Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds.
Junho KohJaekyum KimJin Hyeok YooYecheol KimDongsuk KumJun Won ChoiPublished in: AAAI (2022)
Keyphrases
- point cloud
- structure from motion
- spatio temporal
- laser scanner
- image representation
- object detection and tracking
- single image
- input image
- high resolution
- image sequences
- lidar data
- image features
- segmentation method
- point sets
- moving objects
- similarity measure
- multi object
- multiple images
- object recognition
- background subtraction
- feature points
- dimensionality reduction
- motion estimation