Stack Overflow
Stack Overflow

Questions tagged [cascade-classifier]

A particular case of Ensemble learning, which is based on the concatenation of several classifiers, using all information collected from the output from a given classifier as additional information for the next classifier in the cascade.

170 questions
3
votes
1 answer

Improving LBP/HAAR detection XML cascades

I am trying to do a car detector from UAV images with Python 2.7 and OpenCV 2.4.13. The goal is to detect cars from an upper view in any direction, in urban environments. I am facing time execution and accuracy problems. Detector works fine when I…
Federico
  • 31
  • 2
3
votes
2 answers

OpenCV: detectMultiScale() gives too many points out of the object

I trained my pc with opencv_traincascade all one day long to detect 2€ coins using more than 6000 positive images similar to the following: Now, I have just tried to run a simple OpenCV program to see the results and to check the file cascade.xml.…
SagittariusA
  • 5,289
  • 15
  • 73
  • 127
3
votes
1 answer

Error in Cascade training "trainCascadeObjectDetector" in Matlab

I'm trying to train a cascade classifier by the built-in Matlab function "trainCascadeObjectDetector", but that always shows the following error message when I call this…
Zhi Lu
  • 527
  • 5
  • 22
3
votes
3 answers

Defining an (initial) set of Haar Like Features

When it comes to cascade classifiers (using haar like features) I always read that methods like AdaBoosting are used to select the 'best' features for detection. However this only works if there is some initial set of features to begin boosting.…
user2457516
3
votes
4 answers

OpenCV: Improving the speed of Cascades detection

I need to detect people in real time using OpenCV Cascades. Currently I am using the trained cascade files which comes with OpenCV but later I will train my own LBP Cascades to achieve more speed. I do have a question. what are the ways to speed up…
PeakGen
  • 21,894
  • 86
  • 261
  • 463
3
votes
1 answer

How to deal with HOG feature arrays to use for classification in scikit-learn?

I want to extract HOG features from an image so that I can put them through a classifier (AdaBoost.SAMME, in particular, using scikit-learn: multiclass Adaboost in scikit-learn ensemble). To do that, I need to convert the image into an array-like of…
user961627
  • 12,379
  • 42
  • 136
  • 210
2
votes
0 answers

detectMultiScale hangs when using LBP cascade classifier (OpenCV 4.8.0, C++)

I've trained an LBP cascade classifier for car detection using OpenCV 4.8.0. When I try to use it, the detectMultiScale function hangs. Here's the classifier: BOOST …
SNBS
  • 671
  • 2
  • 22
2
votes
0 answers

Retraining OPENCV Cascade Classifier in python using pretrained XML file over new training data

So I want to train a Open-CV cascade classifier to detect frontal-faces though i want to do it in IR modal. Is there a way I could use the opencv provided xml file for frontal faces from here and train it on my new images to improive the classifier.…
Kathan Vyas
  • 355
  • 3
  • 16
2
votes
0 answers

Pickling cv2.CascadeClassifier

I'm trying to quickly check if cv2.CascasdeClassifier objects can be pickled using a way or another ; as natively they can't: In [1]: import pickle, cv2 In [2]: c = cv2.CascadeClassifier() …
gst
  • 431
  • 1
  • 4
  • 16
2
votes
1 answer

Meaning of Parameters of detectMultiScale(a, b, c)

OpenCV-Python version 3.4.1 I am trying to detect multiple objects through a camera. The objects are Face, eyes, spoon, pen. Spoon and Pen are particular i.e. it should only detect the Pen and Spoon that I have trained it with. But it detects all…
Winbuntu
  • 127
  • 1
  • 4
  • 15
2
votes
1 answer

OpenCV CascadeClassifier Python out of memory

Here is my code: def load_cascades(): cascades = [] for root, dirs, files in os.walk(rooted('data/logos')): for fname in files: if fname == 'cascade.xml': path = os.path.join(root, fname) …
kabeersvohra
  • 1,049
  • 1
  • 14
  • 31
2
votes
1 answer

Best Cascade for detecting Mororcycles (side views) HOG/LBP/HAAR/ Other

I am trying to train cascade to detect motorcycle. I tried LBP (with stage 15) and it's giving too much false negatives, Here is what I did till now, I recorded required traffic videos . Developed a program to track all moving objects and when it…
Severus Tux
  • 265
  • 3
  • 13
2
votes
0 answers

Eliminating false positives detected by an OpenCV face classifier

I am working with thermal videos. My project determines in real-time whether each frame contains a face or not. By "contains a face", I mean this: (one face, this size and angle, per frame) I've trained an LBP cascade classifier for this purpose.…
FartVader
  • 143
  • 1
  • 3
  • 13
2
votes
0 answers

Error in generating samples for trainCascadeObjectDetector in MATLAB

I was trying to train the cascade object detector in matlab with the 30 positive images with specified ROI and 10 negative images (without specified ROI). My code resembles with the matlab example code of 'Stop Sign Detector'. But when I tried to…
user3660102
  • 19
  • 2
2
votes
0 answers

access violation in CascadeObjectDetector using modified XML file

I modified the OpenCV XML file (classifier) which is generated by TrainCascadeObjectDetector of MATLAB, I deleted some items. When i tried to load it with: detector = vision.CascadeObjectDetector('classifier.xml'); I get an access violation…
matlab22
  • 69
  • 8
1
2
3
…
11 12