Search Constraints
« Previous |
11 - 16 of 16
|
Next »
Number of results to display per page
View results as:
Search Results
-
- Creator:
- Skinner, Katherine A., Vasudevan, Ram, Ramanagopal, Manikandasriram S., Ravi, Radhika, Carmichael, Spencer, and Buchan, Austin D.
- Description:
- This dataset is part of a collection created to facilitate research in the use of novel sensors for autonomous vehicle perception. , The dataset collection platform is a Ford Fusion vehicle with a roof-mounted novel sensing suite, which specifically consists of forward-facing stereo uncooled thermal cameras (FLIR 40640U050-6PAAX), event cameras (iniVation DVXplorer), monochrome cameras (FLIR BFS-PGE-16S2M), and RGB cameras (FLIR BFS-PGE-50S5C) time synchronized with ground truth poses from a high precision navigation system. , Further information and resources (such as software tools for converting, managing, and viewing data files) are available on the project website: https://umautobots.github.io/nsavp , and CHANGE NOTICE (January 2024): We identified an error in our timestamp post-processing procedure that caused all camera timestamps to be offset by the exposure time of one of the cameras. We corrected the error, applied the corrected post-processing, and reuploaded the corrected files. The change impacts all camera data files. Prior to the change, the timestamps between the cameras were synchronized with submillisecond accuracy, but the camera and ground truth pose timestamps were offset by up to 0.4 ms, 3 ms, and 15 ms in the afternoon, sunset, and night sequences, respectively. This amounted in up to ~0.25 meters of position error in the night sequences. For consistency, camera calibration was rerun with the corrected calibration sequence files. The camera calibration results have therefore been updated as well, although they have not changed significantly. Finally, we previously downsampled the frame data in the uploaded calibration seqeuence, but we decided to provide the full frame data in the reupload.
- Keyword:
- novel sensing, perception, autonomous vehicles, thermal sensing, neuromorphic imaging, and event cameras
- Citation to related publication:
- https://sites.google.com/umich.edu/novelsensors2023, https://github.com/umautobots/nsavp_tools, and https://umautobots.github.io/nsavp
- Discipline:
- Engineering
-
Novel Sensors for Autonomous Vehicle Perception
User Collection
- Creator:
- Skinner, Katherine A, Vasudevan, Ram, Ramanagopal, Manikandasriram S, Ravi, Radhika, Buchan, Austin D, and Carmichael, Spencer
- Description:
- The Novel Sensors for Autonomous Vehicle Perception Collection of datasets are sequences collected with an autonomous vehicle platform including data from novel sensors. The dataset collection platform is a Ford Fusion vehicle with a roof-mounted novel sensing suite, which specifically consists of forward-facing stereo uncooled thermal cameras (FLIR 40640U050-6PAAX), event cameras (iniVation DVXplorer), monochrome cameras (FLIR BFS-PGE-16S2M), and RGB cameras (FLIR BFS-PGE-50S5C) time synchronized with ground truth poses from a high precision navigation system. Sequences include ~8 km routes, driven repeatedly under varying lighting conditions and/or opposing viewpoints. Further information and resources are available on the project website: https://umautobots.github.io/nsavp
- Keyword:
- novel sensing, perception, autonomous vehicles, thermal sensing, neuromorphic imaging, and event cameras
- Citation to related publication:
- https://umautobots.github.io/nsavp, https://github.com/umautobots/nsavp_tools, and https://sites.google.com/umich.edu/novelsensors2023
- Discipline:
- Engineering
12Works -
- Creator:
- Skinner, Katherine A. , Vasudevan, Ram, Ramanagopal, Manikandasriram S., Ravi, Radhika, Carmichael, Spencer, and Buchan, Austin D.
