people_counter.avi

Marketing researches are area where required to analyze a lot of data. E.g. we want to understand how many people are visiting a bank. In order to count this value, we need to count each man or woman which are entering to or exiting from the bank. For resolving this task there are a lot of approaches: e.g. use special gate with laser or mechanical counter. Though there are people counting tasks where such approaches cannot work or too unuseful. E.g. barrier cannot be used where people flow is very high, and laser counters have limitations as well.

Opposite the approaches above, we found papers where top-mounted camera is used for resolving the people counting task.

 The fact is that most of organization have own IP or CCTV camera based security infrastructure. And also often there is a camera which is already top-mounted. Thus top-mounted camera counting approach is looked very perspective from reusing infrastructure point of view.

We researched a lot of approaches. There are a lot of ready methods for people counting with top-mounted camera. But such methods either are patented or don’t meet our expectation in quality or speed. Thus we developed own method (see demo video).

Method counts human each time they cross a predefined counting line (that is why it is often called as “line-crossing”). The assumption is that the line should be selected orthogonally to the main people flow.

Now we skip implementation details of the method. If shortly, our method is a real time 15 fps+, we tested it usual USB or IP cameras. We tested our method in indoor and outdoor use-case and the quality is 80-90% (dependent on environment condition).

Our method can be used in other applications, e.g. vehicle counting, you could look at the video how it works. Have a nice watching…

tools.avi

This object recognition algorithm is based on own pattern-matching algorithm. The algorithm is able to recognize pre-trained objects which are defined with special set of templates. Theoretically, the algorithm works with any “3D” objects which have good projection on 2D coordinates. However, natural 3D objects are covered by few templates for set of 2D projections. For limited number of object templates, the algorithm works in real-time on PC (Intel P4 3.0 GHz) .

The currency recognition demo application works under Windows XP, Intel P4 3GHz. Quality of recognition: 85%. The solution is cross-platform. The application was tested on Linux, ARM11 and on Linux/Windows, Intel Atom.

Interesting details can be found at: http://www.computer-vision-software.com/blog/2009/10/barcode

nike.avi

This is a demo video of the invariant orientation and scale fast object detection algorithm. The algorithm is a robust in cases when the object is deformed a little

The algorithm is a cross-platform solution.

Performance:

• on ARM11 530MHz, the algorithm gives 1 fps for 640×480 frame;
• on Intel P4 3Hz, the algorithm gives 12 fps and more for 640×480 frame.

Quality: 86%.

am-3.avi

This is a demo video of Rhonda Audience Measurement system (MyAudience product, www.MyAudience.com).

The system is able to recognize gender of a person. So, red rectangle is for a woman, dark blue rectangle is for a man. The quality of gender recognition algorithm is 90%.

The system works on Intel Atom: 10 fps and higher, and on Intel Pentium 4: 15 fps and higher. Besides, it is a cross-platform solution. It was tested on both Windows XP and Linux, and also it was tested on ARM Cortext-A8.

No accelerations (CUDA, fixed point, etc) are used! So, the solution has great potential for improvements.

barcodes-2.avi

Description

Here you can find a demo of the barcode detection and recognition routine. The current version is set up to detect a barcode labels mostly oriented horizontally and vertically. The routine processes each frame of the video stream and scans it trying to detect a barcode starting position, relying on the appearance specific of the barcode labels. As long as a potential starting position detected the routine applies the set of the image filters to increase the readability of the scanned window. Then recognition algorithm tries both to read and validate the barcode label starting from the detected point. You may see for yourself that such combination of detection and recognition algorithms works pretty well.
This demo works with UPC-A and EAN-13 barcode types.

Description

In this post we present a video demo of the gender classifier. This classifier is adapted for frontal- and near to frontal-oriented faces. It is capable to provide the real-time gender recognition with the invariance to complicated lighting conditions. The foundation of the implemented method is an AdaBoost powered extraction of the gender-descriptive features along with the further separation of male / female subsets for learning of the decision-making routine.
The classifier works in the conjunction with face-detector and tries to classify all found faces on the each frame. The achieved accuracy of correct classification is 90-92%, though on small faces (less then 32×32 pixels) returned by face-detector the accuracy of gender recognition could reduce to 80-88%.

overlapped_sonicfire.avi

Description

This video demo illustrates color-histogram-based object tracker in action. CV system tracks people as moving blobs (“clouds” of moving pixels) identifies them and distinct one from another in case of occlusions. When two (or more) blobs are intersected, system merges them in one combined object and marks it by IDs of all those source-objects that currently included in the combination. When one of objects separates from the combination CV system recognize which one is out and re-arrange ID appropriately. This approach works pretty well in case of characteristic histograms.

barcodes.avi

Description

Here is a demo of the jerry-built algorithm that finds barcode plates using Hough transform. Actually the video is mostly speaking for itself. Two points to comment:

• The frames of barcodes are a bit long, since with given approach there is distinct difficulty in precise identification of barcode beginning and ending, so borders where widened to not miss the useful part, which is not really critical since extracted region of interest is still quite small.
• The task was to detect only one barcode, so when there are several of them in the camera sight, CV system selects the best one (those with the most distinct lines). Since conditions of lighting and sharpness are always floating in video, system jumps from one barcode to another.