Pushbroom stereo for high-speed navigation in cluttered environments
By Andrew J. Barry, Russ Tedrake. 2014
103 citations recorded by the source corpus.
We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile ARM processor at 120 frames per second. Our system performs a subset of standard block-matching stereo processing, searching only for obstacles at a single depth. By using an onboard IMU and state-estimator, we can recover the position of obstacles at all other depths, building and updating a local depth-map at framerate. Here, we describe both the algorithm and our implementation on a high-speed, small UAV, flying at over 20 MPH (9 m/s) close to obstacles. The system requires no external sensing or computation and is, to the best of our knowledge, the first high-framerate stereo detection system running onboard a small UAV.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition
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
- Sergey Levine
- Fereshteh Sadeghi
- Pieter Abbeel
- Chelsea Finn
- Abhinav Kumar Gupta
- Lei Tai
- Vikash Kumar
- Saurabh Gupta
In Computer Vision and Pattern Recognition
- Sergey Levine
- Fereshteh Sadeghi
- Pieter Abbeel
- Abhinav Kumar Gupta
- Chelsea Finn
- Luc Van Gool
- Jitendra Malik
- Trevor Darrell
Citations in the corpus
- (CAD)$^2$RL: Real Single-Image Flight without a Single Real Image (2016, methodology): “ometry, and then compute a collisionfree path for reaching the destination [29]. This approach benefits from independent developments in mapping and localization as well as motion planning [28], [20], [4]. The 3D geometry of the local environment can be deduced using SLAM with range sensors [3], cons”