Scene Cut: Class-Specific Object Detection and Segmentation in 3D Scenes

Knopp, Jan; Prasad, Mahesh; Gool, Luc Van

doi:10.1109/3dimpvt.2011.30

Cited by 22 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation: A popular way of formulating object recognition in 3D is to predict the semantic label for each region of a depth map or 3D mesh [37,38,11,10,[39][40][41][42][43][44]. Because of the bottom-up nature, these algorithms can only see a part of object but not the whole object.…”

Section: Related Work and Discussionmentioning

confidence: 99%

Sliding Shapes for 3D Object Detection in Depth Images

Song

Xiao

2014

Lecture Notes in Computer Science

332

284

View full text Add to dashboard Cite

Abstract. The depth information of RGB-D sensors has greatly simplified some common challenges in computer vision and enabled breakthroughs for several tasks. In this paper, we propose to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion, selfocclusion and sensor noises. We take a collection of 3D CAD models and render each CAD model from hundreds of viewpoints to obtain synthetic depth maps. For each depth rendering, we extract features from the 3D point cloud and train an Exemplar-SVM classifier. During testing and hard-negative mining, we slide a 3D detection window in 3D space. Experiment results show that our 3D detector significantly outperforms the state-of-the-art algorithms for both RGB and RGB-D images, and achieves about ×1.7 improvement on average precision compared to DPM and R-CNN. All source code and data are available online.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Sliding Shapes for 3D Object Detection in Depth Images

Song

Xiao

2014

Lecture Notes in Computer Science

332

284

View full text Add to dashboard Cite

show abstract

“…Another advantage of 3-D models is their potential for better object/background segmentation by using depth information. Recently, Knopp et al [15], [16], briefly investigated the application of their implicit shape 3-D models for detection in scenes reconstructed using structure from motion methods. The successful qualitative results obtained by Knopp et al provide encouragement for further research on object recognition based on 3-D scene representation.…”

Section: A 3-d Versus 2-d Modelingmentioning

confidence: 99%

Characterization of 3-D Volumetric Probabilistic Scenes for Object Recognition

Restrepo

Mayer

Ulusoy

et al. 2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

This paper presents a new volumetric representation for categorizing objects in large-scale 3-D scenes reconstructed from image sequences. This work uses a probabilistic volumetric model (PVM) that combines the ideas of background modeling and volumetric multi-view reconstruction to handle the uncertainty inherent in the problem of reconstructing 3-D structures from 2-D images. The advantages of probabilistic modeling have been demonstrated by recent application of the PVM representation to video image registration, change detection and classification of changes based on PVM context. The applications just mentioned, operate on 2-D projections of the PVM. This paper presents the first work to characterize and use the local 3-D information in the scenes. Two approaches to local feature description are proposed and compared: 1) features derived from a PCA analysis of model neighborhoods; and 2) features derived from the coefficients of a 3-D Taylor series expansion within each neighborhood. The resulting description is used in a bag-of-features approach to classify buildings, houses, cars, planes, and parking lots learned from aerial imagery collected over Providence, RI. It is shown that both feature descriptions explain the data with similar accuracy and their effectiveness for dense-feature categorization is compared for the different classes. Finally, 3-D extensions of the Harris corner detector and a Hessian-based detector are used to detect salient features. Both types of salient features are evaluated through object categorization experiments, where only features with maximal response are retained. For most saliency criteria tested, features based on the determinant of the Hessian achieved higher classification accuracy than Harris-based features.

show abstract

“…We assume that the scene has already been segmented into objects and focus on the classification of objects. Some previous works perform segmentation of objects in a 3D scene (Silberman et al, 2012, Knopp et al, 2011 or perform clustering in feature space in order to segment similar objects in an indoor scan .…”

Section: Overviewmentioning

confidence: 99%

Object Classification via Planar Abstraction

Oesau¹,

Lafarge²,

Alliez³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:We present a supervised machine learning approach for classification of objects from sampled point data. The main idea consists in first abstracting the input object into planar parts at several scales, then discriminate between the different classes of objects solely through features derived from these planar shapes. Abstracting into planar shapes provides a means to both reduce the computational complexity and improve robustness to defects inherent to the acquisition process. Measuring statistical properties and relationships between planar shapes offers invariance to scale and orientation. A random forest is then used for solving the multiclass classification problem. We demonstrate the potential of our approach on a set of indoor objects from the Princeton shape benchmark and on objects acquired from indoor scenes and compare the performance of our method with other point-based shape descriptors.

show abstract

Scene Cut: Class-Specific Object Detection and Segmentation in 3D Scenes

Cited by 22 publications

References 25 publications

Sliding Shapes for 3D Object Detection in Depth Images

Sliding Shapes for 3D Object Detection in Depth Images

Characterization of 3-D Volumetric Probabilistic Scenes for Object Recognition

Object Classification via Planar Abstraction

Contact Info

Product

Resources

About