AuroraBlaze's profile - activity

Hi, thank you very much for your reply. I will take a look at it =).

Thank you for your reply. Could you please explain further on the "First you should detect, then you may classify the found region" <<< what can I do to achieve this? Any good tutorials or sample codes where I can refer to as a beginning for me to custom write an algorithm for the neural network to train it to detect a real time object? I would also like to know if after training the neural network, is it still possible for me to use that trained xml file for detection in android like the sample face detection given in opencv for android?

Hi I would like to know if the following is possible using Neural network in opencv, as I found the following link http://docs.opencv.org/modules/ml/doc....

So far, I had tried the traincascade.exe file to perform the object training. But now, I would like to try customizing my own algorithm in C++ using Visual Studio instead of using the existing traincascade algorithm to train the system to recognize an object/pattern.

I would like to know if this neural network can generate an xml file like the traincascade.exe file to be used for detection? Are there any format, etc that I need to follow, so that I can use the generated xml file for detection, by only replacing the xml file in opencv sample code?

Are there any good tutorial & sample codes where I can learn from?

Thank you.

Thank you for the reply. May I have some example on how to do it? Are there any tutorials or guides that I can refer to ?

Is it possible to connect to an external wifi camera and use it for detection instead of using its own android cameras for detection?

Hi

I dont seem to be able to train using opencv_traincascade whenever I created a vec file with a list of images that have the width as 80 and the height as 40.

And it keep showing me this error whenever I entered the following into the cmd.

opencv_traincascaded -data training -vec bananaSamples.vec -bg negative.txt -numStages 5 -minHitRate 0.999 -ma xFalseAlarmRate 0.5 -numPos 150 -numNeg 400 -w 80 -h 40 -mode -ALL

Error Message:

Training parameters are loaded from the parameter file in data folder! Please empty the data folder if you want to use your own set of parameters.

followed by this dialog.

but, I am able to train when I created a vec file with a list of images that have the size of 24x24. May I know why?

Thank you. This method worked for me =)

Hi,

I am facing the same issue as you too and, it took quite some time for me to fix it and I am not sure if it can help, but this is what I did. I know it is a bit late, but I hope it can help others who are facing the same issues as us too. Click onto the:

1) jni folder -> Android.mk 2) add in these codes: OPENCV_CAMERA_MODULES:= on OPENCV_INSTALL_MODULES:= on

3) Save and run.

This is what I have in my Android.mk file

LOCAL_PATH := $(call my-dir)

include $(CLEAR_VARS)

OPENCV_CAMERA_MODULES:= on OPENCV_INSTALL_MODULES:= on

include ../../sdk/native/jni/OpenCV.mk

LOCAL_SRC_FILES := DetectionBasedTracker_jni.cpp LOCAL_C_INCLUDES += $(LOCAL_PATH) LOCAL_LDLIBS += -llog -ldl

LOCAL_MODULE := detection_based_tracker

include $(BUILD_SHARED_LIBRARY)

Well this is what I did and the warning sign is then gone. I followed the guide from this link dev_with_OCV_on_Android at "Application Development with Static Initialization" number 3.

"After that the OpenCV libraries will be copied to your application libs folder during the JNI build.v Eclipse will automatically include all the libraries from the libs folder to the application package (APK)."