2019-12-18 06:13:37 -0600 | received badge | ● Popular Question (source) |
2014-12-03 18:59:29 -0600 | received badge | ● Student (source) |
2013-08-12 15:22:09 -0600 | received badge | ● Teacher (source) |
2013-07-30 05:50:02 -0600 | answered a question | OpenCV CascadeClassifier Segmentation Fault I do cannot recall the TBB version, all I know is I compile OpenCV with BUILD_TBB and WITH_TBB flag on, in console I see it download a tbb archive which I cannot recall the version. This is my C++ implementation: Detector class Initialization Detection, called in a while loop |
2013-07-30 01:55:28 -0600 | commented question | OpenCV CascadeClassifier Segmentation Fault Thanks Steve. I tried your suggestion, changing the all of the code to C++, and still the same problem happened. I get segmentation fault in cascade.detectMultiScale. The gdb and the backtrace is same. Interestingly, I recompile OpenCV without tbb, and the problem vanished... Unfortunately, this cause my application to run 2-3 x slower |
2013-07-29 01:16:48 -0600 | commented question | OpenCV CascadeClassifier Segmentation Fault Today I tried recompile OpenCV without TBB library, and application runs smoothly. I am thinking this is related to parallelization by TBB. I still looking forward to the solution because without TBB, the application runs 2-3x slower :( |
2013-07-27 08:27:16 -0600 | asked a question | OpenCV CascadeClassifier Segmentation Fault This is same question I asked in StackOverflow I am using OpenCV to detect faces in video. Currently I am using CascadeClassifier class, Haar classifier. When I run cascade.detectmultiscale, my program will run normally and suddenly crash with segmentation fault. I debug using gdb and found out thatProgram received signal SIGSEGV, Segmentation fault. Running backtrace, seems like gdb cannot finish the process I tried using the C version of cascade classifier ( the CvHaarClassifierCascade class ), same problem also happens when I run it and debug it. This is the code in case you want to see my implementation: Detector class Initialization Detection, called in a while loop The error always happened after I call Is this known bugs in OpenCV cascade classifier or I have a bad code? I am confused how to debug further on this problem because it ... (more) |
2013-04-24 23:15:44 -0600 | received badge | ● Editor (source) |
2013-04-21 21:59:35 -0600 | commented question | Are there any new algorithm about pedestrian detection,people counting? sorry for double posting, but if you want alternatives to HOG, Latent SVM is based on HOG, and seems to be better at detecting objects. But I cannot find how to create training data for Latent SVM. Anyone know? |
2013-04-21 21:58:18 -0600 | commented question | Are there any new algorithm about pedestrian detection,people counting? Hello flammxy, I do the same approach as you do in people counting. My first attempt, using MIT car and people dataset, result in lot of false positives (both test on separate people and car test images). Then I retrain the model using false positives from negative test set. This result in zero detection - please see my post here. After trying on different dataset and modifying parameters (hit threshold, scale, group thereshold), my conclusion is although HOG is so far the most popular people/object descriptor, the result is not perfect (100% hit rate, no false positives). We have to deal with miss and false positives (in my case, 50% hit rate, 50% false positives. |
2013-04-17 22:45:56 -0600 | received badge | ● Supporter (source) |
2013-04-17 22:45:26 -0600 | answered a question | How to training HOG and use my HOGDescriptor? You need to get the HOG features from all of your positive and negative sample images using HOGDescriptor:compute functions, then feed the result to SVM library such as SVMlight. This page will help you to compute the feature and get the resulting model from SVM Light. The model will be available in genfiles/descriptorVector |