Module 1 Graded Quiz >>> What is the most ACCURATE and PRECISE definition of the camera obscura >>> Visual Perception for Self-Driving Cars
Correct! Camera obscura, which translates to Dark Room Camera in English, is a simple construction with a pinhole aperture in front of an imaging surface.
================================
Correct! Camera extrinsic parameters indeed define the transformations from 3D world coordinates to 3D camera coordinates.
Correct! Camera extrinsic parameters encompass both a rotation matrix and translation vector.
Correct! Recall that the epipolar line helps us to constrain the correspondence search to be along the epipolar line, reducing the search from 2D to 1D.
================================
15.
Question 15
Which of these 3X3 image filters is a Gaussian filter?
Correct answer: Filter 2
================================
Correct! Determining the camera location using its intrinsic and extrinsic parameters is extensively used in the self-driving car domain, for visual odometry for example.
Correct! Camera intrinsic and extrinsic parameters can be used for locating 3D points on a 2D image coordinate frame as well as locating 2D points in a 3D world coordinate system.
Correct! Some complex camera calibration methods allow modeling and estimation of various sophisticated camera parameters such as radial distortion.
Correct! Camera calibration is used to compute camera parameters whether in form of projection matrix or in form of intrinsic and extrinsic matrices.
================================
Correct. Knowledge of the baseline between two camera centers allows the measurements of the same point in each image to be triangulated to identify depth, in the process known as Stereopsis.
================================
Correct! Singular Value Decomposition is the way to go. This problem might also be solved with RQ factorization.
Correct! The focal length is needed to calibrate the stereo camera system.
Correct! The baseline, and the x and y offsets are needed to calibrate the stereo camera system.
================================
Correct! Linear calibration model does not directly provide the intrinsic and extrinsic camera parameters.
Correct! The linear calibration model does not allow us to impose constraints on the solution, such as requiring the focal length to be non-negative.
Correct! The linear calibration model does not take into account complex phenomena such as radial and tangential distortion.
Correct! An exhaustive search for the stereo correspondence takes considerable amount of computation time.
Correct! An exhaustive search for a stereo correspondence finds too many matches, which means that this strategy is unlikely to succeed.
================================
Correct! This is correct order for computing disparity in a pair of stereo images.
================================
Correct! Convolution is associative.
Correct! You can see this from the convolution and cross-correlation equations.
Correct! You can see this from the convolution and cross-correlation equations.
================================
9.
Question 9
Consider a stereo camera setup in the figures below, similar to what you saw in the course slides.
Which of the statement about this configuration are correct? Select all that apply.
