Loading...

Trajectory Estimation of a Vehicle Using Stereo Cameras

Eftekhar, Parham | 2020

787 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52766 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Moghadasi, Reza
  7. Abstract:
  8. Visual odometry(VO) is the process of estimating the egomotion of an agent(e.g., vehicle, human, and robot) using the input of a single or multiple cameras attached to it. Application domains include robotics, wearable computing, augmented reality, and automotive. The term was chosen for its similarity to wheel odometry, which incrementally estimates the motion of a vehicle by integrating the number of turns of its wheels over time. Likewise, VO operates by incrementally estimating the pose of the vehicle through examination of the changes that movements induces on the images of its onboard cameras. For the VO to work effectively, there should be sufficient illumination in the environment and a static scene with sufficient texture to allow apparent motion to be extracted. Furthermore, consecutive frames should be captured by ensuring that they have sufficient scene overlap. In this Thesis, we examine a novel algorithm for fast and robust stereo visual odometry based on feature selection and tracking. the reduction of drift is based on careful selection of a subset of stable features and their tracking through the frames. Experimental results on the KITTI Vision Benchmark Suit are presented which indicate the algorithm rank among the best visual odometry algorithms proposed at the time
  9. Keywords:
  10. Visual Odometry ; Feature Selection ; Egomotion Estimation ; Features Tracking ; Motion Estimation

 Digital Object List