Python cv2.mulSpectrums() Examples

The following are 23 code examples of cv2.mulSpectrums(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module cv2 , or try the search function .
Example #1
Source File: mosse.py    From OpenCV-Python-Tutorial with MIT License 7 votes vote down vote up 
def update(self, frame, rate = 0.125):
        (x, y), (w, h) = self.pos, self.size
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), (x, y))
        img = self.preprocess(img)
        self.last_resp, (dx, dy), self.psr = self.correlate(img)
        self.good = self.psr > 8.0
        if not self.good:
            return

        self.pos = x+dx, y+dy
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), self.pos)
        img = self.preprocess(img)

        A = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)
        H1 = cv2.mulSpectrums(self.G, A, 0, conjB=True)
        H2 = cv2.mulSpectrums(     A, A, 0, conjB=True)
        self.H1 = self.H1 * (1.0-rate) + H1 * rate
        self.H2 = self.H2 * (1.0-rate) + H2 * rate
        self.update_kernel()
Example #2
Source File: mosse.py    From OpenCV-Python-Tutorial with MIT License 6 votes vote down vote up 
def __init__(self, frame, rect):
        x1, y1, x2, y2 = rect
        w, h = map(cv2.getOptimalDFTSize, [x2-x1, y2-y1])
        x1, y1 = (x1+x2-w)//2, (y1+y2-h)//2
        self.pos = x, y = x1+0.5*(w-1), y1+0.5*(h-1)
        self.size = w, h
        img = cv2.getRectSubPix(frame, (w, h), (x, y))

        self.win = cv2.createHanningWindow((w, h), cv2.CV_32F)
        g = np.zeros((h, w), np.float32)
        g[h//2, w//2] = 1
        g = cv2.GaussianBlur(g, (-1, -1), 2.0)
        g /= g.max()

        self.G = cv2.dft(g, flags=cv2.DFT_COMPLEX_OUTPUT)
        self.H1 = np.zeros_like(self.G)
        self.H2 = np.zeros_like(self.G)
        for i in xrange(128):
            a = self.preprocess(rnd_warp(img))
            A = cv2.dft(a, flags=cv2.DFT_COMPLEX_OUTPUT)
            self.H1 += cv2.mulSpectrums(self.G, A, 0, conjB=True)
            self.H2 += cv2.mulSpectrums(     A, A, 0, conjB=True)
        self.update_kernel()
        self.update(frame)
Example #3
Source File: deconvolution.py    From OpenCV-Python-Tutorial with MIT License 6 votes vote down vote up 
def update(_):
        ang = np.deg2rad( cv2.getTrackbarPos('angle', win) )
        d = cv2.getTrackbarPos('d', win)
        noise = 10**(-0.1*cv2.getTrackbarPos('SNR (db)', win))

        if defocus:
            psf = defocus_kernel(d)
        else:
            psf = motion_kernel(ang, d)
        cv2.imshow('psf', psf)

        psf /= psf.sum()
        psf_pad = np.zeros_like(img)
        kh, kw = psf.shape
        psf_pad[:kh, :kw] = psf
        PSF = cv2.dft(psf_pad, flags=cv2.DFT_COMPLEX_OUTPUT, nonzeroRows = kh)
        PSF2 = (PSF**2).sum(-1)
        iPSF = PSF / (PSF2 + noise)[...,np.newaxis]
        RES = cv2.mulSpectrums(IMG, iPSF, 0)
        res = cv2.idft(RES, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT )
        res = np.roll(res, -kh//2, 0)
        res = np.roll(res, -kw//2, 1)
        cv2.imshow(win, res)
Example #4
Source File: mosse.py    From PyCV-time with MIT License 6 votes vote down vote up 
def update(self, frame, rate = 0.125):
        (x, y), (w, h) = self.pos, self.size
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), (x, y))
        img = self.preprocess(img)
        self.last_resp, (dx, dy), self.psr = self.correlate(img)
        self.good = self.psr > 8.0
        if not self.good:
            return

        self.pos = x+dx, y+dy
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), self.pos)
        img = self.preprocess(img)