- Description:
- This dataset is part of a collection released in support of an IROS 2023 workshop publication, with a supporting website ( https://sites.google.com/umich.edu/novelsensors2023). To enable new research in the area of novel sensors for autonomous vehicles, these datasets are designed for the task of place recognition with novel sensors. To our knowledge, this new dataset is the first to include stereo thermal cameras together with stereo event cameras and stereo monochrome cameras, which perform better in low-light than RGB cameras., The dataset collection platform is a Ford Fusion vehicle with roof-mounted sensing suite, which consists of forward-facing stereo uncooled thermal cameras (FLIR Boson 640+ ADK), event cameras (iniVation DVXplorer), monochrome cameras (FLIR BFS-PGE-16S2M), and RGB cameras (FLIR BFS-PGE-50S5C) aligned with ground truth position from a high precision navigation system. Sequences include ~10 km routes, which may be driven repeatedly under varying lighting conditions and feature instances of direct sunlight and low-light that challenge conventional cameras., and A software toolkit to facilitate efficient use of the dataset including dataset download, application of calibration parameters, and evaluation of place recognition results based on standard metrics (e.g., maximum recall at 100% precision). These software tools for converting, managing, and viewing datafiles can be found at the associated GitHub repository ( https://github.com/umautobots/nsavp_tools).
- Keyword:
- novel sensing, perception, autonomous vehicles, thermal sensing, neuromorphic imaging, and event cameras
- Citation to related publication:
- https://sites.google.com/umich.edu/novelsensors2023 and https://github.com/umautobots/nsavp_tools
- Discipline:
- Engineering
-
- Creator:
- Skinner, Katherine A. , Vasudevan, Ram, Ramanagopal, Manikandasriram S., Ravi, Radhika, Carmichael, Spencer, and Buchan, Austin D.
- Description:
- This dataset is part of a collection released in support of an IROS 2023 workshop publication, with a supporting website ( https://sites.google.com/umich.edu/novelsensors2023). To enable new research in the area of novel sensors for autonomous vehicles, these datasets are designed for the task of place recognition with novel sensors. To our knowledge, this new dataset is the first to include stereo thermal cameras together with stereo event cameras and stereo monochrome cameras, which perform better in low-light than RGB cameras., The dataset collection platform is a Ford Fusion vehicle with roof-mounted sensing suite, which consists of forward-facing stereo uncooled thermal cameras (FLIR Boson 640+ ADK), event cameras (iniVation DVXplorer), monochrome cameras (FLIR BFS-PGE-16S2M), and RGB cameras (FLIR BFS-PGE-50S5C) aligned with ground truth position from a high precision navigation system. Sequences include ~10 km routes, which may be driven repeatedly under varying lighting conditions and feature instances of direct sunlight and low-light that challenge conventional cameras., and A software toolkit to facilitate efficient use of the dataset including dataset download, application of calibration parameters, and evaluation of place recognition results based on standard metrics (e.g., maximum recall at 100% precision). These software tools for converting, managing, and viewing datafiles can be found at the associated GitHub repository ( https://github.com/umautobots/nsavp_tools).
- Keyword:
- novel sensing, perception, autonomous vehicles, thermal sensing, neuromorphic imaging, and event cameras
- Citation to related publication:
- https://sites.google.com/umich.edu/novelsensors2023 and https://github.com/umautobots/nsavp_tools
- Discipline:
- Engineering
-
- Creator:
- Kim, Wonhui, Ramanagopal, Manikandasriram Srinivasan, Barto, Charles , Yu, Ming-Yuan, Rosaen, Karl , Goumas, Nick , Vasudevan, Ram, and Johnson-Roberson, Matthew
- Description:
- PedX is a large-scale multi-modal collection of pedestrians at complex urban intersections. The dataset provides high-resolution stereo images and LiDAR data with manual 2D and automatic 3D annotations. The data was captured using two pairs of stereo cameras and four Velodyne LiDAR sensors.
- Citation to related publication:
- https://doi.org/10.48550/arXiv.1809.03605, https://github.com/umautobots/pedx, and http://pedx.io/
- Discipline:
- Engineering
-
- Creator:
- Vasudevan, Ram, Barto, Charles, Rosaen, Karl, Mehta, Rounak, Matthew, Johnson-Roberson, and Nittur Sridhar, Sharath
- Description:
- A dataset for computer vision training obtained from long running computer simulations
- Keyword:
- autonomous driving, simulation, Computer Vision and Pattern Recognition, deep learning, Computer Science, object detection, and Robotics
- Citation to related publication:
- M. Johnson-Roberson, C. Barto, R. Mehta, S. N. Sridhar, K. Rosaen and R. Vasudevan, "Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks?," 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017, pp. 746-753. Available at https://arxiv.org/abs/1610.01983 and https://doi.org/10.1109/ICRA.2017.7989092
- Discipline:
- Engineering