Spaces:
Running
Running
File size: 5,013 Bytes
b7eedf7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
import sys
sys.path.append('droid_slam')
from tqdm import tqdm
import numpy as np
import torch
import lietorch
import cv2
import os
import glob
import time
import argparse
from torch.multiprocessing import Process
from droid import Droid
from pycocotools import mask as masktool
import torch.nn.functional as F
def show_image(image):
image = image.permute(1, 2, 0).cpu().numpy()
cv2.imshow('image', image / 255.0)
cv2.waitKey(1)
def image_stream(imagedir, calib, stride):
""" image generator """
# calib = np.loadtxt(calib, delimiter=" ")
fx, fy, cx, cy = calib[:4]
K = np.eye(3)
K[0,0] = fx
K[0,2] = cx
K[1,1] = fy
K[1,2] = cy
image_list = sorted(glob.glob(f'{imagedir}/*.jpg'))
image_list = image_list[::stride]
for t, imfile in enumerate(image_list):
image = cv2.imread(imfile)
if len(calib) > 4:
image = cv2.undistort(image, K, calib[4:])
h0, w0, _ = image.shape
h1 = int(h0 * np.sqrt((384 * 512) / (h0 * w0)))
w1 = int(w0 * np.sqrt((384 * 512) / (h0 * w0)))
image = cv2.resize(image, (w1, h1))
image = image[:h1-h1%8, :w1-w1%8]
image = torch.as_tensor(image).permute(2, 0, 1)
intrinsics = torch.as_tensor([fx, fy, cx, cy])
intrinsics[0::2] *= (w1 / w0)
intrinsics[1::2] *= (h1 / h0)
yield t, image[None], intrinsics
def save_reconstruction(droid, reconstruction_path):
from pathlib import Path
import random
import string
t = droid.video.counter.value
tstamps = droid.video.tstamp[:t].cpu().numpy()
images = droid.video.images[:t].cpu().numpy()
disps = droid.video.disps_up[:t].cpu().numpy()
poses = droid.video.poses[:t].cpu().numpy()
intrinsics = droid.video.intrinsics[:t].cpu().numpy()
Path("reconstructions/{}".format(reconstruction_path)).mkdir(parents=True, exist_ok=True)
np.save("reconstructions/{}/tstamps.npy".format(reconstruction_path), tstamps)
np.save("reconstructions/{}/images.npy".format(reconstruction_path), images)
np.save("reconstructions/{}/disps.npy".format(reconstruction_path), disps)
np.save("reconstructions/{}/poses.npy".format(reconstruction_path), poses)
np.save("reconstructions/{}/intrinsics.npy".format(reconstruction_path), intrinsics)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("--imagedir", type=str, help="path to image directory")
parser.add_argument("--calib", type=str, help="path to calibration file")
parser.add_argument("--t0", default=0, type=int, help="starting frame")
parser.add_argument("--stride", default=3, type=int, help="frame stride")
parser.add_argument("--weights", default="droid.pth")
parser.add_argument("--buffer", type=int, default=512)
parser.add_argument("--image_size", default=[240, 320])
parser.add_argument("--disable_vis", action="store_true")
parser.add_argument("--beta", type=float, default=0.3, help="weight for translation / rotation components of flow")
parser.add_argument("--filter_thresh", type=float, default=2.4, help="how much motion before considering new keyframe")
parser.add_argument("--warmup", type=int, default=8, help="number of warmup frames")
parser.add_argument("--keyframe_thresh", type=float, default=4.0, help="threshold to create a new keyframe")
parser.add_argument("--frontend_thresh", type=float, default=16.0, help="add edges between frames whithin this distance")
parser.add_argument("--frontend_window", type=int, default=25, help="frontend optimization window")
parser.add_argument("--frontend_radius", type=int, default=2, help="force edges between frames within radius")
parser.add_argument("--frontend_nms", type=int, default=1, help="non-maximal supression of edges")
parser.add_argument("--backend_thresh", type=float, default=22.0)
parser.add_argument("--backend_radius", type=int, default=2)
parser.add_argument("--backend_nms", type=int, default=3)
parser.add_argument("--upsample", action="store_true")
parser.add_argument("--reconstruction_path", help="path to saved reconstruction")
args = parser.parse_args()
args.stereo = False
torch.multiprocessing.set_start_method('spawn')
droid = None
# need high resolution depths
if args.reconstruction_path is not None:
args.upsample = True
tstamps = []
for (t, image, intrinsics) in tqdm(image_stream(args.imagedir, args.calib, args.stride)):
if t < args.t0:
continue
if not args.disable_vis:
show_image(image[0])
if droid is None:
args.image_size = [image.shape[2], image.shape[3]]
droid = Droid(args)
droid.track(t, image, intrinsics=intrinsics)
if args.reconstruction_path is not None:
save_reconstruction(droid, args.reconstruction_path)
traj_est = droid.terminate(image_stream(args.imagedir, args.calib, args.stride))
|