1 /*M///////////////////////////////////////////////////////////////////////////////////////
3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
5 // By downloading, copying, installing or using the software you agree to this license.
6 // If you do not agree to this license, do not download, install,
7 // copy or use the software.
10 // Intel License Agreement
12 // Copyright (C) 2000, Intel Corporation, all rights reserved.
13 // Third party copyrights are property of their respective owners.
15 // Redistribution and use in source and binary forms, with or without modification,
16 // are permitted provided that the following conditions are met:
18 // * Redistribution's of source code must retain the above copyright notice,
19 // this list of conditions and the following disclaimer.
21 // * Redistribution's in binary form must reproduce the above copyright notice,
22 // this list of conditions and the following disclaimer in the documentation
23 // and/or other materials provided with the distribution.
25 // * The name of Intel Corporation may not be used to endorse or promote products
26 // derived from this software without specific prior written permission.
28 // This software is provided by the copyright holders and contributors "as is" and
29 // any express or implied warranties, including, but not limited to, the implied
30 // warranties of merchantability and fitness for a particular purpose are disclaimed.
31 // In no event shall the Intel Corporation or contributors be liable for any direct,
32 // indirect, incidental, special, exemplary, or consequential damages
33 // (including, but not limited to, procurement of substitute goods or services;
34 // loss of use, data, or profits; or business interruption) however caused
35 // and on any theory of liability, whether in contract, strict liability,
36 // or tort (including negligence or otherwise) arising in any way out of
37 // the use of this software, even if advised of the possibility of such damage.
43 /*======================= KALMAN FILTER =========================*/
44 /* State vector is (x,y,w,h,dx,dy,dw,dh). */
45 /* Measurement is (x,y,w,h). */
47 /* Dynamic matrix A: */
48 const float A8[] = { 1, 0, 0, 0, 1, 0, 0, 0,
49 0, 1, 0, 0, 0, 1, 0, 0,
50 0, 0, 1, 0, 0, 0, 1, 0,
51 0, 0, 0, 1, 0, 0, 0, 1,
52 0, 0, 0, 0, 1, 0, 0, 0,
53 0, 0, 0, 0, 0, 1, 0, 0,
54 0, 0, 0, 0, 0, 0, 1, 0,
55 0, 0, 0, 0, 0, 0, 0, 1};
57 /* Measurement matrix H: */
58 const float H8[] = { 1, 0, 0, 0, 0, 0, 0, 0,
59 0, 1, 0, 0, 0, 0, 0, 0,
60 0, 0, 1, 0, 0, 0, 0, 0,
61 0, 0, 0, 1, 0, 0, 0, 0};
63 /* Matrices for zero size velocity: */
64 /* Dinamic matrix A: */
65 const float A6[] = { 1, 0, 0, 0, 1, 0,
72 /* Measurement matrix H: */
73 const float H6[] = { 1, 0, 0, 0, 0, 0,
82 class CvBlobTrackPostProcKalman:public CvBlobTrackPostProcOne
91 float m_DataNoiseSize;
94 CvBlobTrackPostProcKalman();
95 ~CvBlobTrackPostProcKalman();
96 CvBlob* Process(CvBlob* pBlob);
98 virtual void ParamUpdate();
99 }; /* class CvBlobTrackPostProcKalman */
102 CvBlobTrackPostProcKalman::CvBlobTrackPostProcKalman()
104 m_ModelNoise = 1e-6f;
105 m_DataNoisePos = 1e-6f;
106 m_DataNoiseSize = 1e-1f;
