我们从Python开源项目中，提取了以下17个代码示例，用于说明如何使用cv2.cartToPolar()。
def hog(img): h, w = img.shape gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bins = np.int32(bin_n*ang/(2*np.pi)) # quantizing binvalues in (0...16) bin_cells = () mag_cells = () for i in range(wc): for j in range(hc): bin_cells += (bins[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) mag_cells += (mag[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) #np.bincount() return times of each number appear hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # hist is a 16*wc*hc vector return hist
def compute(self, frame): #frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) dx = cv2.filter2D(frame, cv2.CV_32F, self.xkernel) dy = cv2.filter2D(frame, cv2.CV_32F, self.ykernel) orientations = np.zeros_like(dx) magnitudes = np.zeros_like(dx) cv2.cartToPolar(dx,dy, magnitudes,orientations) descriptor = [] frameH, frameW = frame.shape mask_threshold = magnitudes <= self.threshold for row in range(self.rows): for col in range(self.cols): mask = np.zeros_like(frame) mask[((frameH/self.rows)*row):((frameH/self.rows)*(row+1)),(frameW/self.cols)*col:((frameW/self.cols)*(col+1))] = 1 mask[mask_threshold] = 0 a_, b_ = mask.shape hist = cv2.calcHist([orientations], self.channel, mask, [self.bins], self.range) hist = cv2.normalize(hist, None) descriptor.append(hist) return np.concatenate([x for x in descriptor])
def get_mag_ang(img): """ Gets image gradient (magnitude) and orientation (angle) Args: img Returns: Gradient, orientation """ img = np.sqrt(img) gx = cv2.Sobel(np.float32(img), cv2.CV_32F, 1, 0) gy = cv2.Sobel(np.float32(img), cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) return mag, ang, gx, gy
def optical_flow(one, two): """ method taken from (https://chatbotslife.com/autonomous-vehicle-speed-estimation-from-dashboard-cam-ca96c24120e4) """ one_g = cv2.cvtColor(one, cv2.COLOR_RGB2GRAY) two_g = cv2.cvtColor(two, cv2.COLOR_RGB2GRAY) hsv = np.zeros((120, 320, 3)) # set saturation hsv[:,:,1] = cv2.cvtColor(two, cv2.COLOR_RGB2HSV)[:,:,1] # obtain dense optical flow paramters flow = cv2.calcOpticalFlowFarneback(one_g, two_g, flow=None, pyr_scale=0.5, levels=1, winsize=15, iterations=2, poly_n=5, poly_sigma=1.1, flags=0) # convert from cartesian to polar mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1]) # hue corresponds to direction hsv[:,:,0] = ang * (180/ np.pi / 2) # value corresponds to magnitude hsv[:,:,2] = cv2.normalize(mag,None,0,255,cv2.NORM_MINMAX) # convert HSV to int32's hsv = np.asarray(hsv, dtype= np.float32) rgb_flow = cv2.cvtColor(hsv,cv2.COLOR_HSV2RGB) return rgb_flow
def hog(img): h, w = img.shape gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bins = np.int32(bin_n*ang/(2*np.pi)) # quantizing binvalues in (0...16) bin_cells = () mag_cells = () for i in range(wc): for j in range(hc): bin_cells += (bins[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) mag_cells += (mag[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # hist is a 16*wc*hc vector return hist
def hog(img): h, w = img.shape gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bins = np.int32(bin_n*ang/(2*np.pi)) # quantizing binvalues in (0...bin_n) bin_cells = () mag_cells = () for i in range(wc): for j in range(hc): bin_cells += (bins[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) mag_cells += (mag[j*h/hc:(j+1)*h/hc, i*w/wc:(i+1)*w/wc],) hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # hist is a bin_n*wc*hc vector return hist
def writeOpticalFlowImage(self, index, optical_flow): filename = "flow_" + str(index) + ".png" output_path = os.path.join(self.optical_flow_output_directory, filename) # create hsv image shape_optical_flow = optical_flow.shape[:-1] shape_hsv = [shape_optical_flow[0], shape_optical_flow[1], 3] hsv = np.zeros(shape_hsv, np.float32) # set saturation to 255 hsv[:,:,1] = 255 # create colorful illustration of optical flow mag, ang = cv2.cartToPolar(optical_flow[:,:,0], optical_flow[:,:,1]) hsv[:,:,0] = ang*180/np.pi/2 hsv[:,:,2] = cv2.normalize(mag,None,0,255,cv2.NORM_MINMAX) bgr = cv2.cvtColor(hsv,cv2.COLOR_HSV2BGR) cv2.imwrite(output_path, bgr)
def preprocess_hog(digits): samples = [] for img in digits: gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bin_n = 16 bin = np.int32(bin_n*ang/(2*np.pi)) bin_cells = bin[:100,:100], bin[100:,:100], bin[:100,100:], bin[100:,100:] mag_cells = mag[:100,:100], mag[100:,:100], mag[:100,100:], mag[100:,100:] hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # transform to Hellinger kernel eps = 1e-7 hist /= hist.sum() + eps hist = np.sqrt(hist) hist /= norm(hist) + eps samples.append(hist) return np.float32(samples) #Here goes my wrappers:
def hog_single(img): samples=[] gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bin_n = 16 bin = np.int32(bin_n*ang/(2*np.pi)) bin_cells = bin[:100,:100], bin[100:,:100], bin[:100,100:], bin[100:,100:] mag_cells = mag[:100,:100], mag[100:,:100], mag[:100,100:], mag[100:,100:] hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # transform to Hellinger kernel eps = 1e-7 hist /= hist.sum() + eps hist = np.sqrt(hist) hist /= norm(hist) + eps samples.append(hist) return np.float32(samples) #using Compute_hog too much time !
