FeatureBasedTracking - Historique des versions

NicolasSaunier le 20 juillet 2011 à 04:50

2011-07-20T04:50:53Z

← Version précédente		Version du 20 juillet 2011 à 04:50
Ligne 1 :		Ligne 1 :
	The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University.		The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique, McGill University and Carleton University.

	==General Objectives==		==General Objectives==
Ligne 37 :		Ligne 37 :
	==Resources==		==Resources==
	* Open source computer vision projects		* Open source computer vision projects
	** http://code.google.com/p/opencv-feature-tracker/		** OpenCV http://opencv.willowgarage.com/wiki/
			** http://code.google.com/p/opencv-feature-tracker/ (Warning: many bugs, not a good basis to build upon)
	** https://bitbucket.org/Nicolas/trafficintelligence		** https://bitbucket.org/Nicolas/trafficintelligence
	** https://bitbucket.org/trajectories/trajectorymanagementandanalysis		** https://bitbucket.org/trajectories/trajectorymanagementandanalysis
			* Version Control http://mercurial.selenic.com/
	* C++		* C++
	** http://en.cppreference.com/w/cpp		** http://en.cppreference.com/w/cpp
	** http://www.parashift.com/c++-faq-lite/		** http://www.parashift.com/c++-faq-lite/

NicolasSaunier le 28 juin 2011 à 21:12

2011-06-28T21:12:47Z

NicolasSaunier : /* Resources */

2011-06-24T23:05:49Z

Resources

← Version précédente		Version du 24 juin 2011 à 23:05
Ligne 34 :		Ligne 34 :

	==Resources==		==Resources==
			* Open source computer vision projects
	** http://code.google.com/p/opencv-feature-tracker/		** http://code.google.com/p/opencv-feature-tracker/
	** https://bitbucket.org/Nicolas/trafficintelligence		** https://bitbucket.org/Nicolas/trafficintelligence
	** https://bitbucket.org/trajectories/trajectorymanagementandanalysis		** https://bitbucket.org/trajectories/trajectorymanagementandanalysis
			* C++
			** http://en.cppreference.com/w/cpp
			** http://www.parashift.com/c++-faq-lite/

NicolasSaunier le 10 juin 2011 à 03:46

2011-06-10T03:46:49Z

← Version précédente		Version du 10 juin 2011 à 03:46
Ligne 21 :		Ligne 21 :
	** in particular, the steps of feature tracking and grouping can be performed separately or together		** in particular, the steps of feature tracking and grouping can be performed separately or together
	* use of a homography to transform coordinates from image to world space		* use of a homography to transform coordinates from image to world space
	* simple memory management using smart pointers and as much as possible const references for arguments ~~of functions~~		* simple memory management using smart pointers and as much as possible const references for function arguments
	** using for example the Boost library http://www.boost.org/doc/libs/1_46_1/libs/smart_ptr/smart_ptr.htm		** using for example the Boost library http://www.boost.org/doc/libs/1_46_1/libs/smart_ptr/smart_ptr.htm
	* clean interface using the command line and a configuration file		* clean interface using the command line and a configuration file

NicolasSaunier le 10 juin 2011 à 03:46

2011-06-10T03:46:34Z

← Version précédente		Version du 10 juin 2011 à 03:46
Ligne 12 :		Ligne 12 :
	==Summer 2011 project by Ananda Narayanan==		==Summer 2011 project by Ananda Narayanan==

	Expected list of features for the program:		Expected list of features for the program (following http://n.saunier.free.fr/saunier/stock/saunier06feature-based.pdf)

	* feature-based tracking using the KLT implementation of OpenCV, that can be easily extended to use other types of features (eg the fast features used in the opencv sample video_homography)		* feature-based tracking using the KLT implementation of OpenCV, that can be easily extended to use other types of features (eg the fast features used in the opencv sample video_homography)
Ligne 21 :		Ligne 21 :
	** in particular, the steps of feature tracking and grouping can be performed separately or together		** in particular, the steps of feature tracking and grouping can be performed separately or together
	* use of a homography to transform coordinates from image to world space		* use of a homography to transform coordinates from image to world space
			* simple memory management using smart pointers and as much as possible const references for arguments of functions
			** using for example the Boost library http://www.boost.org/doc/libs/1_46_1/libs/smart_ptr/smart_ptr.htm
	* clean interface using the command line and a configuration file		* clean interface using the command line and a configuration file
	* saving all trajectory information for features and moving objects using the project https://bitbucket.org/trajectories/trajectorymanagementandanalysis (if possible, re-use data structure from the same project to avoid time-consuming type conversions)		* saving all trajectory information for features and moving objects using the project https://bitbucket.org/trajectories/trajectorymanagementandanalysis (if possible, re-use data structure from the same project to avoid time-consuming type conversions)

NicolasSaunier le 10 juin 2011 à 03:37

2011-06-10T03:37:22Z

@@ Ligne 1 : / Ligne 1 : @@
 The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University.
-* Objectives
+==General Objectives==
 # Feature-based tracking, using any "standard" feature tracker, eg KLT
 #* look at fast features and the opencv sample video_homography
@@ Ligne 9 : / Ligne 9 : @@
 # Semi-automated tracking
 # Other vehicle/road user tracking methods, eg using background subtraction, tracking by detection (HoG detection)...
 * Resources
 ** http://code.google.com/p/opencv-feature-tracker/
 ** https://bitbucket.org/Nicolas/trafficintelligence
 ** https://bitbucket.org/trajectories/trajectorymanagementandanalysis