109 m_DataNoiseSize *= (float)pow(20.,2.);
111 m_DataNoiseSize /= (float)pow(20.,2.);
114 AddParam("ModelNoise",&m_ModelNoise);
115 AddParam("DataNoisePos",&m_DataNoisePos);
116 AddParam("DataNoiseSize",&m_DataNoiseSize);
119 m_pKalman = cvCreateKalman(STATE_NUM,4);
120 memcpy( m_pKalman->transition_matrix->data.fl, A, sizeof(A));
121 memcpy( m_pKalman->measurement_matrix->data.fl, H, sizeof(H));
123 cvSetIdentity( m_pKalman->process_noise_cov, cvRealScalar(m_ModelNoise) );
124 cvSetIdentity( m_pKalman->measurement_noise_cov, cvRealScalar(m_DataNoisePos) );
125 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 2,2) = m_DataNoiseSize;
126 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 3,3) = m_DataNoiseSize;
127 cvSetIdentity( m_pKalman->error_cov_post, cvRealScalar(1));
128 cvZero(m_pKalman->state_post);
129 cvZero(m_pKalman->state_pre);
131 SetModuleName("Kalman");
134 CvBlobTrackPostProcKalman::~CvBlobTrackPostProcKalman()
136 cvReleaseKalman(&m_pKalman);
139 void CvBlobTrackPostProcKalman::ParamUpdate()
141 cvSetIdentity( m_pKalman->process_noise_cov, cvRealScalar(m_ModelNoise) );
142 cvSetIdentity( m_pKalman->measurement_noise_cov, cvRealScalar(m_DataNoisePos) );
143 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 2,2) = m_DataNoiseSize;
144 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 3,3) = m_DataNoiseSize;
147 CvBlob* CvBlobTrackPostProcKalman::Process(CvBlob* pBlob)
149 CvBlob* pBlobRes = &m_Blob;
151 CvMat Zmat = cvMat(4,1,CV_32F,Z);
156 m_pKalman->state_post->data.fl[0+4] = CV_BLOB_X(pBlob)-m_pKalman->state_post->data.fl[0];
157 m_pKalman->state_post->data.fl[1+4] = CV_BLOB_Y(pBlob)-m_pKalman->state_post->data.fl[1];
160 m_pKalman->state_post->data.fl[2+4] = CV_BLOB_WX(pBlob)-m_pKalman->state_post->data.fl[2];
161 m_pKalman->state_post->data.fl[3+4] = CV_BLOB_WY(pBlob)-m_pKalman->state_post->data.fl[3];
163 m_pKalman->state_post->data.fl[0] = CV_BLOB_X(pBlob);
164 m_pKalman->state_post->data.fl[1] = CV_BLOB_Y(pBlob);
165 m_pKalman->state_post->data.fl[2] = CV_BLOB_WX(pBlob);
166 m_pKalman->state_post->data.fl[3] = CV_BLOB_WY(pBlob);
169 { /* Nonfirst call: */
170 cvKalmanPredict(m_pKalman,0);
171 Z[0] = CV_BLOB_X(pBlob);
172 Z[1] = CV_BLOB_Y(pBlob);
173 Z[2] = CV_BLOB_WX(pBlob);
174 Z[3] = CV_BLOB_WY(pBlob);
175 cvKalmanCorrect(m_pKalman,&Zmat);
176 cvMatMulAdd(m_pKalman->measurement_matrix, m_pKalman->state_post, NULL, &Zmat);
177 CV_BLOB_X(pBlobRes) = Z[0];
178 CV_BLOB_Y(pBlobRes) = Z[1];
179 // CV_BLOB_WX(pBlobRes) = Z[2];
180 // CV_BLOB_WY(pBlobRes) = Z[3];
186 void CvBlobTrackPostProcKalman::Release()
191 CvBlobTrackPostProcOne* cvCreateModuleBlobTrackPostProcKalmanOne()
193 return (CvBlobTrackPostProcOne*) new CvBlobTrackPostProcKalman;
196 CvBlobTrackPostProc* cvCreateModuleBlobTrackPostProcKalman()
198 return cvCreateBlobTrackPostProcList(cvCreateModuleBlobTrackPostProcKalmanOne);
200 /*======================= KALMAN FILTER =========================*/
204 /*======================= KALMAN PREDICTOR =========================*/
205 class CvBlobTrackPredictKalman:public CvBlobTrackPredictor
209 CvBlob m_BlobPredict;
213 float m_DataNoisePos;
214 float m_DataNoiseSize;
