Journal ArticleDOI
Simultaneous Recognition and Modeling for Learning 3-D Object Models From Everyday Scenes
Reads0
Chats0
TLDR
A framework to address simultaneous object recognition and modeling at the same time, which is solely online, and a formulation based on maximum likelihood estimation is developed.Abstract:
Object recognition and modeling have classically been studied separately, but practically, they are two closely correlated aspects. In this paper, by exploring the interrelations, we propose a framework to address these two problems at the same time, which we call simultaneous recognition and modeling. Differing from traditional recognition process which consists of off-line object model learning and on-line recognition procedures, our method is solely online. Starting with an empty object database, we incrementally build up object models while at the same time using these models to identify newly observed object views. In the proposed framework, objects are modeled as view graphs and a probabilistic observation model is presented. Both the appearance and the spatial structure of the object are examined, and a formulation based on maximum likelihood estimation is developed. Joint object recognition and modeling are achieved by solving the optimization problem. To evaluate the framework, we have developed a method for simultaneously learning multiple 3-D object models directly from the cluttered indoor environment and tested it using several everyday scenes. Experimental results demonstrate that the framework can cope with the recognition and modeling problem together nicely.read more
Citations
More filters
Journal ArticleDOI
View-Based 3-D Model Retrieval: A Benchmark
TL;DR: By quantitatively analyzing the performances, it is discovered the graph matching-based method with deep features, especially the clique graph matching algorithm with convolutional neural networks features, can usually outperform the others.
Journal ArticleDOI
Unsupervised Learning of 3-D Local Features From Raw Voxels Based on a Novel Permutation Voxelization Strategy
TL;DR: An unsupervised 3-D local feature learning framework based on a novel permutation voxelization strategy to learn high-level and hierarchical 3- D local features from raw3-D voxels and results show that the learned local features outperform the other state-of-the-art 2-D shape descriptors.
Journal ArticleDOI
Speedup 3-D Texture-Less Object Recognition Against Self-Occlusion for Intelligent Manufacturing
TL;DR: An online 3-D object detection and pose estimation method to overcome self-occlusion for textureless objects and can maximize the GPU parallel processing capabilities especially in practice is proposed.
Proceedings ArticleDOI
Object Recognition App for Visually Impaired
TL;DR: This project proposes an android application to help blind people see through handheld device like mobile phone that integrates various techniques to build a rich android application that will not only recognize objects around visually impaired people in real time but also give an audio output to assist them as quickly as possible.
Journal ArticleDOI
Deep Correlated Joint Network for 2-D Image-Based 3-D Model Retrieval
TL;DR: Li et al. as discussed by the authors proposed a deep correlated joint network (DCJN) approach for 2D image-based 3D model retrieval, which can jointly learn two distinct deep neural networks, which are trained for individual modalities to learn two deep nonlinear transformations for visual feature extraction from the co-embedding feature space.
References
More filters
Journal ArticleDOI
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Journal ArticleDOI
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Journal ArticleDOI
Shape matching and object recognition using shape contexts
TL;DR: This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.
Proceedings Article
Visual categorization with bags of keypoints
TL;DR: This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches and shows that it is simple, computationally efficient and intrinsically invariant.