ObjectTracking - Revision history

imported>Projects221: /* Algorithm Accuracy */

2015-12-12T01:59:14Z

Algorithm Accuracy

← Older revision		Revision as of 01:59, 12 December 2015
Line 84:		Line 84:
	=== Algorithm Accuracy ===		=== Algorithm Accuracy ===

	Overall, accuracy was satisfactory in testing both 60 fps and 30 fps (tracking at every other frame). There was failure in 9 videos (total = 104 videos) usually due to facial hair near marker or head hair that slips onto face, and in these cases, color correction using commercial video editing software was applied to highlight marker of interest. This change resulting in accurate tracking.		Overall, accuracy was satisfactory in testing both 60 fps and 30 fps (tracking at every other frame). There was failure in 9 videos (total = 104 videos) usually due to facial hair near marker or head hair that slips onto face, and in these cases, color correction using commercial video editing software was applied to highlight marker of interest. This change resulting in accurate tracking. (See Fig. 5 for examples.)
	[[File:Tracking_photos.jpg\|center\|800px\|thumb\|Fig. 5 - Bounding box at 1 and 1201 frames for two participants. Green lines indicated centroid trajectory. Color adjustments improved poor tracking.]]		[[File:Tracking_photos.jpg\|center\|800px\|thumb\|Fig. 5 - Bounding box at 1 and 1201 frames for two participants. Green lines indicated centroid trajectory. Color adjustments improved poor tracking.]]

imported>Projects221: /* RBFNN Speed Evaluation */

2015-12-12T01:58:57Z

RBFNN Speed Evaluation

← Older revision		Revision as of 01:58, 12 December 2015
Line 80:		Line 80:
	Mean length of videos tested = 1642 frames (SD = 182 frames), therefore avg length to process one marker for one movie = 30.05 min at 60 fps (using MacBook Air)		Mean length of videos tested = 1642 frames (SD = 182 frames), therefore avg length to process one marker for one movie = 30.05 min at 60 fps (using MacBook Air)

	Due to the sheer runtime length of this section of the algorithm, I do not have a plot evaluating the runtime. However, it became clear to me through this process that this section of the algorithm would be too slow for the sheer amount of data that I have. So, I propose the following ~~change~~ to the algorithm: the object is found in every 10th frame and a potential trajectory of the marker is interpolated. Then, at a second pass, the object trajectory is found at the middle frames between those of the first pass (5th, 15th, etc.). If the marker location is within an acceptable margin of error, then no change is made to the interpolation. If the found location is outside of an acceptable margin of error, then the interpolation is refit bother immediately prior to and after that frame, and the algorithm iteratively checks the middle frames again (2nd/3rd, 7th/8th). This would significantly reduce runtime, and could even be first tested at a higher frame jump (i.e. the first pass tests every 20 frames, etc.) The figure to the right shows this alternative algorithm. Note that, also, on further reflection, I found that the background extension method of their algorithm was not necessary for these purposes, so it is removed in the accompanying figure.		Due to the sheer runtime length of this section of the algorithm, I do not have a plot evaluating the runtime. However, it became clear to me through this process that this section of the algorithm would be too slow for the sheer amount of data that I have. So, I propose the following changes to the algorithm (Fig. 4): the object is found in every 10th frame and a potential trajectory of the marker is interpolated. Then, at a second pass, the object trajectory is found at the middle frames between those of the first pass (5th, 15th, etc.). If the marker location is within an acceptable margin of error, then no change is made to the interpolation. If the found location is outside of an acceptable margin of error, then the interpolation is refit bother immediately prior to and after that frame, and the algorithm iteratively checks the middle frames again (2nd/3rd, 7th/8th). This would significantly reduce runtime, and could even be first tested at a higher frame jump (i.e. the first pass tests every 20 frames, etc.) The figure to the right shows this alternative algorithm. Note that, also, on further reflection, I found that the background extension method of their algorithm was not necessary for these purposes, so it is removed in the accompanying figure.

	=== Algorithm Accuracy ===		=== Algorithm Accuracy ===

imported>Projects221: /* K-means Evaluation */

2015-12-12T01:58:34Z

K-means Evaluation

← Older revision		Revision as of 01:58, 12 December 2015
Line 72:		Line 72:
	=== K-means Evaluation ===		=== K-means Evaluation ===
	[[File:Kmeans_results.jpg\|300px\|left\|thumb\|Fig. 3 - Size of bounding box vs. runtime of K-means portion of algorithm.]]		[[File:Kmeans_results.jpg\|300px\|left\|thumb\|Fig. 3 - Size of bounding box vs. runtime of K-means portion of algorithm.]]
	It was proposed in the original paper that the K-means segmentation of the object color from its background would not take a lot of time. ~~Here I show~~ a plot of the runtime of this segment of the algorithm as a function of one side of the bounding box square in which it is segmenting the colors into two clusters. As expected, runtime seemed to be a relatively linear function of bounding box size.		It was proposed in the original paper that the K-means segmentation of the object color from its background would not take a lot of time. Fig. 3 shows a plot of the runtime of this segment of the algorithm as a function of one side of the bounding box square in which it is segmenting the colors into two clusters. As expected, runtime seemed to be a relatively linear function of bounding box size.

