└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Event-based Camera Datasets 2 | 3 | ## Survey Papers 4 | - _[Event-based Vision: A Survey](http://rpg.ifi.uzh.ch/docs/EventVisionSurvey.pdf)_, IEEE Trans. Pattern Anal. Machine Intell. (TPAMI), 2020. 5 | 6 | ## List of Datasets: 7 | - From Real Scenes 8 | - DAVIS Data [Dataset](http://rpg.ifi.uzh.ch/davis_data.html)   size:~10GB
9 | paper name: _[The event-camera dataset and simulator: Event-based data for pose estimation, visual odometry, and SLAM](https://journals.sagepub.com/doi/full/10.1177/0278364917691115)_, IJRR, 2017.
10 | features : to motivate research on new algorithms for high-speed and high-dynamic-range, ground-truth camera poses from a motion-capture, 11 | a simulator that released open-source to create synthetic event-camera data.
12 | task: __SLAM__
13 | devices：DAVIS240C, motion-capture system 14 | 15 | - EED [Dataset](http://prg.cs.umd.edu/BetterFlow.html)   size:59MB
16 | paper name: _[Event-based Moving Object Detection and Tracking](https://ieeexplore.ieee.org/abstract/document/8593805)_, IROS, 2018.
17 | features : objects of multiple sizes moving at different speeds in a variety of lighting conditions indoor
18 | task: __moving object detection,__ __moving object tracking__
19 | devices：DAVIS240B 20 | 21 | - MVSEC [Dataset](https://daniilidis-group.github.io/mvsec)   size:~30G
22 | paper name: _[The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://ieeexplore.ieee.org/abstract/document/8288670)_, IEEE Robot. Autom. Lett.(RA-L), 2018.
23 | features : a synchronized stereo pair event based camera system, carried on a handheld rig, flown by a hexacopter, driven on top of a car, and mounted on a motorcycle,in a variety of different illumination levels and environments
24 | task: __SLAM__
25 | devices：DAVIS m346B(stereo), VI-Sensor(stereo), Velodyne Puck LITE,GPS 26 | 27 | - EV-IMO [Dataset](http://prg.cs.umd.edu/EV-IMO.html)   size:~30G
28 | paper name: _[EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras](https://ieeexplore.ieee.org/abstract/document/8968520)_, IROS, 2019.
29 | features : 32 minutes of indoor recording with up to 3 fast moving objects in the camera field of view, including accurate pixel-wise motion masks, egomotion and ground truth depth. suitable for learning approach for motion segmentation in indoor scenes
30 | task: __motion segmentation__
31 | devices：DAVIS 346C 32 | 33 | - DSEC [Dataset](http://rpg.ifi.uzh.ch/dsec.html)   size:~150G
34 | paper name: _[DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://ieeexplore.ieee.org/abstract/document/9387069)_, IEEE Robot. Autom. Lett.(RA-L),2021.
35 | features :driving under challenging illumination conditions such as night, sunrise, and sunset
36 | task: __SLAM__
37 | devices: stereo event camera(2x Prophesee Gen3.1), GNSS, LiDAR, stereo RGB camera 38 | 39 | - TUM-VIE [Dataset](https://go.vision.in.tum.de/tumvie)   size:~300G
40 | paper name: _[TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset](https://ieeexplore.ieee.org/abstract/document/9636728)_, IROS,2021. 41 |
42 | features : handheld and head-mounted sequences in indoor and outdoor environments, including rapid motion during sports and high dynamic range scenarios
43 | task: __SLAM__
44 | devices: stereo event camera(2x Prophesee Gen4-CD), motion capture, IMU, stereo RGB camera 45 | 46 | - EventScape [Dataset](http://rpg.ifi.uzh.ch/RAMNet.html)   size:~70G
47 | paper name: _[Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction](https://ieeexplore.ieee.org/abstract/document/9359329)_, RA-L,2021. 48 |
49 | features : events, intensity frames, semantic labels, and depth maps recorded in the CARLA simulator
50 | task: __SLAM，__ __semantic segmentation，__ __depth estimation__
51 | devices: CARLA simulator 52 | 53 | - ViViD++ [Dataset](https://visibilitydataset.github.io/)   size:more than 250min
54 | paper name: _[ViViD++ : Vision for Visibility Dataset](https://ieeexplore.ieee.org/abstract/document/9760091)_, RA-L,2022. 55 |
56 | features : developing robust visual SLAM under poor illumination
57 | devices1: mono event camera(Handheld DAVIS240C),Thermal,IMU,RGB-D
58 | devices2: mono event camera(Driving DVXplorer),Thermal,RGB,RTK-GPS,Ouster OS1 LiDAR 59 | 60 | - EV-IMO [Dataset](http://prg.cs.umd.edu/EV-IMO.html)   size:~40G
61 | paper name: _[EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms](https://arxiv.org/abs/2205.03467)_, arxiv, 2022.
62 | features : temporal synchronization between sensors, less jitter, and a more efficient npz format
63 | task: __motion segmentation,__ __SfM,__ __Object Recognition__
64 | devices：2x Prophesee Gen3， Samsung Gen3, Prophesee ATIS Gen3 65 | - UZH-FPV ... 66 | - MOD ... 67 | 68 | - From Static Pictures 69 | - N-Caltech101 70 | - N-Cars 71 | 72 | ## Rank by Citations 73 | [EED](#EED)     _202_
74 | [DSEC](#DSEC)     _76_
75 | [TUM-VIE](#TUM-VIE)    _19_
76 | [ViViD++](#ViViD++)     _12_
77 | 78 | ## Related Links 79 | [Teams and researchers in China](https://github.com/LarryDong/EventCameraGroupsCN)
80 | [Event-based Resources](https://github.com/uzh-rpg/event-based_vision_resources)
81 | [Event-SLAM Hong Kong University](https://github.com/arclab-hku/Event_based_VO-VIO-SLAM) 82 | --------------------------------------------------------------------------------