        A = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)
        H1 = cv2.mulSpectrums(self.G, A, 0, conjB=True)
        H2 = cv2.mulSpectrums(     A, A, 0, conjB=True)
        self.H1 = self.H1 * (1.0-rate) + H1 * rate
        self.H2 = self.H2 * (1.0-rate) + H2 * rate
        self.update_kernel()
Example #5
Source File: tracker.py    From KCF-DSST-py with MIT License 6 votes vote down vote up 
def train_scale(self, image, ini=False):
        xsf = self.get_scale_sample(image)

        # Adjust ysf to the same size as xsf in the first time
        if ini:
            totalSize = xsf.shape[0]
            self.ysf = cv2.repeat(self.ysf, totalSize, 1)

        # Get new GF in the paper (delta A)
        new_sf_num = cv2.mulSpectrums(self.ysf, xsf, 0, conjB=True)

        new_sf_den = cv2.mulSpectrums(xsf, xsf, 0, conjB=True)
        new_sf_den = cv2.reduce(real(new_sf_den), 0, cv2.REDUCE_SUM)

        if ini:
            self.sf_den = new_sf_den
            self.sf_num = new_sf_num
        else:
            # Get new A and new B
            self.sf_den = cv2.addWeighted(self.sf_den, (1 - self.scale_lr), new_sf_den, self.scale_lr, 0)
            self.sf_num = cv2.addWeighted(self.sf_num, (1 - self.scale_lr), new_sf_num, self.scale_lr, 0)

        self.update_roi()

    # 检测当前图像尺度
Example #6
Source File: deconvolution.py    From PyCV-time with MIT License 6 votes vote down vote up 
def update(_):
        ang = np.deg2rad( cv2.getTrackbarPos('angle', win) )
        d = cv2.getTrackbarPos('d', win)
        noise = 10**(-0.1*cv2.getTrackbarPos('SNR (db)', win))

        if defocus:
            psf = defocus_kernel(d)
        else:
            psf = motion_kernel(ang, d)
        cv2.imshow('psf', psf)

        psf /= psf.sum()
        psf_pad = np.zeros_like(img)
        kh, kw = psf.shape
        psf_pad[:kh, :kw] = psf
        PSF = cv2.dft(psf_pad, flags=cv2.DFT_COMPLEX_OUTPUT, nonzeroRows = kh)
        PSF2 = (PSF**2).sum(-1)
        iPSF = PSF / (PSF2 + noise)[...,np.newaxis]
        RES = cv2.mulSpectrums(IMG, iPSF, 0)
        res = cv2.idft(RES, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT )
        res = np.roll(res, -kh//2, 0)
        res = np.roll(res, -kw//2, 1)
        cv2.imshow(win, res)
Example #7
Source File: mosse.py    From PyCV-time with MIT License 6 votes vote down vote up 
def update(self, frame, rate = 0.125):
        (x, y), (w, h) = self.pos, self.size
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), (x, y))
        img = self.preprocess(img)
        self.last_resp, (dx, dy), self.psr = self.correlate(img)
        self.good = self.psr > 8.0
        if not self.good:
            return

        self.pos = x+dx, y+dy
        self.last_img = img = cv2.getRectSubPix(frame, (w, h), self.pos)
        img = self.preprocess(img)

