3D trackletsGPS/IMU inertial navigation systemKITTI datasetVelodyne 3D laser scannerstereo cameras
Figures from the paper
Abstract (AI)
We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10–100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations, and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets, and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide.
Key Findings
1
Dataset covers diverse real-world driving environments ranging from freeways and rural areas to inner-city scenes with many static and dynamic objects.
2
Described the recording platform, data format, and provided utilities to facilitate dataset use by the research community.
3
Included object labels as 3D tracklets and provided online benchmarks for stereo, optical flow, object detection, and other tasks.
4
Introduced a novel large-scale dataset captured from a VW station wagon for mobile robotics and autonomous driving research.
5
Provided calibrated, synchronized, timestamped, rectified and raw image sequences to support precise sensor fusion and algorithm development.
6
Recorded 6 hours of traffic scenarios at 10–100 Hz across multiple sensor modalities including high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner, and a high-precision GPS/IMU.
Research Object
KITTI dataset (sensor recordings from a VW station wagon for mobile robotics and autonomous driving)
Research Subject
Multimodal, calibrated and synchronized sensor data (stereo color/grayscale cameras, Velodyne 3D LiDAR, GPS/IMU) of diverse real-world traffic scenarios with 3D tracklet object labels and benchmarks for tasks such as stereo, optical flow, and object detection
Publication Details
Publication Date
2013-08-23
Journal
Publisher
ISSN
Cited by
9863
Access Type
Author Information
Download PDF
Subscribe to digest
Cited by10
ORB-SLAM: A Versatile and Accurate Monocular SLAM System2015
Object Detection With Deep Learning: A Review2019
Deep learning in optical metrology: a review2022
Sampling-Based Robot Motion Planning: A Review2014
Gibson Env: Real-World Perception for Embodied Agents2018
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research2022
A Comprehensive Survey of Visual SLAM Algorithms2022
Sensors and AI Techniques for Situational Awareness in Autonomous Ships: A Review2020
Road Hazard Stimuli: Annotated naturalistic road videos for studying hazard detection and scene perception2023
Planning and Decision-Making for Autonomous Vehicles2018