	=== RBFNN Speed Evaluation ===		=== RBFNN Speed Evaluation ===

imported>Projects221: /* Gesture-Tracking Algorithm */

2015-12-12T01:58:20Z

Gesture-Tracking Algorithm

← Older revision		Revision as of 01:58, 12 December 2015
Line 52:		Line 52:
	[[File:Algorithm_flow.jpg\|upright\|200px\|right\|thumb\|Fig. 2 - Object tracking algorithm (adopted from Deshmukh, P. K. & Gholap, Y., 2012)]]		[[File:Algorithm_flow.jpg\|upright\|200px\|right\|thumb\|Fig. 2 - Object tracking algorithm (adopted from Deshmukh, P. K. & Gholap, Y., 2012)]]

	I chose to use as a starting point, the algorithm described in Deshmukh, P. K. & Gholap, Y. (2012). Efficient object tracking using K-means and radial basis function [5]. I include here the abstract from this paper, as well as a flowchart of the algorithm process (~~that I made, but copied in style from their paper~~), as it most succinctly describes their algorithm.		I chose to use as a starting point, the algorithm described in Deshmukh, P. K. & Gholap, Y. (2012). Efficient object tracking using K-means and radial basis function [5]. I include here the abstract from this paper, as well as a flowchart of the algorithm process (Fig. 2), as it most succinctly describes their algorithm.

	''"In the present article, an efficient method for object tracking is proposed using Radial Basis Function Neural Networks and K-means. This proposed method starts with K-means algorithm to do the segmentation of the object and background in the frame. The Pixel-based color features are used for identifying and tracking the object. The remaining background is also considered. These classified features of object and extended background are used to train the Radial Basis Function Neural Network. The trained network will track the object in next subsequent frames. This method is tested for the video sequences and is suitable for real-time tracking due to its low complexity. The objective of this experiment is to minimize the computational cost of the tracking method with required accuracy."''		''"In the present article, an efficient method for object tracking is proposed using Radial Basis Function Neural Networks and K-means. This proposed method starts with K-means algorithm to do the segmentation of the object and background in the frame. The Pixel-based color features are used for identifying and tracking the object. The remaining background is also considered. These classified features of object and extended background are used to train the Radial Basis Function Neural Network. The trained network will track the object in next subsequent frames. This method is tested for the video sequences and is suitable for real-time tracking due to its low complexity. The objective of this experiment is to minimize the computational cost of the tracking method with required accuracy."''

imported>Projects221: /* Recording Setup */

2015-12-12T01:57:36Z

Recording Setup

← Older revision		Revision as of 01:57, 12 December 2015
Line 41:		Line 41:


	Recording took place in a quiet, secure room. Two Canon Vixia HF R600 were used for video recording: one to the front, at around a distance of 8 ft 10 in, one to the side at 6 ft 3 in, and was filmed at 60 fps. This was the highest frame rate available for this camera. This camera was selected due to discussions with the filmographer for our department that it was a quality under $300 camcorder. Audio was recorded using a Zoom H6, at 96 kHz sampling rate and 24-bit depth. Cellists were lit using a Pro LED 1000 12x12 LED Panel Light. Cellists wore 1-in squares of retroreflective tape, placed at the center of the forehead, the nose, the top of the hands, the center point on the clavicle (below the neck), both shoulders, the lower rib, and the right cheek. Participants were asked to wear dark clothing that was not too loose-fitting.		Recording took place in a quiet, secure room (Fig. 1). Two Canon Vixia HF R600 were used for video recording: one to the front, at around a distance of 8 ft 10 in, one to the side at 6 ft 3 in, and was filmed at 60 fps. This was the highest frame rate available for this camera. This camera was selected due to discussions with the filmographer for our department that it was a quality under $300 camcorder. Audio was recorded using a Zoom H6, at 96 kHz sampling rate and 24-bit depth. Cellists were lit using a Pro LED 1000 12x12 LED Panel Light. Cellists wore 1-in squares of retroreflective tape, placed at the center of the forehead, the nose, the top of the hands, the center point on the clavicle (below the neck), both shoulders, the lower rib, and the right cheek. Participants were asked to wear dark clothing that was not too loose-fitting.

