Vegetation segmentation for feature matching

In this paper, we present a new application of image segmentation algorithms and an adaptation of the image segmentation method of Tavakoli Targhi et al. to the problem of vegetation segmentation. While the traditional goal of image segmentation is to provide a figure/ground segmentation for object recognition or semantic segmentation to assist humans, we propose to use image segmentation in order to boost performance of local invariant feature detectors. In particular, we analyze the performance of MSER feature detector and we show that we can prune all features detected on vegetation to gain a 67% speed-up while accuracy of image matching does not decrease. The image segmentation method of Tavakoli Targhi et al. that we adapt to the problem of vegetation segmentation is based on singular value decomposition (SVD) of local image patches, where the sum of the smaller singular values describes the high frequency part of the patch. The results of the automatic segmentation of vegetation show that the average overlap between manual and automatic vegetation segmentation is 33% and that the automatic procedure for vegetation segmentation can prune 25% of MSER features, resulting in 33% faster image retrieval.

Perko research vegetation image retrieval.jpg

Figure: An example of improved image retrieval results when vegetation is segmented out and 1-NN matching strategy is used. The first column shows query images with corresponding masks while in the second to sixth column, the five best matching images are shown for the original query image (first row), for a query image with vegetation segmented out manually (second row), and automatically (third row). With vegetation present, all five retrieved images are incorrect. With vegetation excluded, the accuracy improves substantially.


Publications for vegetation segmentation