Datasets
Standard Dataset
LFSD-Dataset
- Citation Author(s):
- Submitted by:
- Shuo Wang
- Last updated:
- Fri, 06/21/2024 - 13:34
- DOI:
- 10.21227/s85q-cf10
- License:
Abstract
Lettuce Farm SLAM Dataset (LFSD) is a VSLAM dataset based on RGB and depth images captured by VegeBot robot in a lettuce farm. The dataset consists of RGB and depth images, IMU, and RTK-GPS sensor data. Detection and tracking of lettuce plants on images are annotated with the standard Multiple Object Tracking (MOT) format. It aims to accelerate the development of algorithms for localization and mapping in the agricultural field, and crop detection and tracking. Supplementary python scripts for converting raw data files (text and JPG image files) to ROS bag files for ROS1 and ROS2 systems, as well as converting MOT annotation files to target detection annotation files, are provided for the convenience of users.
Please refer to the uploaded file Dataset file list_new.pdf for data structure, and refer to the Instructions.pdf document for usage instructions
Dataset Files
- Sequence_5.zip (2.40 GB)
- Sequence_6.zip (2.14 GB)
- Sequence_7.zip (2.27 GB)
- Sequence_8.zip (2.61 GB)
- Sequence_3.zip (4.24 GB)
- Sequence_4.zip (4.59 GB)
- Sequence_2.zip (16.13 GB)
- Sequence_1.zip (22.99 GB)
- image_imu_GPS_to_rosbag.py (5.42 kB)
- MOT_to_VOC.py (6.57 kB)
Documentation
Attachment | Size |
---|---|
Instructions.pdf | 525.86 KB |
Dataset file list_new.pdf | 290.17 KB |
Comments
How to combine the sequence which is divided in parts to use for orb slam 3?