이경무

Bio: 이경무 is an academic researcher. The author has contributed to research in topics: Segmentation. The author has an hindex of 1, co-authored 1 publications receiving 21 citations.

Object discovery in 3D scenes via shape analysis

Abstract: We present a method for discovering object models from 3D meshes of indoor environments. Our algorithm first decomposes the scene into a set of candidate mesh segments and then ranks each segment according to its “objectness” - a quality that distinguishes objects from clutter. To do so, we propose five intrinsic shape measures: compactness, symmetry, smoothness, and local and global convexity. We additionally propose a recurrence measure, codifying the intuition that frequently occurring geometries are more likely to correspond to complete objects. We evaluate our method in both supervised and unsupervised regimes on a dataset of 58 indoor scenes collected using an Open Source implementation of Kinect Fusion [1]. We show that our approach can reliably and efficiently distinguish objects from clutter, with Average Precision score of .92. We make our dataset available to the public.

Annotated Image Datasets of Rosette Plants

Abstract: While image-based approaches to plant phenotyping are gaining momentum, benchmark data focusing on typical imaging situations and tasks in plant phenotyping are still lacking, making it dicult to compare existing methodologies. This report describes a benchmark dataset of raw and annotated images of plants. We describe the plant material, environmental conditions, and imaging setup and procedures, as well as the datasets where this image selection stems from. We also describe the annotation process, since all of these images have been manually segmented by experts, such that each leaf has its own label. Color images in the dataset show top-down views on young rosette plants. Two datasets show dierent genotypes of Arabidopsis while another dataset shows tobacco (Nicoticana tobacum) under dierent treatments. A version of the dataset, described also in this report, is in the public domain at http://www.plant-phenotyping.org/CVPPP2014-dataset and can be used for the purpose of plant/leaf segmentation from background, with accompanying evaluation scripts. This version was used in the Leaf Segmentation Challenge (LSC) of the Computer Vision Problems in Plant Phenotyping (CVPPP 2014) workshop organized in conjunction with the

Discovering object instances from scenes of Daily Living

Abstract: We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered scenes contain multiple objects. Each image provides only a partial, possibly very different view of each object. An object instance discovery program must be able to link pieces of visual information from multiple images and extract the consistent patterns.

Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction

Abstract: Structure from motion (SfM) is a common technique to recover 3D geometry and camera poses from sets of images of a common scene. In many urban environments, however, there are symmetric, repetitive, or duplicate structures that pose challenges for SfM pipelines. The result of these ambiguous structures is incorrectly placed cameras and points within the reconstruction. In this paper, we present a post-processing method that can not only detect these errors, but successfully resolve them. Our novel approach proposes the strong and informative measure of conflicting observations, and we demonstrate that it is robust to a large variety of scenes.