def optical_flow(one, two): """ method taken from https://chatbotslife.com/autonomous-vehicle-speed-estimation-from-dashboard-cam-ca96c24120e4 input: image_current, image_next (RGB images) calculates optical flow magnitude and angle and places it into HSV image """ one_g = cv2.cvtColor(one, cv2.COLOR_RGB2GRAY) two_g = cv2.cvtColor(two, cv2.COLOR_RGB2GRAY) hsv = np.zeros((120, 320, 3)) # set saturation hsv[:,:,1] = cv2.cvtColor(two, cv2.COLOR_RGB2HSV)[:,:,1] # obtain dense optical flow paramters flow = cv2.calcOpticalFlowFarneback(one_g, two_g, flow=None, pyr_scale=0.5, levels=1, winsize=10, iterations=2, poly_n=5, poly_sigma=1.1, flags=0) # convert from cartesian to polar mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1]) # hue corresponds to direction hsv[:,:,0] = ang * (180/ np.pi / 2) # value corresponds to magnitude hsv[:,:,2] = cv2.normalize(mag,None,0,255,cv2.NORM_MINMAX) # convert HSV to int32's hsv = np.asarray(hsv, dtype= np.float32) rgb_flow = cv2.cvtColor(hsv,cv2.COLOR_HSV2RGB) return rgb_flow
def hog(img, bin_n=8, cell_size=4): img = cv2.resize(img,(128,128)) gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bin = np.int32(bin_n*ang/(2*np.pi)) bin_cells = [] mag_cells = [] cellx = celly = cell_size for i in range(0,img.shape[0]/celly): for j in range(0,img.shape[1]/cellx): bin_cells.append(bin[i*celly : i*celly+celly, j*cellx : j*cellx+cellx]) mag_cells.append(mag[i*celly : i*celly+celly, j*cellx : j*cellx+cellx]) hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # transform to Hellinger kernel eps = 1e-7 hist /= hist.sum() + eps hist = np.sqrt(hist) hist /= norm(hist) + eps hist_out = np.reshape(hist,(32,32,8)) return hist_out
def extract_optical_flow(fn, times, frames=8, scale_factor=1.0): cap = cv2.VideoCapture(fn) n_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT) outputs = [] if n_frames < frames * 2: return outputs def resize(im): if scale_factor != 1.0: new_size = (int(im.shape[1] * scale_factor), int(im.shape[0] * scale_factor)) return cv2.resize(im, new_size, interpolation=cv2.INTER_LINEAR) else: return im for t in times: cap.set(cv2.CAP_PROP_POS_FRAMES, min(t * n_frames, n_frames - 1 - frames)) ret, frame0 = cap.read() im0 = resize(cv2.cvtColor(frame0, cv2.COLOR_BGR2GRAY)) mags = [] middle_frame = frame0 for f in range(frames - 1): ret, frame1 = cap.read() if f == frames // 2: middle_frame = frame1 im1 = resize(cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)) flow = cv2.calcOpticalFlowFarneback(im0, im1, None, 0.5, 3, 15, 3, 5, 1.2, 0) mag, ang = cv2.cartToPolar(flow[...,0], flow[...,1]) mags.append(mag) im0 = im1 mag = np.sum(mags, 0) mag = mag.clip(min=0) norm_mag = (mag - mag.min()) / (mag.max() - mag.min() + 1e-5) x = middle_frame[..., ::-1].astype(np.float32) / 255 outputs.append((x, norm_mag)) return outputs
def extract_optical_flow(fn, n_frames=34): img = dd.image.load(fn) if img.shape != (128*34, 128, 3): return [] frames = np.array_split(img, 34, axis=0) grayscale_frames = [fr.mean(-1) for fr in frames] mags = [] skip_frames = np.random.randint(34 - n_frames + 1) middle_frame = frames[np.random.randint(skip_frames, skip_frames+n_frames)] im0 = grayscale_frames[skip_frames] for f in range(1+skip_frames, 1+skip_frames+n_frames-1): im1 = grayscale_frames[f] flow = cv2.calcOpticalFlowFarneback(im0, im1, None, # flow 0.5, # pyr_scale 3, # levels np.random.randint(3, 20), # winsize 3, #iterations 5, #poly_n 1.2, #poly_sigma 0 # flags ) mag, ang = cv2.cartToPolar(flow[...,0], flow[...,1]) mags.append(mag) im0 = im1 mag = np.sum(mags, 0) mag = mag.clip(min=0) #norm_mag = np.tanh(mag * 10000) norm_mag = (mag - mag.min()) / (mag.max() - mag.min() + 1e-5) outputs = [] outputs.append((middle_frame, norm_mag)) return outputs
