Automatic joint classification and segmentation of whole cell 3D images
Pattern Recognition
Model-based plane-segmentation using optical flow and dominant plane
MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
Superpixel analysis for object detection and tracking with application to UAV imagery
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Scene modelling and classification using learned spatial relations
COSIT'09 Proceedings of the 9th international conference on Spatial information theory
Turbopixel segmentation using Eigen-images
IEEE Transactions on Image Processing
Functional scene element recognition for video scene analysis
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Building semantic scene models from unconstrained video
Computer Vision and Image Understanding
Hi-index | 0.00 |
We present a novel method for joint segmentation and pixelwise classification of images, classifying each pixel in the image into one of a set of broad categories. We propose a 2-step approach for this problem, first estimating image structure through dense region segmentation, which provides initial spatial grouping (superpixels), then performing recognition by classifying each superpixel according to its features. Two types of region features are investigated: perceptual grouping features derived from neighborhood relations in the superpixel graph, and a histogram of pixel textons within the superpixel. Region classification is performed by boosting for perceptual features and histogram matching for texton features. We also introduce a novel extension of multi-class boosting: MAP estimation in the space of classifier ensemble outputs. Extensive results on aerial imagery are presented using a label vocabulary of trees, roads, vehicles, grass, shadows, and buildings. We evaluate the two methods across the categories, and compare them to the standard approach of classifying image blocks without prior segmentation. In our experiments perceptual features using multi-class boosting provide the best performance.