Stack Overflow
Stack Overflow

Questions tagged [pose-estimation]

The specific task of determining the position and orientation of an object in an image relative to the camera coordinates is called Pose Estimation.

The pose of a camera is also known as the camera Extrinsic Parameters. It is a 3x4 matrix where the first 3 columns are the rotation (orientation) and the las column is the translation (position).

Camera Pose matrix. Rotation and Translation

291 questions
2
votes
1 answer

How to calculate the confidence score of a keypoint estimation from a heatmap

I have tried to build the Convolutional Pose Machines model from this paper here (https://arxiv.org/pdf/1602.00134.pdf). The model works fine and outputs 15 heatmaps (one per keypoint + 1 for background). From these heatmaps I can calculate the…
Johann Gerberding
  • 21
  • 4
2
votes
1 answer

how to combine (merge) different regression models

I am working on training different models for different estimation of human pose problems. actually, what I need is to get different outputs from a regression model for different joints of the human body. After I did searches for this problem, I…
tara
  • 51
  • 8
2
votes
0 answers

Find actual distance betweeen two aruco markers in meters

Context: I have a big 2mx2m arena on which 4 aruco markers are printed, their position from a corner of the arena is known and is fixed. Now I have another aruco marker on a robot moving over this arena. PS the position known are in 2d. Problem: I…
Ayush Patel
  • 21
  • 3
2
votes
1 answer

Tensorflow.js Posenet with HTMLVideoElement returns position 0,0

TensorFlow.js version tensorflow.js 1.5.2 posenet 2.2.1 Browser version Google Chrome Version 80.0.3987.149 (Official Build) (64-bit) Problem I am trying to do pose estimation with my camera passing the video element to posenet but the position…
Rogelio Gámez
  • 477
  • 1
  • 4
  • 5
2
votes
0 answers

How to improve a trajectory of a camera, built from rotation and translation?

I am trying to recover a trajectory of a 2D camera, using a sequence of 2D-images and OpenCV. But the trajectory I get is not so good as I would like it to be. It goes back and forth instead of going just forth. I have a sequence of photos taken on…
Olya Agapova
  • 31
  • 4
2
votes
0 answers

Use Raspberry's VideoCore IV GPU for chainer model. Requires cupy? cuda?

I am trying to run Idein/chainer-pose-proposal-net on a Raspberry Pi 3 B+. This is a pose estimation model (specifically Pose Proposal Networks by Taiki Sekii) in Chainer. In the README it is suggested that it can use the Raspberry's VideoCore IV…
Martin
  • 1,141
  • 14
  • 24
2
votes
0 answers

solvePnP results differ too much from expected results (Python, OpenCV)

I have a car with a camera, an imu and a gps on top of it. The camera takes pictures while driving around. The pictures and the gps coordinates are synchronized. Now, I am trying to get the camera pose from the pictures (relative to the imu), but…
trippeljojo
  • 65
  • 1
  • 11
2
votes
0 answers

Extracting keypoints from posenet to a json file?

I am looking into the tensorflow implementation of posenet to do pose estimation in real time and also if possible in an offline mode. I am looking into the following repo : https://github.com/tensorflow/tfjs-models/tree/master/posenet The…
tim tensor
  • 39
  • 8
2
votes
1 answer

How to use outputs of posenet model in tflite

I am using the tflite model for posenet from here. It takes input 1*353*257*3 input image and returns 4 arrays of dimens 1*23*17*17, 1*23*17*34, 1*23*17*64 and 1*23*17*1. The model has an output stride of 16. How can I get the coordinates of all 17…
Death14Stroke
  • 101
  • 1
  • 6
2
votes
1 answer

ValueError: Error when checking target : expected dense_4 to have shape (4, ) but got array with shape (1, )

I have tried this model (" https://github.com/LZQthePlane/Online-Realtime-Action-Recognition-based-on-OpenPose ")for my own data set (i have given sit action video and converted to csv file ). Csv file contains 1000 records. Now in action_enum.py I…
Malathi K
  • 71
  • 12
2
votes
1 answer

OverflowError: signed integer is greater than maximum

I am getting an overflow error sometimes signed integer greater than or less than maximum or minimum respectively. My code for pose estimation: import cv2 import dlib import numpy as np from imutils import face_utils face_landmark_path =…
Aditya Kumar
  • 93
  • 1
  • 3
  • 7
2
votes
0 answers

cv2 pose estimation using homography matrix

I am trying to calculate the pose of image Y, given image X. Image Y is the same as image X rotated 90º degrees. 1 -So, for starters i find the matches between both images. 2 -Then i store all the good matches. 3 -The homography between the the…
user201305016
  • 41
  • 4
2
votes
0 answers

Camera position in world coordinate is not working but object pose in camera co ordinate system is working properly

I am working on the camera (iphone camera) pose estimation for head mount device (Hololens) using LEDs as a marker, using the solvepnp. I have calibrated the camera below is the camera intrinsic parameters /* approx model*/ double focal_length =…
slv
  • 21
  • 2
2
votes
1 answer

How to calculate an epipolar line with a stereo pair of images in Python OpenCV

How can I take two images of an object from different angles and draw epipolar lines on one based on points from the other? For example, I would like to be able to select a point on the left picture using a mouse, mark the point with a circle, and…
JinseiNagai
  • 351
  • 1
  • 2
  • 10
2
votes
2 answers

TensorFlow - keypoint detection yields a heatmap of zeros

I'm using a detection-based CNN for hand pose estimation(finding hand joints in a depth image of a single hand). My plan was to first use an FCN to find the 2D coordinates of all the 16 key points. The backbone is ResNet-50-FPN and the computation…
Harper Long
  • 98
  • 9
1 2 3
…
19 20