        A = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)
        H1 = cv2.mulSpectrums(self.G, A, 0, conjB=True)
        H2 = cv2.mulSpectrums(     A, A, 0, conjB=True)
        self.H1 = self.H1 * (1.0-rate) + H1 * rate
        self.H2 = self.H2 * (1.0-rate) + H2 * rate
        self.update_kernel()
Example #8
Source File: mosse.py    From PyCV-time with MIT License 6 votes vote down vote up 
def __init__(self, frame, rect):
        x1, y1, x2, y2 = rect
        w, h = map(cv2.getOptimalDFTSize, [x2-x1, y2-y1])
        x1, y1 = (x1+x2-w)//2, (y1+y2-h)//2
        self.pos = x, y = x1+0.5*(w-1), y1+0.5*(h-1)
        self.size = w, h
        img = cv2.getRectSubPix(frame, (w, h), (x, y))

        self.win = cv2.createHanningWindow((w, h), cv2.CV_32F)
        g = np.zeros((h, w), np.float32)
        g[h//2, w//2] = 1
        g = cv2.GaussianBlur(g, (-1, -1), 2.0)
        g /= g.max()

        self.G = cv2.dft(g, flags=cv2.DFT_COMPLEX_OUTPUT)
        self.H1 = np.zeros_like(self.G)
        self.H2 = np.zeros_like(self.G)
        for i in xrange(128):
            a = self.preprocess(rnd_warp(img))
            A = cv2.dft(a, flags=cv2.DFT_COMPLEX_OUTPUT)
            self.H1 += cv2.mulSpectrums(self.G, A, 0, conjB=True)
            self.H2 += cv2.mulSpectrums(     A, A, 0, conjB=True)
        self.update_kernel()
        self.update(frame)
Example #9
Source File: deconvolution.py    From PyCV-time with MIT License 6 votes vote down vote up 
def update(_):
        ang = np.deg2rad( cv2.getTrackbarPos('angle', win) )
        d = cv2.getTrackbarPos('d', win)
        noise = 10**(-0.1*cv2.getTrackbarPos('SNR (db)', win))

        if defocus:
            psf = defocus_kernel(d)
        else:
            psf = motion_kernel(ang, d)
        cv2.imshow('psf', psf)

        psf /= psf.sum()
        psf_pad = np.zeros_like(img)
        kh, kw = psf.shape
        psf_pad[:kh, :kw] = psf
        PSF = cv2.dft(psf_pad, flags=cv2.DFT_COMPLEX_OUTPUT, nonzeroRows = kh)
        PSF2 = (PSF**2).sum(-1)
        iPSF = PSF / (PSF2 + noise)[...,np.newaxis]
        RES = cv2.mulSpectrums(IMG, iPSF, 0)
        res = cv2.idft(RES, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT )
        res = np.roll(res, -kh//2, 0)
        res = np.roll(res, -kw//2, 1)
        cv2.imshow(win, res)
Example #10
Source File: mosse.py    From PyCV-time with MIT License 5 votes vote down vote up 
def correlate(self, img):
        C = cv2.mulSpectrums(cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT), self.H, 0, conjB=True)
        resp = cv2.idft(C, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT)
        h, w = resp.shape
        _, mval, _, (mx, my) = cv2.minMaxLoc(resp)
        side_resp = resp.copy()
        cv2.rectangle(side_resp, (mx-5, my-5), (mx+5, my+5), 0, -1)
        smean, sstd = side_resp.mean(), side_resp.std()
        psr = (mval-smean) / (sstd+eps)
        return resp, (mx-w//2, my-h//2), psr
Example #11
Source File: mosse.py    From PyCV-time with MIT License 5 votes vote down vote up 
def correlate(self, img):
        C = cv2.mulSpectrums(cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT), self.H, 0, conjB=True)
        resp = cv2.idft(C, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT)
        h, w = resp.shape
        _, mval, _, (mx, my) = cv2.minMaxLoc(resp)
        side_resp = resp.copy()
        cv2.rectangle(side_resp, (mx-5, my-5), (mx+5, my+5), 0, -1)
        smean, sstd = side_resp.mean(), side_resp.std()
        psr = (mval-smean) / (sstd+eps)
        return resp, (mx-w//2, my-h//2), psr
Example #12
Source File: kcftracker.py    From KCFpy with MIT License 5 votes vote down vote up 
def gaussianCorrelation(self, x1, x2):
		if(self._hogfeatures):
			c = np.zeros((self.size_patch[0], self.size_patch[1]), np.float32)
			for i in xrange(self.size_patch[2]):
				x1aux = x1[i, :].reshape((self.size_patch[0], self.size_patch[1]))
				x2aux = x2[i, :].reshape((self.size_patch[0], self.size_patch[1]))
				caux = cv2.mulSpectrums(fftd(x1aux), fftd(x2aux), 0, conjB = True)
				caux = real(fftd(caux, True))
				#caux = rearrange(caux)
				c += caux
			c = rearrange(c)
		else:
			c = cv2.mulSpectrums(fftd(x1), fftd(x2), 0, conjB = True)   # 'conjB=' is necessary!
			c = fftd(c, True)
			c = real(c)
			c = rearrange(c)