NicolasSaunier le 9 juin 2011 à 23:03

2011-06-09T23:03:46Z

← Version précédente		Version du 9 juin 2011 à 23:03
Ligne 3 :		Ligne 3 :
	* Objectives		* Objectives
	# Feature-based tracking, using any "standard" feature tracker, eg KLT		# Feature-based tracking, using any "standard" feature tracker, eg KLT
	# Compensating small camera vibration (could work for small re-calibrations): an idea is to use features on background objects		#* look at fast features and the opencv sample video_homography
			# Compensating small camera vibration (could work for small re-calibrations)
			#* an idea is to use features on background objects
	# Generic features		# Generic features
	# Semi-automated tracking		# Semi-automated tracking

NicolasSaunier le 9 juin 2011 à 20:52

2011-06-09T20:52:14Z

← Version précédente		Version du 9 juin 2011 à 20:52
Ligne 2 :		Ligne 2 :

	* Objectives		* Objectives
	** Feature-based tracking, using any "standard" feature tracker, eg KLT		# Feature-based tracking, using any "standard" feature tracker, eg KLT
	** Generic features		# Compensating small camera vibration (could work for small re-calibrations): an idea is to use features on background objects
	** Semi-automated tracking		# Generic features
	** Other vehicle/road user tracking methods, eg using background subtraction, tracking by detection (HoG detection)...		# Semi-automated tracking
			# Other vehicle/road user tracking methods, eg using background subtraction, tracking by detection (HoG detection)...
	* Resources		* Resources
	** http://code.google.com/p/opencv-feature-tracker/		** http://code.google.com/p/opencv-feature-tracker/
	** https://bitbucket.org/Nicolas/trafficintelligence		** https://bitbucket.org/Nicolas/trafficintelligence
	** https://bitbucket.org/trajectories/trajectorymanagementandanalysis		** https://bitbucket.org/trajectories/trajectorymanagementandanalysis

NicolasSaunier : Page créée avec « The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University. * Objectives … »

2011-05-19T22:36:31Z

Page créée avec « The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University. * Objectives … »

Nouvelle page

The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University.

* Objectives
** Feature-based tracking, using any "standard" feature tracker, eg KLT
** Generic features
** Semi-automated tracking
** Other vehicle/road user tracking methods, eg using background subtraction, tracking by detection (HoG detection)...
* Resources
** http://code.google.com/p/opencv-feature-tracker/
** https://bitbucket.org/Nicolas/trafficintelligence
** https://bitbucket.org/trajectories/trajectorymanagementandanalysis

← Version précédente		Version du 28 juin 2011 à 21:12
Ligne 15 :		Ligne 15 :

	* feature-based tracking using the KLT implementation of OpenCV, that can be easily extended to use other types of features (eg the fast features used in the opencv sample video_homography)		* feature-based tracking using the KLT implementation of OpenCV, that can be easily extended to use other types of features (eg the fast features used in the opencv sample video_homography)
			** check that new features are generated at more than the specified minimum feature distance when others are lost
	** it should include at least the following constraints on motion regularity to avoid errors and improve results		** it should include at least the following constraints on motion regularity to avoid errors and improve results
	*** features have a minimum length, minimum displacement over the last n frames, the angle between two successive displacement vectors and the ratio of their norm may not be too large (if not, the feature track is disrupted: if the feature is too short, it is discarded)		*** features have a minimum length, minimum displacement over the last n frames, the angle between two successive displacement vectors and the ratio of their norm may not be too large (if not, the feature track is disrupted: if the feature is too short, it is discarded)
Ligne 20 :		Ligne 21 :
	* clean and modular design that can be easily extended: speed should be reasonable		* clean and modular design that can be easily extended: speed should be reasonable
	** in particular, the steps of feature tracking and grouping can be performed separately or together		** in particular, the steps of feature tracking and grouping can be performed separately or together
	* use of a homography to transform coordinates from image to world space		* use of a homography to transform coordinates from image to world space, accomodate if unavailable (test if it exists or use a configuration parameter)
	* simple memory management using smart pointers and as much as possible const references for function arguments		* simple memory management using smart pointers and as much as possible const references for function arguments
	** using for example the Boost library http://www.boost.org/doc/libs/1_46_1/libs/smart_ptr/smart_ptr.htm		** using for example the Boost library http://www.boost.org/doc/libs/1_46_1/libs/smart_ptr/smart_ptr.htm
	* clean interface using the command line and a configuration file		* clean interface using the command line and a configuration file
			** make '''all''' tracking parameters available
	* saving all trajectory information for features and moving objects using the project https://bitbucket.org/trajectories/trajectorymanagementandanalysis (if possible, re-use data structure from the same project to avoid time-consuming type conversions)		* saving all trajectory information for features and moving objects using the project https://bitbucket.org/trajectories/trajectorymanagementandanalysis (if possible, re-use data structure from the same project to avoid time-consuming type conversions)

FeatureBasedTracking - Historique des versions

NicolasSaunier le 20 juillet 2011 à 04:50

NicolasSaunier le 28 juin 2011 à 21:12

NicolasSaunier : /* Resources */

NicolasSaunier le 10 juin 2011 à 03:46

NicolasSaunier le 10 juin 2011 à 03:46

NicolasSaunier le 10 juin 2011 à 03:37

NicolasSaunier le 9 juin 2011 à 23:03

NicolasSaunier le 9 juin 2011 à 20:52

NicolasSaunier : Page créée avec « The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University. * Objectives … »

NicolasSaunier : /* Resources */

NicolasSaunier : Page créée avec « The goal of this page is to record the objectives of the development of a vision-based road user tracking tool at Ecole Polytechnique and Carleton University. * Objectives … »