217 CvBlobTrackPredictKalman();
218 ~CvBlobTrackPredictKalman();
220 void Update(CvBlob* pBlob);
221 virtual void ParamUpdate();
226 }; /* class CvBlobTrackPredictKalman */
229 void CvBlobTrackPredictKalman::ParamUpdate()
231 cvSetIdentity( m_pKalman->process_noise_cov, cvRealScalar(m_ModelNoise) );
232 cvSetIdentity( m_pKalman->measurement_noise_cov, cvRealScalar(m_DataNoisePos) );
233 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 2,2) = m_DataNoiseSize;
234 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 3,3) = m_DataNoiseSize;
237 CvBlobTrackPredictKalman::CvBlobTrackPredictKalman()
239 m_ModelNoise = 1e-6f;
240 m_DataNoisePos = 1e-6f;
241 m_DataNoiseSize = 1e-1f;
244 m_DataNoiseSize *= (float)pow(20.,2.);
246 m_DataNoiseSize /= (float)pow(20.,2.);
249 AddParam("ModelNoise",&m_ModelNoise);
250 AddParam("DataNoisePos",&m_DataNoisePos);
251 AddParam("DataNoiseSize",&m_DataNoiseSize);
254 m_pKalman = cvCreateKalman(STATE_NUM,4);
255 memcpy( m_pKalman->transition_matrix->data.fl, A, sizeof(A));
256 memcpy( m_pKalman->measurement_matrix->data.fl, H, sizeof(H));
258 cvSetIdentity( m_pKalman->process_noise_cov, cvRealScalar(m_ModelNoise) );
259 cvSetIdentity( m_pKalman->measurement_noise_cov, cvRealScalar(m_DataNoisePos) );
260 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 2,2) = m_DataNoiseSize;
261 CV_MAT_ELEM(*m_pKalman->measurement_noise_cov, float, 3,3) = m_DataNoiseSize;
262 cvSetIdentity( m_pKalman->error_cov_post, cvRealScalar(1));
263 cvZero(m_pKalman->state_post);
264 cvZero(m_pKalman->state_pre);
266 SetModuleName("Kalman");
269 CvBlobTrackPredictKalman::~CvBlobTrackPredictKalman()
271 cvReleaseKalman(&m_pKalman);
274 CvBlob* CvBlobTrackPredictKalman::Predict()
278 cvKalmanPredict(m_pKalman,0);
279 m_BlobPredict.x = m_pKalman->state_pre->data.fl[0];
280 m_BlobPredict.y = m_pKalman->state_pre->data.fl[1];
281 m_BlobPredict.w = m_pKalman->state_pre->data.fl[2];
282 m_BlobPredict.h = m_pKalman->state_pre->data.fl[3];
284 return &m_BlobPredict;
287 void CvBlobTrackPredictKalman::Update(CvBlob* pBlob)
290 CvMat Zmat = cvMat(4,1,CV_32F,Z);
291 m_BlobPredict = pBlob[0];
295 m_pKalman->state_post->data.fl[0+4] = CV_BLOB_X(pBlob)-m_pKalman->state_post->data.fl[0];
296 m_pKalman->state_post->data.fl[1+4] = CV_BLOB_Y(pBlob)-m_pKalman->state_post->data.fl[1];
299 m_pKalman->state_post->data.fl[2+4] = CV_BLOB_WX(pBlob)-m_pKalman->state_post->data.fl[2];
300 m_pKalman->state_post->data.fl[3+4] = CV_BLOB_WY(pBlob)-m_pKalman->state_post->data.fl[3];
302 m_pKalman->state_post->data.fl[0] = CV_BLOB_X(pBlob);
303 m_pKalman->state_post->data.fl[1] = CV_BLOB_Y(pBlob);
304 m_pKalman->state_post->data.fl[2] = CV_BLOB_WX(pBlob);
305 m_pKalman->state_post->data.fl[3] = CV_BLOB_WY(pBlob);
308 { /* Nonfirst call: */
309 Z[0] = CV_BLOB_X(pBlob);
310 Z[1] = CV_BLOB_Y(pBlob);
311 Z[2] = CV_BLOB_WX(pBlob);
312 Z[3] = CV_BLOB_WY(pBlob);
313 cvKalmanCorrect(m_pKalman,&Zmat);
316 cvKalmanPredict(m_pKalman,0);
322 CvBlobTrackPredictor* cvCreateModuleBlobTrackPredictKalman()
324 return (CvBlobTrackPredictor*) new CvBlobTrackPredictKalman;
326 /*======================= KALMAN PREDICTOR =========================*/