Search

Search Results

Zenodo Logo
Zenodo
Kapil, Rudraksh; Marvasti-Zadeh, Seyed Mojtaba; Erbilgin, Nadir; Ray, Nilanjan 2024-01-04 This is the RT-Trees dataset proposed and used in the paper titled, "Shadowsense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection From RGB-Thermal Drone Imagery", published at the IEEE/CVF WACV 2024 conference. Due to the size of the dataset and Zenodo's 50GB limit, the dataset is partitioned into two separate uploads. This upload contains the evaluation splits (test & val), along with the labelled subset of RGB training images used for a supervised training experiment, and the much larger set of unlabelled RGB images used for fully-unsupervised training.  The second upload includes the corresponding unlabelled thermal images used for unsupervised training. https://creativecommons.org/licenses/by/4.0/legalcode
Zenodo Logo
Zenodo
Kapil, Rudraksh; Marvasti-Zadeh, Seyed Mojtaba; Erbilgin, Nadir; Ray, Nilanjan 2024-01-04 This is the RT-Trees dataset proposed and used in the paper titled, "Shadowsense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection From RGB-Thermal Drone Imagery", published at the IEEE/CVF WACV 2024 conference. Due to the size of the dataset and Zenodo's 50GB limit, the dataset is partitioned into two separate uploads. This upload contains the unlabelled thermal images used for unsupervised training The first upload includes evaluation splits (test & val), along with the labelled subset of RGB training images used for a supervised training experiment, and the much larger set of unlabelled RGB images used for fully-unsupervised training. https://creativecommons.org/licenses/by/4.0/legalcode

Map search instructions

1.Turn on the map filter by clicking the “Limit by map area” toggle.
2.Move the map to display your area of interest. Holding the shift key and clicking to draw a box allows for zooming in on a specific area. Search results change as the map moves.
3.Access a record by clicking on an item in the search results or by clicking on a location pin and the linked record title.
Note: Clusters are intended to provide a visual preview of data location. Because there is a maximum of 50 records displayed on the map, they may not be a completely accurate reflection of the total number of search results.