View Javadoc
1   /*
2    * Copyright (C) 2017 Alberto Irurueta Carro (alberto@irurueta.com)
3    *
4    * Licensed under the Apache License, Version 2.0 (the "License");
5    * you may not use this file except in compliance with the License.
6    * You may obtain a copy of the License at
7    *
8    *         http://www.apache.org/licenses/LICENSE-2.0
9    *
10   * Unless required by applicable law or agreed to in writing, software
11   * distributed under the License is distributed on an "AS IS" BASIS,
12   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   * See the License for the specific language governing permissions and
14   * limitations under the License.
15   */
16  package com.irurueta.geometry.refiners;
17  
18  import com.irurueta.algebra.Matrix;
19  import com.irurueta.geometry.HomogeneousPoint2D;
20  import com.irurueta.geometry.Line2D;
21  import com.irurueta.geometry.estimators.LockedException;
22  import com.irurueta.geometry.estimators.NotReadyException;
23  import com.irurueta.numerical.EvaluationException;
24  import com.irurueta.numerical.GradientEstimator;
25  import com.irurueta.numerical.fitting.LevenbergMarquardtMultiDimensionFitter;
26  import com.irurueta.numerical.fitting.LevenbergMarquardtMultiDimensionFunctionEvaluator;
27  import com.irurueta.numerical.robust.InliersData;
28  
29  import java.util.BitSet;
30  import java.util.List;
31  
32  /**
33   * Refines an homogeneous 2D point by taking into account an initial estimation,
34   * inlier samples and their residuals.
35   * This class can be used to find a solution that minimizes error of inliers in
36   * LMSE terms.
37   * Typically, a refiner is used by a robust estimator, however it can also be
38   * useful in some other situations.
39   */
40  @SuppressWarnings("DuplicatedCode")
41  public class HomogeneousPoint2DRefiner extends Point2DRefiner<HomogeneousPoint2D> {
42  
43      /**
44       * Constructor.
45       */
46      public HomogeneousPoint2DRefiner() {
47      }
48  
49      /**
50       * Constructor.
51       *
52       * @param initialEstimation           initial estimation to be set.
53       * @param keepCovariance              true if covariance of estimation must be kept after
54       *                                    refinement, false otherwise.
55       * @param inliers                     set indicating which of the provided matches are inliers.
56       * @param residuals                   residuals for matched samples.
57       * @param numInliers                  number of inliers on initial estimation.
58       * @param samples                     collection of samples.
59       * @param refinementStandardDeviation standard deviation used for
60       *                                    Levenberg-Marquardt fitting.
61       */
62      public HomogeneousPoint2DRefiner(
63              final HomogeneousPoint2D initialEstimation, final boolean keepCovariance, final BitSet inliers,
64              final double[] residuals, final int numInliers, final List<Line2D> samples,
65              final double refinementStandardDeviation) {
66          super(initialEstimation, keepCovariance, inliers, residuals, numInliers, samples, refinementStandardDeviation);
67      }
68  
69      /**
70       * Constructor.
71       *
72       * @param initialEstimation           initial estimation to be set.
73       * @param keepCovariance              true if covariance of estimation must be kept after
74       *                                    refinement, false otherwise.
75       * @param inliersData                 inlier data, typically obtained from a robust
76       *                                    estimator.
77       * @param samples                     collection of samples.
78       * @param refinementStandardDeviation standard deviation used for
79       *                                    Levenberg-Marquardt fitting.
80       */
81      public HomogeneousPoint2DRefiner(
82              final HomogeneousPoint2D initialEstimation, final boolean keepCovariance, final InliersData inliersData,
83              final List<Line2D> samples, final double refinementStandardDeviation) {
84          super(initialEstimation, keepCovariance, inliersData, samples, refinementStandardDeviation);
85      }
86  
87      /**
88       * Refines provided initial estimation.
89       *
90       * @return refined estimation.
91       * @throws NotReadyException if not enough input data has been provided.
92       * @throws LockedException   if estimator is locked because refinement is
93       *                           already in progress.
94       * @throws RefinerException  if refinement fails for some reason (e.g. unable
95       *                           to converge to a result).
