University of Michigan North Campus long-term vision and lidar dataset

By Nicholas Carlevaris-Bianco, Arash K. Ushani, Ryan M. Eustice. 2016

643 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Environmental Engineering, Geology, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Fu Zhang
2. Cyrill Stachniss
3. Jens Behley
4. Giseop Kim
5. Jiarong Lin
6. Ayoung Kim
7. Ignacio Vizzo
8. Dongjiao He

In Computer Vision and Pattern Recognition

1. Ayoung Kim
2. Giseop Kim
3. Jens Behley
4. Cyrill Stachniss
5. Roberto Arroyo
6. Dongjiao He
7. Cheng Wang
8. Jiarong Lin

In Environmental Engineering

1. Fu Zhang
2. Cyrill Stachniss
3. Jens Behley
4. Ignacio Vizzo
5. Jiarong Lin
6. Giseop Kim
7. Cheng Wang
8. Roberto Arroyo

In Geology

1. Fu Zhang
2. Cyrill Stachniss
3. Giseop Kim
4. Ayoung Kim
5. Jens Behley
6. Jiarong Lin
7. Dongjiao He
8. Wei Xu

In Evaluation & Benchmarks

1. Cheng Wang
2. Yonina C. Eldar
3. Saifullahi Aminu Bello
4. Shangshu Yu
5. Ignacio Vizzo
6. Cyrill Stachniss
7. Pablo Fernández Alcantarilla
8. Nir Shlezinger

Citations in the corpus

• Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map (2018, methodology): “We use the KITTI dataset 2 [27], the NCLT dataset [28], and the Complex Urban LiDAR dataset 4 [29] for the validation of our method.”
• Street-view change detection with deconvolutional networks (2016, background): “For example, two datasets have been recently made publicly available to the robotics community (Carlevaris-Bianco et al. 2015;Maddern et al. 2016).”
• Review: deep learning on 3D point clouds (2020, methodology): “This was developed by the University of Michigan [123].”
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics (2021, methodology): “In our final experiment we evaluate KalmanNet on the Michigan NCLT data set [28].”
• MulRan: Multimodal Range Dataset for Urban Place Recognition (2020, neutral): “TABLE I: Dataset comparison with respect to range sensor configuration and fitness for place recognition study Datasets Freiburg[3] [4] KITTI[5] NCLT[6] [7] nuScenes[8] Marulan[9] Oxford Radar Robotcar [10] Among range-measuring sensors, LiDAR has been widely adopted in robotics including autonomous c”
• FAST-LIO2: Fast Direct LiDAR-Inertial Odometry (2021, background): “The last one, “nclt” [59] is a large-scale, long-term autonomy UGV (unmanned ground vehicle) dataset collected in the University of Michigan’s North Campus.”
• KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done the Right Way (2022, methodology): “For that, we use the MulRan dataset [15], a handheld device [22], and a segway dataset [5].”
• The TUM VI Benchmark for Evaluating Visual-Inertial Odometry (2018, neutral): “UMich NCLT [11] 2015 in/outdoors Segway 6 RGB (omni) 1600x1200 @5Hz 3-axis acc/gyro @100Hz sw fused GPS/IMU/laser pose @150Hz, acc≈10cm 27 seqs, 147.”
• TartanAir: A Dataset to Push the Limits of Visual SLAM (2020, neutral): “Dataset Sensors/Ground Truth Label Conditions Motion Pattern Seq Num Stereo Flow Depth Lidar Pose Light Weather Season DynObj KITTI [12] � � � � � � Car 22 Virtual KITTI [21] � � � � � � Car 50 EuRoC MAV [14] � � � MAV 11 TUM RGB-D [13] � � � Hand 15 ICL-NUM [28] � � Hand 8 SceneNet [20] � � � � Ran”