		if(x1.ndim==3 and x2.ndim==3):
			d = (np.sum(x1[:,:,0]*x1[:,:,0]) + np.sum(x2[:,:,0]*x2[:,:,0]) - 2.0*c) / (self.size_patch[0]*self.size_patch[1]*self.size_patch[2])
		elif(x1.ndim==2 and x2.ndim==2):
			d = (np.sum(x1*x1) + np.sum(x2*x2) - 2.0*c) / (self.size_patch[0]*self.size_patch[1]*self.size_patch[2])

		d = d * (d>=0)
		d = np.exp(-d / (self.sigma*self.sigma))

		return d
Example #13
Source File: kcftracker.py    From KCFnb with MIT License 5 votes vote down vote up 
def gaussianCorrelation(self, x1, x2):
		#t0 = time()
		if(self._hogfeatures):
			c = np.zeros((self.size_patch[0], self.size_patch[1]), np.float32)
			for i in xrange(self.size_patch[2]):
				x1aux = x1[i, :].reshape((self.size_patch[0], self.size_patch[1]))
				x2aux = x2[i, :].reshape((self.size_patch[0], self.size_patch[1]))
				caux = cv2.mulSpectrums(fftd(x1aux), fftd(x2aux), 0, conjB = True)
				caux = real(fftd(caux, True))
				#caux = rearrange(caux)
				c += caux
			c = rearrange(c)
		else:
			c = cv2.mulSpectrums(fftd(x1), fftd(x2), 0, conjB = True)   # 'conjB=' is necessary!
			c = fftd(c, True)
			c = real(c)
			c = rearrange(c)

		#t1 = time()
		#self.tt = 0.9*self.tt + 0.1*(t1-t0)
		#print self.tt

		if(x1.ndim==3 and x2.ndim==3):
			d = (np.sum(x1[:,:,0]*x1[:,:,0]) + np.sum(x2[:,:,0]*x2[:,:,0]) - 2.0*c) / (self.size_patch[0]*self.size_patch[1]*self.size_patch[2])
		elif(x1.ndim==2 and x2.ndim==2):
			d = (np.sum(x1*x1) + np.sum(x2*x2) - 2.0*c) / (self.size_patch[0]*self.size_patch[1]*self.size_patch[2])

		d = d * (d>=0)
		d = np.exp(-d / (self.sigma*self.sigma))

		return d
Example #14
Source File: mosse.py    From open-vot with MIT License 5 votes vote down vote up 
def _linear_correlation(self, img):
        C = cv2.mulSpectrums(
            cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT), self.H, 0, conjB=True)
        resp = cv2.idft(C, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT)
        h, w = resp.shape
        _, mval, _, (mx, my) = cv2.minMaxLoc(resp)
        side_resp = resp.copy()
        cv2.rectangle(side_resp, (mx - 5, my - 5), (mx + 5, my + 5), 0, -1)
        smean, sstd = side_resp.mean(), side_resp.std()
        psr = (mval - smean) / (sstd + self.cfg.eps)

        return resp, (mx - w // 2, my - h // 2), psr
Example #15
Source File: mosse.py    From open-vot with MIT License 5 votes vote down vote up 
def update(self, image):
        if image.ndim == 3:
            image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        (x, y), (w, h) = self.t_center, self.t_sz
        self.last_img = img = cv2.getRectSubPix(image, (w, h), (x, y))
        img = self._preprocess(img)
        self.last_resp, (dx, dy), self.psr = self._linear_correlation(img)
        self.good = self.psr > self.cfg.psr_thr

        if self.good:
            self.t_center = x + dx, y + dy
            self.last_img = img = cv2.getRectSubPix(
                image, (w, h), self.t_center)
            img = self._preprocess(img)