def compute_flow(impath1, impath2, outdir, fbcodepath=os.getenv("HOME") + '/fbcode'): stem = os.path.splitext(os.path.basename(impath1))[0] deepmatch_cmd = os.path.join(fbcodepath, '_bin/experimental/deeplearning/dpathak' + '/video-processing/deepmatch/deepmatch') call([deepmatch_cmd, impath1, impath2, '-out', os.path.join(outdir, stem + '_sparse.txt'), '-downscale', '2']) img1 = cv2.imread(impath1).astype(float) M = np.zeros((img1.shape[0], img1.shape[1]), dtype=np.float32) filt = np.array([[1., -1.]]).reshape((1, -1)) for c in range(3): gx = convolve2d(img1[:, :, c], filt, mode='same') gy = convolve2d(img1[:, :, c], filt.T, mode='same') M = M + gx**2 + gy**2 M = M / np.max(M) with open(os.path.join(outdir, '_edges.bin'), 'w') as f: M.tofile(f) epicflow_command = os.path.join(fbcodepath, '_bin/experimental/deeplearning/dpathak' + '/video-processing/epicflow/epicflow') call([epicflow_command, impath1, impath2, os.path.join(outdir, '_edges.bin'), os.path.join(outdir, stem + '_sparse.txt'), os.path.join(outdir, 'flow.flo')]) flow = read_flo(os.path.join(outdir, 'flow.flo')) hsv = np.zeros_like(img1).astype(np.uint8) hsv[..., 1] = 255 mag, ang = cv2.cartToPolar(flow[..., 0].astype(float), flow[..., 1].astype(float)) hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX) hsv[..., 0] = ang * 180 / np.pi / 2 bgr = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR) cv2.imwrite(os.path.join(outdir, stem + '_flow.png'), bgr)
def run_deepmatch(imname1, imname2): command = os.getenv("HOME") + '/fbcode/_bin/experimental/' + \ 'deeplearning/dpathak/video-processing/deepmatch/deepmatch' call([command, imname1, imname2, '-out', os.getenv("HOME") + '/local/data/trash/tmp.txt', '-downscale', '2']) with open(os.getenv("HOME") + '/local/data/trash/tmp.txt', 'r') as f: lines = f.readlines() lines = [x.strip().split(' ') for x in lines] vals = np.array([[float(y) for y in x] for x in lines]) x = ((vals[:, 0] - 8.) / 16.).astype(int) y = ((vals[:, 1] - 8.) / 16.).astype(int) U = np.zeros((int(np.max(y)) + 1, int(np.max(x)) + 1)) U[(y, x)] = vals[:, 2] - vals[:, 0] V = np.zeros((int(np.max(y)) + 1, int(np.max(x)) + 1)) V[(y, x)] = vals[:, 3] - vals[:, 1] img1 = cv2.imread(imname1) U1 = cv2.resize(U, (img1.shape[1], img1.shape[0])) V1 = cv2.resize(V, (img1.shape[1], img1.shape[0])) mag, ang = cv2.cartToPolar(U1, V1) print(np.max(mag)) hsv = np.zeros_like(img1) hsv[..., 1] = 255 hsv[..., 0] = ang * 180 / np.pi / 2 hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX) bgr = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR) return bgr
def extract_optical_flow(fn, times, frames=8, scale_factor=1.0): cap = cv2.VideoCapture(fn) if not cap.isOpened(): return [] n_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT) outputs = [] if n_frames < frames * 2: return outputs def resize(im): if scale_factor != 1.0: new_size = (int(im.shape[1] * scale_factor), int(im.shape[0] * scale_factor)) return cv2.resize(im, new_size, interpolation=cv2.INTER_LINEAR) else: return im for t in times: cap.set(cv2.CAP_PROP_POS_FRAMES, min(t * n_frames, n_frames - 1 - frames)) ret, frame0 = cap.read() im0 = resize(cv2.cvtColor(frame0, cv2.COLOR_BGR2GRAY)) mags = [] middle_frame = frame0 flows = [] for f in range(frames - 1): ret, frame1 = cap.read() if f == frames // 2: middle_frame = frame1 im1 = resize(cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)) flow = cv2.calcOpticalFlowFarneback(im0, im1, None, 0.5, # py_scale 8, # levels int(40 * scale_factor), # winsize 10, # iterations 5, # poly_n 1.1, # poly_sigma cv2.OPTFLOW_FARNEBACK_GAUSSIAN) #mag, ang = cv2.cartToPolar(flow[...,0], flow[...,1]) #mags.append(mag) flows.append(flow) im0 = im1 flow = (np.mean(flows, 0) / 100).clip(-1, 1) #flow = np.mean(flows, 0) #flow /= (flow.mean() * 5 + 1e-5) #flow = flow.clip(-1, 1) #flows = flows / (np.mean(flows, 0, keepdims=True) + 1e-5) x = middle_frame[..., ::-1].astype(np.float32) / 255 outputs.append((x, flow)) return outputs
