Stack Overflow
Stack Overflow

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 enables images, or sequences of images, to be processed by a computer using algorithms. There are many aspects to computer vision, including mathematics, physics (especially optics), imaging hardware, , and .

Some basic techniques used in computer vision are:

  • Image acquisition
  • Pre-processing
  • Feature Extraction
  • Detection/Segmentation
  • High-Level processing
  • Decision making
13127 questions
4
votes
1 answer

I want to know if there is the clothing object class in the MS COCO dataset?

I want to do something about clothing segmentation, so I need to train the network on dataset which has the clothing class. Anyone can answer me? I do not find something about classes in the http://mscoco.org/
guoqiang Wei
  • 73
  • 1
  • 6
4
votes
2 answers

'Resource exhausted' memory error when trying to train a Keras model

I'm trying to train a VGG19 model for a binary image classification problem. My dataset doesn't fit into the memory, so I use batches and the .fit_generator function of the model. However, even when trying to train with batches, I get the following…
Denis Yakovenko
  • 2,398
  • 3
  • 38
  • 70
4
votes
1 answer

TensorFlow: Does each session run initiate a different batch of data in a graph?

Meaning to say if I have the following graph like: images, labels = load_batch(...) with slim.arg_scope(inception_resnet_v2_arg_scope()): logits, end_points = inception_resnet_v2(images, num_classes = dataset.num_classes, is_training =…
kwotsin
  • 2,642
  • 8
  • 27
  • 55
4
votes
1 answer

How to find the angle formed by blades of a wind turbine when the yaw is changed?

This is a continuation of the question from Here-How to find angle formed by the blades of a wind turbine with respect to a horizontal imaginary axis? I've decided to use the following methodology for this-  Getting a frame from a camera and…
AGP
  • 53
  • 8
4
votes
1 answer

Deep learning for face detection in mobile device

I want to create a face detection mobile app and I want to do it with a regular Deep Learning(Convolutional Network). I will train it with my computer and use trained data in the mobile app. My question is that: can I get very fast computation in…
Fcoder
  • 8,466
  • 17
  • 54
  • 90
4
votes
1 answer

HOG Person Detector: False Positive detections on background subtracted images

I am working on a project which requires detection of people in a scene. Initially after running the HOG detector on the original frames a particular background object was being detected as a person on all the frames, giving me 3021 false positive…
Nik
  • 175
  • 1
  • 8
4
votes
5 answers

Faster-RCNN, why don't we just use only RPN for detection?

As we know, faster-RCNN has two main parts: one is region proposal network(RPN), and another one is fast-RCNN. My question is, now that region proposal network(RPN) can output class scores and bounding boxes and is trainable, why do we need…
user3094631
  • 285
  • 1
  • 12
4
votes
2 answers

Tensorflow: Is preprocessing on TFRecord files faster than real-time data preprocessing?

In Tensorflow, it seems that preprocessing could be done on either during training time, when the batch is created from raw images (or data), or when the images are already static. Given that theoretically, the preprocessing should take roughly…
kwotsin
  • 2,642
  • 8
  • 27
  • 55
4
votes
0 answers

How to get the z coordinate (distance) from a Kinect v2 RGB coordinate?

I am trying to convert libfreenect RGB coordinates into DEPTH coordinates, in order to find the z coordinate (distance of object). I tried so many things but I was not able to get the resolutions right. Any ideas? I am using rgbmat in order to apply…
Engo
  • 749
  • 1
  • 13
  • 42
4
votes
4 answers

Drawing contours using cv2.approxPolyDP() in python

I'm unable to draw complete contours of a shape using cv2.approxPolyDP(). I'm getting the following result: But I want output like this: Here's my code: import cv2 im = cv2.imread('C:\Python27\Test\Targets\s1.jpg') # read picture imgray =…
Vikas Tomar
  • 59
  • 1
  • 1
  • 9
4
votes
1 answer

What is the difference between contours and contours[0] when len(contours)=1?

I want to find the contours of an image to then draw its convex hull. What I am doing is loading the image, threshold it, find its contours and then draw the convex hull. gray = cv2.imread(test_paths[i], 0) ret, thresh = cv2.threshold(gray, 127,…
Manuel Lagunas
  • 2,026
  • 15
  • 30
4
votes
1 answer

What to do with negative rho values in hough transform?

Here is my code for creating the hough accumulator for lines in image : void hough_lines_acc(cv::Mat img_a_edges, std::vector > &hough_acc) { for (size_t r = 0; r < img_a_edges.rows; r++) { for (size_t c = 0; c <…
darth vader
  • 181
  • 1
  • 2
  • 13
4
votes
4 answers

Is it possible for either Microsoft Computer Vision API or Google's Cloud Vision API to get a location for objects?

I am trying to develop an application that needs to know the location of tagged objects in an image. Knowing that there is a "piano" in an image is not enough, I need to know where that piano is in the image. Both Microsoft's Computer Vision API…
abagshaw
  • 4,960
  • 3
  • 28
  • 58
4
votes
2 answers

Detecting individual boxes in W2 with opencv - python

I've done extensive research and cannot find a combination of techniques that will achieve what I need. I have a situation where I need to perform OCR on hundreds of W2s to extract the data for a reconciliation. The W2s are very poor quality, as…
keyoung1
  • 53
  • 6
4
votes
1 answer

Crop image with corrected distortion in OpenCV (Python)

I've been looking for a response in other posts and trying several ways to get it but I couldn't find anything solving my problem. I'm trying to correct optical distortion in an image and I get it, but now I want to crop my image in order to delete…
Carlos
  • 675
  • 1
  • 7
  • 27
1 2 3
…
99 100