            F = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)
            A = cv2.mulSpectrums(self.G, F, 0, conjB=True)
            B = cv2.mulSpectrums(F, F, 0, conjB=True)
            self.A = self.A * (1.0 - self.cfg.interp_factor) + \
                A * self.cfg.interp_factor
            self.B = self.B * (1.0 - self.cfg.interp_factor) + \
                B * self.cfg.interp_factor
            self._update_kernel()

        return np.array([x - 0.5 * (w - 1), y - 0.5 * (h - 1), w, h])
Example #16
Source File: mosse.py    From open-vot with MIT License 5 votes vote down vote up 
def init(self, image, init_rect):
        if image.ndim == 3:
            image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        init_rect = init_rect.astype(int)
        init_rect[2:] += init_rect[:2]
        x1, y1, x2, y2 = init_rect
        w, h = map(cv2.getOptimalDFTSize, [x2 - x1, y2 - y1])
        x1, y1 = (x1 + x2 - w) // 2, (y1 + y2 - h) // 2
        self.t_center = x, y = x1 + 0.5 * (w - 1), y1 + 0.5 * (h - 1)
        self.t_sz = w, h
        img = cv2.getRectSubPix(image, (w, h), (x, y))

        self.win = cv2.createHanningWindow((w, h), cv2.CV_32F)
        g = np.zeros((h, w), np.float32)
        g[h // 2, w // 2] = 1
        g = cv2.GaussianBlur(g, (-1, -1), self.cfg.sigma)
        g /= g.max()

        self.G = cv2.dft(g, flags=cv2.DFT_COMPLEX_OUTPUT)
        self.A = np.zeros_like(self.G)
        self.B = np.zeros_like(self.G)
        for _i in range(128):
            patch = self._preprocess(self._random_warp(img))
            F = cv2.dft(patch, flags=cv2.DFT_COMPLEX_OUTPUT)
            self.A += cv2.mulSpectrums(self.G, F, 0, conjB=True)
            self.B += cv2.mulSpectrums(F, F, 0, conjB=True)
        self._update_kernel()
        self.update(image)
Example #17
Source File: csk.py    From open-vot with MIT License 5 votes vote down vote up 
def _polynomial_correlation(self, x1, x2, a, b):
        xcorr = cv2.mulSpectrums(fft2(x1), fft2(x2), 0, conjB=True)
        xcorr = fftshift(real(ifft2(xcorr)))

        out = (xcorr / x1.size + a) ** b

        return out
Example #18
Source File: csk.py    From open-vot with MIT License 5 votes vote down vote up 
def _linear_correlation(self, x1, x2):
        xcorr = cv2.mulSpectrums(fft2(x1), fft2(x2), 0, conjB=True)
        xcorr = fftshift(real(ifft2(xcorr)))

        return xcorr / x1.size
Example #19
Source File: kcf.py    From open-vot with MIT License 5 votes vote down vote up 
def _gaussian_correlation(self, x1, x2, sigma):
        xcorr = np.zeros((self.feat_sz[0], self.feat_sz[1]), np.float32)
        for i in range(self.feat_sz[2]):
            xcorr_ = cv2.mulSpectrums(
                fft2(x1[:, :, i]), fft2(x2[:, :, i]), 0, conjB=True)
            xcorr_ = real(ifft2(xcorr_))
            xcorr += xcorr_
        xcorr = fftshift(xcorr)

