Stack Overflow
Stack Overflow

Questions tagged [keypoint]

In computer vision field a keypoint is an interest point detected by the SIFT algorithm. Use this tag for programming issues related to the use of keypoints in the field of computer vision.

is an algorithm that finds "keypoints" in images that are robust to scale variations, perspective and lighting. In order to identify those keypoints, descriptors are generated basing on the surrounding pixels of the keypoint. This way, the same keypoints can be located in different images, which is called matching.

Programing questions related to keypoints in computer vision applications are an appropriate field for this tag.

187 questions
1
vote
1 answer

How to convert world coordinates to image coordinates for datasets like Shrec 17 and DHG

I am working on a machine learning model for detecting Keypoints for hands using depth image. So far the datasets I have seen includes labels for keypoints/skeletons in world and image view (See Shrec 17 or DHG dataset). I have seen couple of papers…
Saurabh Pradhan
  • 75
  • 5
1
vote
1 answer

How to start with landmark detector for custom objects?

I am trying to make a landmark detector for a custom object, this panel: I am going through multiple approaches to it: using heatmaps and regression-based ones. I tried hands on this Kaggle notebook and found it useful, but has data in grayscale…
Pe Dro
  • 2,651
  • 3
  • 24
  • 44
1
vote
2 answers

Problem with converting Tensorflow model of Superpoint to tflite model for Android

I am trying to convert the saved model from Tensorflow implementation of Superpoint to a tflite model to test it on Android. I started with downloading the saved model from…
Roman
  • 31
  • 4
1
vote
1 answer

How to do hyperparameter tuning in Detectron2

Detectron2 COCO Person Keypoint Detection Baselines with Keypoint R-CNN R50-FPN How do I do hyperparameter tuning with the model above? Which files do I have to open? Thanks
asz999
  • 23
  • 1
  • 4
1
vote
0 answers

OpenPose for Batch Processing Videos

I am working on pose estimation for hands and face using OpenPose (https://github.com/CMU-Perceptual-Computing-Lab/openpose) on Google Colab. I have hundred videos in my dataset, right now I am able to run OpenPose on each video individually. Is…
Shambhavi Mishra
  • 23
  • 2
1
vote
0 answers

Finding 3D position of an object given 2 Images

Hello I would like to find the 3D position of an object given 2 different views of an object. Things that I can provide here are: I can calculate the intrinsic matrix of each camera. I also know the 2D coordinates of the objects see here. Providing…
Komanechi
  • 11
  • 2
1
vote
0 answers

Displaying coordinate keypoints in OpenCV

I run a simple detector on an aerial image to detect blobs according to the parameters I set (i don't care for distractors for now). Eventually, I need to display the coordinates (x,y) of the blobs on the image (at least the ones bigger than a…
Andrea Rolli
  • 11
  • 2
1
vote
0 answers

How are groundtruths (heatmaps and PAFs) in pose estimation generated?

I hope you're doing well in this time of the pandemic. I'm working with keypoint processing; more specifically, trying to identify the location and orientation of an object based on its keypoints. I have read some research papers and saw that they…
bardhito
  • 11
  • 2
1
vote
0 answers

Direct Heatmap Regression with Fully Convolutional Nets

I'm trying to develop a fully-convolutional neural net to estimate the 2D locations of keypoints in images that contain renders of known 3D models. I've read plenty of literature on this subject (human pose estimation, model based estimation, graph…
Will Snyder
  • 51
  • 1
  • 3
1
vote
1 answer

What are Octaves and Sub levels in KAZE and AKAZE?

I am having a hard time trying to understand the Octaves and Sub-levels in the Non-Linear Scale space (KAZE and AKAZE). For the SIFT- Octaves is a collection of same sized images and sub-level is number of gaussian blurred images to be generated in…
Karan Kothari
  • 91
  • 2
  • 12
1
vote
0 answers

Python: Crop image and detect new keypoints

I have some images with keypoints marking the corners of a mask. I want to crop these images and define the new keypoints. For example, given this image. Keypoints marked by the black 'x' I want to crop the image, i.e. the grey box and detect the…
Lloyd Rayner
  • 1,009
  • 2
  • 7
  • 10
1
vote
1 answer

Why am i getting not enough values to unpack (expected 2, got 1) for some images?

import cv2 import numpy as np import sys from IPython.display import Image from matplotlib import pyplot as plt import numpy import os img = cv2.imread('C:\\Users\\not-cropped.jpg') gray= cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) search_params =…
James
  • 77
  • 1
  • 1
  • 6
1
vote
0 answers

Two questions regarding 2D human pose detection

1). I am training a network for 2D pose detection, and current plan is add MPII, LSP and Human3.6 in the training set. It looks like each dataset has slightly different set of marked keypoints. How should I deal with it? To my understanding, I…
David
  • 23
  • 4
1
vote
1 answer

Saving KeyPoint as String and converting back to KeyPoint

I would like to cache KeyPoint in a JSON file and then retrieve them later for use in a FlannBasedMatcher. Is there a way to convert the KeyPoint to something like an array of strings or floats that could be stored and then retreived from a JSON…
Anters Bear
  • 1,816
  • 1
  • 15
  • 41
1
vote
0 answers

How to enable non-free algorythms (SIFT, SURF) of OpenCV for Python?

I compiled the opencv-master by adding extra modules from opencv_contrib-master with CMake based on the following guide:…
Gary
  • 11
  • 2
1 2 3
…
12 13