schestowitz.com » Android

Car Navigation for Android: Multi-scale Classifier

Roy Schestowitz — Wed, 20 Jun 2012 16:35:45 +0000

ed and green hues represent the matching from dual-scale classifiers of the rear of cars. Some more bugs were removed in this latest iteration of the implementation.

Car Navigation: Indicators of Approach of Obstacles

Roy Schestowitz — Tue, 19 Jun 2012 06:36:50 +0000

he circle at the left shows whether the car is getting closer (white) or going away (red). The size of the circle is indicative of length.

Car Rear Classifier With 39 Negative Samples, 39 Positive Samples, Sample Size 40×40

Roy Schestowitz — Mon, 18 Jun 2012 07:39:26 +0000

esting shown on various cars excluded from the training set. I will soon release a PDF document to explain what my program is achieving and how.

Extensive Static Test of Car Tracker (for Navigation/Collision) and Tracking With Increased Sample Size

Roy Schestowitz — Sun, 17 Jun 2012 08:16:09 +0000

ASED on further experiments, at the expense of performance in terms of framerate we can easily improve accuracy to the point of perfect tracking for particular cars. This is done by increasing the sample (window) size on which the tree is trained.

Using 20 positives and only 10 negatives for training.

20 positives and 20 negatives with a sample size of 40×40

Tiny Set for Training of a Local Binary Patterns (LBP) Classifier

Roy Schestowitz — Sat, 16 Jun 2012 10:22:14 +0000

ased on cascade training with just 10 negatives and 20 positives (various cars and distances, poses). The real FPS rate is 6+; in the demo it’s decreased by the grabbing/streaming of screenshots for video capturing.

Initial Test

Zoom Changes and Local Binary Patterns Classifier Applied to Red Car

Car Tracking Test (Static With Panning)

6 FPS for tracking (1-minute video)

This video shows tracking of a car based on training with just 10 negatives and 20 positives (without cars like the one in this demo). The real FPS rate is around 6; grabbing and saving a video such as this (in real time) entails a massive performance penalty, so this demo cannot show just how smooth the tracking really is. For a classifier trained on more examples the performance will be comparable. If some code cruft is removed and the rendering gets optimised, 8 FPS seems reachable (this device generally captures raw video at about 10 FPS).

Car Navigation Single Car Classifier

Roy Schestowitz — Tue, 12 Jun 2012 14:50:35 +0000

ith a training set of just a dozen positives from a single car I have let the experiment run. The purpose of this experiment is to test the alarm (collision) mechanism for short-range D alone.

Car Navigation Version 6.3 (Android)

Roy Schestowitz — Tue, 12 Jun 2012 08:14:10 +0000

Dashboard and tracking enriched somewhat, footage on Motorola Droid (captured by someone else). I’ve not gotten around to implementing better tracking yet.

AndroidScreencast: Screencasting in Android (Car Navigation)

Roy Schestowitz — Fri, 08 Jun 2012 23:28:59 +0000

sing androidscreencast is simple. As their site puts it, the steps to follow are as follows:

- Install the android sdk
- Connect your device through USB cable and ensure it’s detected with “adb devices”
- Make sure you have Java Runtime Environment 5 or later installed
- Click HERE. You can launch it by typing “javaws [jnlp file]” from a command line.

Here is an example video I took on a tablet:

Keywords: androidscreencast android linux tablet

Classification on Android Tablet – Parts 1-5

Roy Schestowitz — Fri, 08 Jun 2012 11:00:27 +0000

he videos show a first attempt to demonstrate the application. It is difficult to demonstrate without dumping a stream of frames directly from the tablet, thus obtaining a proper screencast. There are 5 parts, with splitting done due to a technical issue with the microphone [1, 2, 3, 4, 5] (10 minutes or so in total).

I’ll look for a better way to demonstrate it. Someone told me there is a screencasts app for Android.

Keywords: android opencv ics archos linux Mobile Phone Wireless electronics Cell mobiledevice haar classification tracking machinelearning eclipse computervision research dalvik java Robot

Cascade Classification in OpenCV – Parts 1-9

Roy Schestowitz — Thu, 07 Jun 2012 20:09:24 +0000

ascade classification is easy to work with in OpenCV, but it is not so well documented. This series of short videos explains how this is done on GNU/Linux-based systems (although it may be useful and applicable to other platforms too). The videos were not scripted or planned, so please excuse the occasional stuttering and mistakes.

Keywords: OpenCV android linux gnu ubuntu cmake eclipse computervision research haar tracking machinelearning