        out = (np.sum(x1 * x1) + np.sum(x2 * x2) - 2.0 * xcorr) / x1.size
        out[out < 0] = 0
        out = np.exp(-out / self.cfg.sigma ** 2)

        return out
Example #20
Source File: kcf.py    From open-vot with MIT License 5 votes vote down vote up 
def _polynomial_correlation(self, x1, x2, a, b):
        xcorr = np.zeros((self.feat_sz[0], self.feat_sz[1]), np.float32)
        for i in range(self.feat_sz[2]):
            xcorr_ = cv2.mulSpectrums(
                fft2(x1[:, :, i]), fft2(x2[:, :, i]), 0, conjB=True)
            xcorr_ = real(ifft2(xcorr_))
            xcorr += xcorr_
        xcorr = fftshift(xcorr)

        out = (xcorr / x1.size + a) ** b

        return out
Example #21
Source File: kcf.py    From open-vot with MIT License 5 votes vote down vote up 
def _linear_correlation(self, x1, x2):
        xcorr = np.zeros((self.feat_sz[0], self.feat_sz[1]), np.float32)
        for i in range(self.feat_sz[2]):
            xcorr_ = cv2.mulSpectrums(
                fft2(x1[:, :, i]), fft2(x2[:, :, i]), 0, conjB=True)
            xcorr_ = real(ifft2(xcorr_))
            xcorr += xcorr_
        xcorr = fftshift(xcorr)

        return xcorr / x1.size
Example #22
Source File: tracker.py    From KCF-DSST-py with MIT License 5 votes vote down vote up 
def gaussianCorrelation(self, x1, x2):
        if self._hogfeatures:
            c = np.zeros((self.size_patch[0], self.size_patch[1]), np.float32)
            for i in xrange(self.size_patch[2]):
                x1aux = x1[i, :].reshape((self.size_patch[0], self.size_patch[1]))
                x2aux = x2[i, :].reshape((self.size_patch[0], self.size_patch[1]))
                caux = cv2.mulSpectrums(fftd(x1aux), fftd(x2aux), 0, conjB=True)
                caux = real(fftd(caux, True))
                # caux = rearrange(caux)
                c += caux
            c = rearrange(c)
        else:
            # 'conjB=' is necessary!在做乘法之前取第二个输入数组的共轭.
            c = cv2.mulSpectrums(fftd(x1), fftd(x2), 0, conjB=True)
            c = fftd(c, True)
            c = real(c)
            c = rearrange(c)
 
        if x1.ndim == 3 and x2.ndim == 3:
            d = (np.sum(x1[:, :, 0] * x1[:, :, 0]) + np.sum(x2[:, :, 0] * x2[:, :, 0]) - 2.0 * c) / (
                        self.size_patch[0] * self.size_patch[1] * self.size_patch[2])
        elif x1.ndim == 2 and x2.ndim == 2:
            d = (np.sum(x1 * x1) + np.sum(x2 * x2) - 2.0 * c) / (
                        self.size_patch[0] * self.size_patch[1] * self.size_patch[2])
 
        d = d * (d >= 0)
        d = np.exp(-d / (self.sigma * self.sigma))
 
        return d

    # 使用第一帧和它的跟踪框，初始化KCF跟踪器
Example #23
Source File: mosse.py    From OpenCV-Python-Tutorial with MIT License 5 votes vote down vote up 
def correlate(self, img):
        C = cv2.mulSpectrums(cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT), self.H, 0, conjB=True)
        resp = cv2.idft(C, flags=cv2.DFT_SCALE | cv2.DFT_REAL_OUTPUT)
        h, w = resp.shape
        _, mval, _, (mx, my) = cv2.minMaxLoc(resp)
        side_resp = resp.copy()
        cv2.rectangle(side_resp, (mx-5, my-5), (mx+5, my+5), 0, -1)
        smean, sstd = side_resp.mean(), side_resp.std()
        psr = (mval-smean) / (sstd+eps)
        return resp, (mx-w//2, my-h//2), psr