.http://www.mdpi.com/2072-4292/7/6/6932diverse scene stitchingcross-group retrievalaerial image stitchingaerial video surveillance |
| spellingShingle | Tao Yang Jing Li Jingyi Yu Sibing Wang Yanning Zhang Diverse Scene Stitching from a Large-Scale Aerial Video Dataset Remote Sensing diverse scene stitching cross-group retrieval aerial image stitching aerial video surveillance |
| title | Diverse Scene Stitching from a Large-Scale Aerial Video Dataset |
| title_full | Diverse Scene Stitching from a Large-Scale Aerial Video Dataset |
| title_fullStr | Diverse Scene Stitching from a Large-Scale Aerial Video Dataset |
| title_full_unstemmed | Diverse Scene Stitching from a Large-Scale Aerial Video Dataset |
| title_short | Diverse Scene Stitching from a Large-Scale Aerial Video Dataset |
| title_sort | diverse scene stitching from a large scale aerial video dataset |
| topic | diverse scene stitching cross-group retrieval aerial image stitching aerial video surveillance |
| url | http://www.mdpi.com/2072-4292/7/6/6932 |
| work_keys_str_mv | AT taoyang diversescenestitchingfromalargescaleaerialvideodataset AT jingli diversescenestitchingfromalargescaleaerialvideodataset AT jingyiyu diversescenestitchingfromalargescaleaerialvideodataset AT sibingwang diversescenestitchingfromalargescaleaerialvideodataset AT yanningzhang diversescenestitchingfromalargescaleaerialvideodataset |