Efficient rotation invariant object detection using boosted Random Ferns

Villamizar, Michael; Moreno-Noguer, Francesc; Andrade‐Cetto, Juan; Sanfeliu, Alberto

doi:10.1109/cvpr.2010.5540104

Cited by 48 publications

(59 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This estimator uses the Hough transform to learn and map the local appearances of objects (encoded by RFs) into probabilistic votes for the object center. This methodology overcomes to previous works which compute rough estimators or predict the object size at first [13,22].…”

Section: Introductionmentioning

confidence: 93%

“…In other words, these approaches aim for (ii) reducing the search space during the detection phase. This is also achieved by means of branch and bound techniques [8,9], using object priors [1] or splitting the process in two consecutive phases of object estimation and specific detection [11,13,14,22]. Finally, other works (iii) have proposed to share features across object classes or views [20,23,25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient 3D Object Detection using Multiple Pose-Specific Classifiers

Villamizar¹,

Gräbner²,

Andrade‐Cetto³

et al. 2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

We propose an efficient method for object localization and 3D pose estimation. A two-step approach is used. In the first step, a pose estimator is evaluated in the input images in order to estimate potential object locations and poses. These candidates are then validated, in the second step, by the corresponding pose-specific classifier. The result is a detection approach that avoids the inherent and expensive cost of testing the complete set of specific classifiers over the entire image. A further speedup is achieved by feature sharing. Features are computed only once and are then used for evaluating the pose estimator and all specific classifiers. The proposed method has been validated on two public datasets for the problem of detecting of cars under several views. The results show that the proposed approach yields high detection rates while keeping efficiency.

show abstract

Section: Introductionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Efficient 3D Object Detection using Multiple Pose-Specific Classifiers

Villamizar¹,

Gräbner²,

Andrade‐Cetto³

et al. 2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…2 (d)). For this purpose, we resort to Boosted Random Ferns (BRFs) since they have demonstrated to be able to detect objects robustly and with low computational cost [44,39].…”

Section: The Object Classifiermentioning

confidence: 99%

“…Subsequently, Boosted Random Ferns (BRFs) were introduced to efficiently learn and detect object classes under intra-class appearance changes [35,39,44]. The BRFs improve the detection performance of RFs since the most discriminative ferns are selected via boosting to compute the object classifier.…”

Section: Introductionmentioning

confidence: 99%

Random clustering ferns for multimodal object recognition

Villamizar

Garrell

Sanfeliu

et al. 2016

Neural Comput & Applic

View full text Add to dashboard Cite

We propose an efficient and robust method for the recognition of objects exhibiting multiple intraclass modes, where each one is associated to a particular object appearance. The proposed method, called Random Clustering Ferns (RCFs), combines synergically a single and real-time classifier, based on the boosted assembling of extremely-randomized trees (ferns), with an unsupervised and probabilistic approach in order to recognize efficiently object instances in images and discover simultaneously the most prominent appearance modes of the object through tree-structured visual words. In particular, we use Boosted Random Ferns (BRFs) and probabilistic Latent Semantic Analysis (pLSA) to obtain a discriminative and multimodal classifier that automatically clusters the response of its randomized trees in function of the visual object appearance.The proposed method is validated extensively in synthetic and real experiments, showing that the method is capable of detecting objects with diverse and complex appearance distributions in real-time performance.

show abstract

“…Extensions on this work, have been done in [17], where a pool of shared RFs was created obtaining a faster and efficient method for detecting even multiple classes. On top of that, in [16], a boosting algorithm was used for training the classifier with the best samples over the image domain.…”

Section: Boosted Random Ferns (Brfs)mentioning

confidence: 99%

Real Time People Detection Combining Appearance and Depth Image Spaces Using Boosted Random Ferns

Vaquero

Villamizar

Sanfeliu

2015

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a robust and real-time method for people detection in urban and crowed environments. Unlike other conventional methods which either focus on single features or compute multiple and independent classifiers specialized in a particular feature space, the proposed approach creates a synergic combination of appearance and depth cues in a unique classifier. The core of our method is a Boosted Random Ferns classifier that selects automatically the most discriminative local binary features for both the appearance and depth image spaces. Based on this classifier, a fast and robust people detector which maintains high detection rates in spite of environmental changes is created. The proposed method has been validated in a challenging RGB-D database of people in urban scenarios and has shown that outperforms state-ofthe-art approaches in spite of the difficult environment conditions. As a result, this method is of special interest for real-time robotic applications where people detection is a key matter, such as human-robot interaction or safe navigation of mobile robots for example.

show abstract

Efficient rotation invariant object detection using boosted Random Ferns

Abstract: We

Cited by 48 publications

References 28 publications

Efficient 3D Object Detection using Multiple Pose-Specific Classifiers

Efficient 3D Object Detection using Multiple Pose-Specific Classifiers

Random clustering ferns for multimodal object recognition

Real Time People Detection Combining Appearance and Depth Image Spaces Using Boosted Random Ferns

Contact Info

Product

Resources

About