TY - GEN
T1 - Dense segmentation of textured fruits in video sequences
AU - Qureshi, Waqar S.
AU - Satoh, Shin'ichi
AU - Dailey, Matthew N.
AU - Ekpanyapong, Mongkol
PY - 2014
Y1 - 2014
N2 - Autonomous monitoring of fruit crops based on mobile camera sensors requires methods to segment fruit regions from the background in images. Previous methods based on color and shape cues have been successful in some cases, but the detection of textured green fruits among green plant material remains a challenging problem. A recently proposed method uses sparse keypoint detection, keypoint descriptor computation, and keypoint descriptor classification followed by morphological techniques to fill the gaps between positively classified keypoints. We propose a textured fruit segmentation method based on super-pixel oversegmentation, dense SIFT descriptors, and and bag-of-visual-word histogram classification within each super-pixel. An empirical evaluation of the proposed technique for textured fruit segmentation yields a 96:67% detection rate, a per-pixel accuracy of 97:657%, and a per frame false alarm rate of 0:645%, compared to a detection rate of 90:0%, accuracy of 84:94%, and false alarm rate of 0:887% for the baseline sparse keypoint-based method. We conclude that super-pixel oversegmentation, dense SIFT descriptors, and bag-of-visual-word histogram classification are effective for in-field segmentation of textured green fruits from the background.
AB - Autonomous monitoring of fruit crops based on mobile camera sensors requires methods to segment fruit regions from the background in images. Previous methods based on color and shape cues have been successful in some cases, but the detection of textured green fruits among green plant material remains a challenging problem. A recently proposed method uses sparse keypoint detection, keypoint descriptor computation, and keypoint descriptor classification followed by morphological techniques to fill the gaps between positively classified keypoints. We propose a textured fruit segmentation method based on super-pixel oversegmentation, dense SIFT descriptors, and and bag-of-visual-word histogram classification within each super-pixel. An empirical evaluation of the proposed technique for textured fruit segmentation yields a 96:67% detection rate, a per-pixel accuracy of 97:657%, and a per frame false alarm rate of 0:645%, compared to a detection rate of 90:0%, accuracy of 84:94%, and false alarm rate of 0:887% for the baseline sparse keypoint-based method. We conclude that super-pixel oversegmentation, dense SIFT descriptors, and bag-of-visual-word histogram classification are effective for in-field segmentation of textured green fruits from the background.
KW - Dense Classification
KW - Super-pixels
KW - Visual Word Histograms
UR - http://www.scopus.com/inward/record.url?scp=84906910860&partnerID=8YFLogxK
U2 - 10.5220/0004689304410447
DO - 10.5220/0004689304410447
M3 - Conference contribution
AN - SCOPUS:84906910860
SN - 9789897580048
T3 - VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications
SP - 441
EP - 447
BT - VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications
PB - SciTePress
T2 - 9th International Conference on Computer Vision Theory and Applications, VISAPP 2014
Y2 - 5 January 2014 through 8 January 2014
ER -