Data filtering with support vector machines in geometric camera calibration

Abstract

The use of non-metric digital cameras in close-range photogrammetric applications and machine vision has become a popular research agenda. Being an essential component of photogrammetric evaluation, camera calibration is a crucial stage for non-metric cameras. Therefore, accurate camera calibration and orientation procedures have become prerequisites for the extraction of precise and reliable 3D metric information from images. The lack of accurate inner orientation parameters can lead to unreliable results in the photogrammetric process. A camera can be well defined with its principal distance, principal point offset and lens distortion parameters. Different camera models have been formulated and used in close-range photogrammetry, but generally sensor orientation and calibration is performed with a perspective geometrical model by means of the bundle adjustment. In this study, support vector machines (SVMs) using radial basis function kernel is employed to model the distortions measured for Olympus Aspherical Zoom lens Olympus E10 camera system that are later used in the geometric calibration process. It is intended to introduce an alternative approach for the on-the-job photogrammetric calibration stage. Experimental results for DSLR camera with three focal length settings (9, 18 and 36 mm) were estimated using bundle adjustment with additional parameters, and analyses were conducted based on object point discrepancies and standard errors. Results show the robustness of the SVMs approach on the correction of image coordinates by modelling total distortions on-the-job calibration process using limited number of images.

Support Vector Regression Machine Learning based Maximum Power Point Tracking for Solar Photovoltaic systems

“…Support vector machines (SVM) were initially built to classify binary issues and were expanded to include the classification and regression of multiclass problems. In the training data set, by estimating the linear or nonlinear relationship between a given input and its associated output, the support vector machine regression (SVMR) technique [31] predicts the output based on the input. As a result, the developed SVMR model may be used to predict outcomes based on supplied inputs.…”

“…dimensional space [31] In other terms, the distance between any data point and the ideal hyperplane is smaller than ε. Where ε represents the radius of the tube.…”

“…The ε-intensive loss function is a function that is used to optimize generalization boundaries that are close to actual value and are located at a particular distance by ignoring errors. As a result, SVMR is defined as the solution to the optimization problem [31] given in Eq. ( 5) and Eq.…”

Parameter calibration of a vision sensor with a geometric similarity constraint

“…Generally speaking, camera calibration consists of two steps. The first step involves the choice of an appropriate camera model, which can be divided into either linear or non-linear, which can be used to describe the behavior of the imaging system [4,5]. The second step is the estimation of all parameters that a certain camera model incorporates, i.e.…”