Randomized trees for real-time keypoint recognition

By Vincent Lepetit, Pascal Lagger, Pascal Fua. Computer Vision and Pattern Recognition, 2005

509 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d0faf378ca4d6227b47bb36254a57f7ceeb0c566

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Guiding Visual Surveillance by Tracking Human Attention (2009, unknown): “Randomised trees and ferns have been successfully applied to the tasks of object detection and classification in small image patches [1, 2, 7, 10, 18].”
Random Forests (2012, unknown): “フィルタ φ は扱うデータに応じて定義する必要があるが,コンピュータビジョンの分野で広く用いられているのは,図 2のように処理対象の局所パッチの中である 2点を取り出し,その差分を計算するというものである [11], [16].”
Object retrieval with large vocabularies and fast spatial matching (2007, methodology): “We replace this exact computation by an approximate nearest neighbor method, and use a forest of 8 randomized k-d trees [5, 15, 23] built over the cluster centers at the beginning of each iteration to increase speed.”
End-to-End Learning of Decision Trees and Forests (2019, background): “In order to improve their performance, it is common practice to engineer split features for a specific task (Lepetit et al. 2005; Gall and Lempitsky 2009; Kontschieder et al. 2013; Cordts et al. 2017).”
Structured class-labels in random forests for semantic image labelling (2011, background): “Recently, random forests were customized for a large variety of tasks in computer vision [5, 11, 20, 19, 21, 22].”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, background): “In a similar manner to Amit et al. (1997), Lepetit et al. (2005) , several texture-layout potential classifiers can be trained on random subsets of the image data and combined by averaging:”
Semi-supervised On-Line Boosting for Robust Tracking (2008, unknown): “[2] uses randomized trees and ferns based on pixel pairs [3] to discriminate key points by classiﬁers.”
Scalable Recognition with a Vocabulary Tree (2006, methodology): “For example, Lepetit, Lagger and Fua [ 7 ] use re-rendering of image patches to train multiple decision trees that are used to index keypoints, somewhat reminiscent of locality sensitive hashing [6, 3]. The measurements used in their trees are ratios of pixel intensities.”
The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects (2006, methodology): “For the unary potentials, we use randomised decision trees [12] which are both straightforward to implement and very efficient.”
Random Forests for Real Time 3D Face Analysis (2012, background): “Random forests (Breiman 2001) (RFs) have been successful in semantic segmentation (Shotton et al. 2008), keypoint recognition (Lepetit et al. 2005), object detection (Gall and Lempitsky 2009; Gall et al. 2011), action recognition (Yao et al. 2010; Gall et al. 2011), and real time human pose…”
Efficient Visual Search of Videos Cast as Text Retrieval (2009, methodology): “Recently, however, efficient search methods using hierarchical tree structured vocabulary [24], vocabulary indexed by randomized trees [28], or descriptor indexing by decision trees [ 14 ], [26] have been used.”