96       */
97      @Override
98      public HomogeneousPoint2D refine() throws NotReadyException, LockedException, RefinerException {
99          final var result = new HomogeneousPoint2D();
100         refine(result);
101         return result;
102     }
103 
104     /**
105      * Refines provided initial estimation.
106      * This method always sets a value into provided result instance regardless
107      * of the fact that error has actually improved in LMSE terms or not.
108      *
109      * @param result instance where refined estimation will be stored.
110      * @return true if result improved (decreases) in LMSE terms respect to
111      * initial estimation, false if no improvement has been achieved.
112      * @throws NotReadyException if not enough input data has been provided.
113      * @throws LockedException   if estimator is locked because refinement is
114      *                           already in progress.
115      * @throws RefinerException  if refinement fails for some reason (e.g. unable
116      *                           to converge to a result).
117      */
118     @Override
119     public boolean refine(final HomogeneousPoint2D result) throws NotReadyException, LockedException, RefinerException {
120         if (isLocked()) {
121             throw new LockedException();
122         }
123         if (!isReady()) {
124             throw new NotReadyException();
125         }
126 
127         locked = true;
128 
129         if (listener != null) {
130             listener.onRefineStart(this, initialEstimation);
131         }
132 
133         final var initialTotalResidual = totalResidual(initialEstimation);
134 
135         try {
136             final var initParams = initialEstimation.asArray();
137 
138             // output value to be fitted/optimized will contain residuals
139             final var y = new double[numInliers];
140             // input values will contain planes to compute residuals
141             final var nDims = Line2D.LINE_NUMBER_PARAMS;
142             final var x = new Matrix(numInliers, nDims);
143             final var nSamples = inliers.length();
144             var pos = 0;
145             for (var i = 0; i < nSamples; i++) {
146                 if (inliers.get(i)) {
147                     // sample is inlier
148                     final var line = samples.get(i);
149                     line.normalize();
150                     x.setElementAt(pos, 0, line.getA());
151                     x.setElementAt(pos, 1, line.getB());
152                     x.setElementAt(pos, 2, line.getC());
153 
154                     y[pos] = residuals[i];
155                     pos++;
156                 }
157             }
158 
159             final var evaluator = new LevenbergMarquardtMultiDimensionFunctionEvaluator() {
160 
161                 private final Line2D line = new Line2D();
162 
163                 private final HomogeneousPoint2D point = new HomogeneousPoint2D();
164 
165                 private final GradientEstimator gradientEstimator = new GradientEstimator(p -> {
166                     this.point.setCoordinates(p);
167                     return residual(this.point, line);
168                 });
169 
170                 @Override
171                 public int getNumberOfDimensions() {
172                     return nDims;
173                 }
174 
175                 @Override
176                 public double[] createInitialParametersArray() {
177                     return initParams;
178                 }
179 
180                 @Override
181                 public double evaluate(final int i, final double[] point, final double[] params,
182                                        final double[] derivatives) throws EvaluationException {
183                     // point contains a,b,c values for line
184                     line.setParameters(point);
185 
186                     // params contains coordinates of point
187                     this.point.setCoordinates(params);
188 
189                     final var y = residual(this.point, line);
190                     gradientEstimator.gradient(params, derivatives);
191 
192                     return y;
193                 }
194             };
195 
196             final var fitter = new LevenbergMarquardtMultiDimensionFitter(evaluator, x, y,
197                     getRefinementStandardDeviation());
198 
199             fitter.fit();
200 
201             // obtain estimated params
202             final var params = fitter.getA();
203 
204             // update point
205             result.setCoordinates(params);
206 
207             if (keepCovariance) {
208                 // keep covariance
209                 covariance = fitter.getCovar();
210             }
211 
212             final var finalTotalResidual = totalResidual(result);
213             final var errorDecreased = finalTotalResidual < initialTotalResidual;
214 
215             if (listener != null) {
216                 listener.onRefineEnd(this, initialEstimation, result, errorDecreased);
217             }
218 
219             return errorDecreased;
220         } catch (final Exception e) {
221             throw new RefinerException(e);
222         } finally {
223             locked = false;
224         }
225     }
226 }