	====Procedure====		====Procedure====

imported>Projects221: /* Procedure */

2015-12-12T01:56:56Z

Procedure

← Older revision		Revision as of 01:56, 12 December 2015
Line 45:		Line 45:
	====Procedure====		====Procedure====
	Performers were asked to memorize all excerpts prior to the filming session. Upon arrival, they were given a few minutes to warm up, and markers were attached. They were then asked to play the two versions of the ‘unfamiliar’ excerpt, in two ways. In the first way, they will be asked to “play as if all of the notes are part of one line”. Performers played each version of the excerpt up to 5 times, or as many as needed to get two acceptable takes. Once two takes for each excerpt/version were obtained with markers on, the markers were removed and one take was obtained of each excerpt/version.		Performers were asked to memorize all excerpts prior to the filming session. Upon arrival, they were given a few minutes to warm up, and markers were attached. They were then asked to play the two versions of the ‘unfamiliar’ excerpt, in two ways. In the first way, they will be asked to “play as if all of the notes are part of one line”. Performers played each version of the excerpt up to 5 times, or as many as needed to get two acceptable takes. Once two takes for each excerpt/version were obtained with markers on, the markers were removed and one take was obtained of each excerpt/version.
	~~<br>~~
	~~<br>~~
	<br>		<br>
	<br>		<br>

imported>Projects221: /* Participants */

2015-12-12T01:56:47Z

Participants

← Older revision		Revision as of 01:56, 12 December 2015
Line 31:		Line 31:

	====Participants====		====Participants====
			[[File:Studio.jpeg\|right\|350px\|thumb\|Fig. 1 - Recording studio setup. Side camera shown in left side of picture]]
	13 (7 female) cello performance majors. Recruitment via email over departmental listservs. The email notified them that they would be filmed.		13 (7 female) cello performance majors. Recruitment via email over departmental listservs. The email notified them that they would be filmed.

imported>Projects221: /* Stimuli */

2015-12-12T01:56:39Z

Stimuli

← Older revision		Revision as of 01:56, 12 December 2015
Line 34:		Line 34:

	====Stimuli====		====Stimuli====
	~~[[File:Studio.jpeg\|right\|350px\|thumb\|Fig. 1 - Recording studio setup. Side camera shown in left side of picture]]~~
	The opening 8 bars of the 3rd Ricercar by Domenico Gabrielli. The cellists were instructed to prepare two versions of the unfamiliar excerpt, one of which had long marked phrases, and the other of which had shorter marked melodic groupings. Tempo, bowings, and fingerings were marked and required for all excerpts.		The opening 8 bars of the 3rd Ricercar by Domenico Gabrielli. The cellists were instructed to prepare two versions of the unfamiliar excerpt, one of which had long marked phrases, and the other of which had shorter marked melodic groupings. Tempo, bowings, and fingerings were marked and required for all excerpts.

imported>Projects221: /* Stimuli */

2015-12-12T01:56:30Z

Stimuli

← Older revision		Revision as of 01:56, 12 December 2015
Line 34:		Line 34:

	====Stimuli====		====Stimuli====
			[[File:Studio.jpeg\|right\|350px\|thumb\|Fig. 1 - Recording studio setup. Side camera shown in left side of picture]]
	The opening 8 bars of the 3rd Ricercar by Domenico Gabrielli. The cellists were instructed to prepare two versions of the unfamiliar excerpt, one of which had long marked phrases, and the other of which had shorter marked melodic groupings. Tempo, bowings, and fingerings were marked and required for all excerpts.		The opening 8 bars of the 3rd Ricercar by Domenico Gabrielli. The cellists were instructed to prepare two versions of the unfamiliar excerpt, one of which had long marked phrases, and the other of which had shorter marked melodic groupings. Tempo, bowings, and fingerings were marked and required for all excerpts.

imported>Projects221: /* Recording Setup */

2015-12-12T01:56:17Z

Recording Setup

← Older revision		Revision as of 01:56, 12 December 2015
Line 38:		Line 38:
	====Recording Setup====		====Recording Setup====

	~~[[File:Studio.jpeg\|right\|350px\|thumb\|Fig. 1 - Recording studio setup. Side camera shown in left side of picture]]~~
	Recording took place in a quiet, secure room. Two Canon Vixia HF R600 were used for video recording: one to the front, at around a distance of 8 ft 10 in, one to the side at 6 ft 3 in, and was filmed at 60 fps. This was the highest frame rate available for this camera. This camera was selected due to discussions with the filmographer for our department that it was a quality under $300 camcorder. Audio was recorded using a Zoom H6, at 96 kHz sampling rate and 24-bit depth. Cellists were lit using a Pro LED 1000 12x12 LED Panel Light. Cellists wore 1-in squares of retroreflective tape, placed at the center of the forehead, the nose, the top of the hands, the center point on the clavicle (below the neck), both shoulders, the lower rib, and the right cheek. Participants were asked to wear dark clothing that was not too loose-fitting.		Recording took place in a quiet, secure room. Two Canon Vixia HF R600 were used for video recording: one to the front, at around a distance of 8 ft 10 in, one to the side at 6 ft 3 in, and was filmed at 60 fps. This was the highest frame rate available for this camera. This camera was selected due to discussions with the filmographer for our department that it was a quality under $300 camcorder. Audio was recorded using a Zoom H6, at 96 kHz sampling rate and 24-bit depth. Cellists were lit using a Pro LED 1000 12x12 LED Panel Light. Cellists wore 1-in squares of retroreflective tape, placed at the center of the forehead, the nose, the top of the hands, the center point on the clavicle (below the neck), both shoulders, the lower rib, and the right cheek. Participants were asked to wear dark clothing that was not too loose-fitting.