Styjun

What is "industrial ethernet"?

Why tighten down in a criss-cross pattern?

Dates on degrees don’t make sense – will people care?

"How can you guarantee that you won't change/quit job after just couple of months?" How to respond?

What does the hyphen "-" mean in "tar xzf -"?

Can Ogre clerics use Purify Food and Drink on humanoid characters?

Has there been any indication at all that further negotiation between the UK and EU is possible?

Do I need a shock-proof watch for cycling?

Why do textbooks often include the solutions to odd or even numbered problems but not both?

What is the legal status of travelling with methadone in your carry-on?

What does "play with your toy’s toys" mean?

Array initialization optimization

Is "Busen" just the area between the breasts?

Why is it recommended to mix yogurt starter with a small amount of milk before adding to the entire batch?

Count All Possible Unique Combinations of Letters in a Word

How can I politely work my way around not liking coffee or beer when it comes to professional networking?

What's currently blocking the construction of the wall between Mexico and the US?

Heavily limited premature compiler translates text into excecutable python code

How large would a mega structure have to be to host 1 billion people indefinitely?

Non-flat partitions of a set

What happens to Cessna electric flaps that are moving when power is lost?

What could exist inside and between the walls of a Dyson Sphere?

Methodology: Writing unit tests for another developer

Trainee keeps missing deadlines for independent learning

Centroid of a object detected using MOG2 algorithm of OpenCV not giving uniform results

HOG for “detecting object” opencvvehicle tracking with haar-like features and camshiftNon-closed contours in matplotlib?Find Area of a OpenCV ContourOpenCV - Applying BGS + Blob detection to both counting pedestrians and vehicles in a video simultaneously ( Code provided )OpenCV contour minimum dimension location in pythonFind edges (graph edges) in a binary image using OpenCVDetection of multiple objects (using OpenCV)To detect a moving ball in monochromatic images using opencvPython - openCv to detect circles giving strange results

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

I am trying to implement a simple vehicle tracking algorithm without using any complex classifiers.
I am using simple MOG2 background subtraction. Then I am using cv2.findContours() and getting bounding points of the contour(x,y,w,h)
Then I am trying to find out centroid by using Moments.

But as I am printing out the centroid, I can see that it is not moving at a uniform rate through subsequent frames. Even the extreme points of the contours are also not moving at a uniform rate.

What I am trying to implement: Calculate centroid, Check if the centroid has crossed a line and extract the picture of the vehicle.

Problem: The centroid/ extreme points of the contour are not moving at uniform rate. Hence my logic is not triggered for some objects which leads to loss of accuracy.

Please help!!

python opencv3.0 object-detection

share|improve this question

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

add a comment | 

0

I am trying to implement a simple vehicle tracking algorithm without using any complex classifiers.
I am using simple MOG2 background subtraction. Then I am using cv2.findContours() and getting bounding points of the contour(x,y,w,h)
Then I am trying to find out centroid by using Moments.

But as I am printing out the centroid, I can see that it is not moving at a uniform rate through subsequent frames. Even the extreme points of the contours are also not moving at a uniform rate.

What I am trying to implement: Calculate centroid, Check if the centroid has crossed a line and extract the picture of the vehicle.

Problem: The centroid/ extreme points of the contour are not moving at uniform rate. Hence my logic is not triggered for some objects which leads to loss of accuracy.

Please help!!

python opencv3.0 object-detection

share|improve this question

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

add a comment | 

I am trying to implement a simple vehicle tracking algorithm without using any complex classifiers.
I am using simple MOG2 background subtraction. Then I am using cv2.findContours() and getting bounding points of the contour(x,y,w,h)
Then I am trying to find out centroid by using Moments.

But as I am printing out the centroid, I can see that it is not moving at a uniform rate through subsequent frames. Even the extreme points of the contours are also not moving at a uniform rate.

What I am trying to implement: Calculate centroid, Check if the centroid has crossed a line and extract the picture of the vehicle.

Problem: The centroid/ extreme points of the contour are not moving at uniform rate. Hence my logic is not triggered for some objects which leads to loss of accuracy.

Please help!!

python opencv3.0 object-detection

share|improve this question

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

share|improve this question

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

share|improve this question

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11

asked Mar 25 at 8:34

KAUSTAV BAGCHIKAUSTAV BAGCHI

11