A Bag of Words Approach for 3D Object Categorization

Toldo, Roberto; Castellani, Umberto; Fusiello, Andrea

doi:10.1007/978-3-642-01811-4_11

Cited by 49 publications

(30 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In case of noisy data, and objects attached to other objects, it is worth to analyse which parts of the vector contain the best information. In the future, a bag-of-words approach will be applied to be able to weight the attributes in the feature vector (Toldo et al, 2009). The weighting depends again on the class of the component.…”

Section: Discussionmentioning

confidence: 99%

User-assisted Object Detection by Segment Based Similarity Measures in Mobile Laser Scanner Data

Elberink

Kemboi

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper describes a method that aims to find all instances of a certain object in Mobile Laser Scanner (MLS) data. In a userassisted approach, a sample segment of an object is selected, and all similar objects are to be found. By selecting samples from multiple classes, a classification can be performed. Key assumption in this approach is that a one-to-one relationship exists between segments and objects. In this paper the focus is twofold: (1) to explain how to get proper segments, and (2) to describe how to find similar objects. Point attributes that help separating neighbouring objects are presented. These point attributes are used in an attributed connected component algorithm where segments are grown, based on proximity and attribute values. Per component, a feature vector is proposed that consists of two parts. The first is a height histogram, containing information on the height distribution of points within a component. The second contains size and shape information, based on the components' bounding box. A simple correlation function is used to find similarities between samples, as selected by a user, and other components. Our approach is tested on a MLS dataset, containing over 300 objects in 13 classes. Detection accuracies heavily depend on the success of the segmentation, and the number of selected samples in combination with the variety of object types in the scene.

show abstract

Section: Discussionmentioning

confidence: 99%

User-assisted Object Detection by Segment Based Similarity Measures in Mobile Laser Scanner Data

Elberink

Kemboi

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Recently, several bag-of-words saliency metrics have been explored [21]- [24]. Among the "words" (descriptors) appearing in an image, only the salient words are selectively captured and referred to as a bag-of-keypoints in [23].…”

Section: B Review Of Visual Saliencymentioning

confidence: 99%

“…Among the "words" (descriptors) appearing in an image, only the salient words are selectively captured and referred to as a bag-of-keypoints in [23]. In [24], a histogram of the distribution of words was used as a global signature of an image, and only salient regions were sampled to solve an object classification problem.…”

Section: B Review Of Visual Saliencymentioning

confidence: 99%

Combined visually and geometrically informative link hypothesis for pose-graph visual SLAM using bag-of-words

Kim

Eustice

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper reports on a method to combine expected information gain with visual saliency scores in order to choose geometrically and visually informative loop-closure candidates for pose-graph visual simultaneous localization and mapping (SLAM). Two different bag-of-words saliency metrics are introduced-global saliency and local saliency. Global saliency measures the rarity of an image throughout the entire data set, while local saliency describes the amount of texture richness in an image. The former is important in measuring an overall global saliency map for a given area, and is motivated from inverse document frequency (a measure of rarity) in information retrieval. Local saliency is defined by computing the entropy of the bag-of-words histogram, and is useful to avoid adding visually benign key frames to the map. The two different metrics are presented and experimentally evaluated with indoor and underwater imagery to verify their utility.

show abstract

“…What's more, even popular 2D features such as SURF have been extended to 3D [15]. (While no one feature combines the advantages of all, the reliability of these has allowed people to move to the next step of retrieval (BOF based [21]), classification ( [28]) and recognition([2])). For pose estimation, the problems of orientation, noise, deformation and finding good shape description, means that performing ICP-based 3D matching on huge databases, is very expensive and prone to minima.…”

Section: Introductionmentioning

confidence: 99%

Class-specific 3D localization using constellations of object parts

Prasad

Knopp

Gool

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

Improvement in acquisition systems, has resulted in the ability to capture more realistic 3D models of real world objects, creating a need for better data processing techniques, as in the case of text and images. In this paper, we address the issue of learning classspecific, deformable, 3D part-based structure for object part localization in 3D models/scenes. We employ an inference framework upon fully connected part-based graphs inspired by Pictorial Structures (PS), which combine the local appearance of parts and the long-range structural properties. Using efficient tools for learning the model and performing inference, we show good results on a variety of classes, outperforming PS [7] and ISM [15]. Further, a similar inference framework is employed to find dense correspondences between 3D models, seeded by the above object part localization. Our results show promise for application in more complex 3D processing tasks such as part retrieval, pose estimation, scene understanding and recognition.

show abstract

A Bag of Words Approach for 3D Object Categorization

Cited by 49 publications

References 16 publications

User-assisted Object Detection by Segment Based Similarity Measures in Mobile Laser Scanner Data

User-assisted Object Detection by Segment Based Similarity Measures in Mobile Laser Scanner Data

Combined visually and geometrically informative link hypothesis for pose-graph visual SLAM using bag-of-words

Class-specific 3D localization using constellations of object parts

Contact Info

Product

Resources

About