Questions tagged [computer-vision]
Use this tag for questions related to Computer Vision -- any aspect of software that enables computers to perceive, understand and react to their environment using cameras. For questions related to image filtering and quantification, use the tag [image-processing] instead.
computer-vision
15,805
questions
2
votes
0
answers
62
views
Image Stitching opencv
I'm trying to stitch two images together using OpenCV's Stitcher class, but despite getting good matches between the two images, the stitching process fails. I've checked my code and the matches seem ...
- 93
0
votes
0
answers
37
views
How to accurately calculate absolute bbox coordinates of detected text in Doctr ocr?
I have been trying to draw bbox on a picture of the document which I am trying to ocr using mindee-doctr to see the detected lines of text. The problem I am facing is the absolute coordinates of the ...
0
votes
2
answers
85
views
Identify two figures for similarity [closed]
I am trying to find a reliable way to determine the similarity between geometric shapes (polygons).
In one of my approaches, I tried to use the cvopen library and the findContours() and matchShapes() ...
- 125
-1
votes
0
answers
98
views
How do I mark the differences between the two pictures with C++?
I want to compare the two images below, but none of the codes I have tried produce any meaningful output. Here are the pictures :
Orginal
Changed
Desired Result
First, the sizes of the pictures are ...
- 1
0
votes
0
answers
27
views
How do I convert an image that is a top view of a 3D model of a house into a 2D floor plan?
How do I convert an image, which is a top view of a 3D model of a house, into a 2D floor plan (e.g., an AutoCAD drawing)? What manual drawing techniques, mathematics, algorithms, and software are ...
- 383
0
votes
0
answers
35
views
Computer Vision, Extrinsic calibration. Determining the camera pose of a number of cameras using OpenCV, SfM(custom) and Python
I am a novice programmer and new to this platform, so I apologise upfront for any ignorance.
Forewarning: The problem I seek to overcome may not be strictly programming(python) based, but instead ...
- 1
1
vote
0
answers
80
views
Image stitching with opencv-python
So I've been trying to stitch some images together to create one big panorama but the Stitcher from OpenCV doesn't want to do so.
There's enough overlap on the images so the Stitcher should be able to ...
- 93
-2
votes
0
answers
11
views
CNN Predicting Random Images
I have Trained the model with CNN. The MODEl i have Trained for Binary classification with chest - X - Ray images. Even after training the model. Model is predicting Random images like cars, animals ...
0
votes
0
answers
39
views
OpenCV : How to compute 3D points with SfM methods with a known fundamental matrix?
For a university project, we are working on implementing a basic SfM pipeline, using Middlebury's "temple" dataset. This means that, for each image, the projection matrix for that given ...
-2
votes
0
answers
37
views
Should I train an OCR model for handwritten text recognition for a mobile app or just avail API services?
Is it worth building a handwritten text recognition model for a mobile app (need to finish this project by next month)? Must be at least 75% accurate.
I'm building a simple Android mobile app (react ...
- 1
0
votes
0
answers
66
views
Parsing Error with YOLOv3 and OpenCV 4.10.0 when reading yolov3.cfg
I'm encountering a parsing error when attempting to load a YOLOv3 model using OpenCV 4.10.0 in Python. Specifically, the error occurs while trying to read the configuration file yolov3.cfg. Despite ...
0
votes
0
answers
22
views
reconstructing 3D points using cv2.triangulatePoints vs doing it with equations do not yield same results
In the provided code snippet, I am performing stereo triangulation to reconstruct 3D points from corresponding 2D points captured by two different cameras.
First, I loaded calibration data such as ...
-1
votes
0
answers
16
views
Taking input from an Action Classifier Model in UE5
I have trained an action classifier model that classifies players action using web cam in real time.
It uses media pipe to detect the pose of the person and feeds the model with x, y, depth and ...
0
votes
0
answers
33
views
How to unittest a complex calculation?
In the domain of computer vision, I want to unittest the projection of 3d coordinates to 2d(image) space, and some similar problems. My issue is that I cannot define in terms of numbers, what the ...
- 1
0
votes
0
answers
31
views
Using instance segmentation on human cells for biology project
I am stuck doing some instance segmentation for my project that is related to biology.
I have some pictures of human cells (there is around 5 cells per image) and what I want to achieve is to create a ...
