Multiclass Road Sign Detection using Multiplicative Kernel

  title={Multiclass Road Sign Detection using Multiplicative Kernel},
  author={Valentina Zadrija and Sinisa Segvic},
We consider the problem of multiclass road sign detection using a classification function with multiplicative kernel comprised from two kernels. We show that problems of detection and within-foreground classification can be jointly solved by using one kernel to measure object-background differences and another one to account for within-class variations. The main idea behind this approach is that road signs from different foreground variations can share features that discriminate them from… 

Figures and Tables from this paper

Experimental Evaluation of Multiplicative Kernel SVM Classifiers for Multi-Class Detection

This work considers the multi-class object detection approach based on a non-parametric multiplicative kernel, which provides both separation against backgrounds and feature sharing among foreground classes, and proposes to reduce the number of detectors in a novel way, by an appropriate detector selection procedure.



Learning a Family of Detectors via Multiplicative Kernels

This work shows that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions.

Road sign recognition system based on GentleBoost with sharing features

A fast road sign detection and recognition system that takes advantage of the HSI color space to filter most of the false alarms and can detect and recognize road signs efficiently and accurately.

Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle

A novel two-stage technique is proposed which achieves improved detection results by applying temporal and spatial constraints to the occurrences of traffic signs in video by filtering the detection tracks by a learned discriminative model.

Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Object Detection

  • Bo WuR. Nevatia
  • Computer Science
    2007 IEEE 11th International Conference on Computer Vision
  • 2007
This paper proposes a boosting based learning method, called Cluster Boosted Tree (CBT), to automatically construct tree structured object detectors, and shows that this approach outperforms the state-of-the-art methods.

Sharing Visual Features for Multiclass and Multiview Object Detection

A multitask learning procedure, based on boosted decision stumps, that reduces the computational and sample complexity by finding common features that can be shared across the classes (and/or views) and considerably reduce the computational cost of multiclass object detection.

Histograms of oriented gradients for human detection

  • N. DalalB. Triggs
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.

High-Performance Rotation Invariant Multiview Face Detection

A series of innovative methods are proposed to construct a high-performance rotation invariant multiview face detector, including the width-first-search (WFS) tree detector structure, the vector boosting algorithm for learning vector-output strong classifiers, the domain-partition-based weak learning method, the sparse feature in granular space, and the heuristic search for sparse feature selection.

Fast Multi-view Face Detection

A multi-view detector presented in this pa-per is a combination of Viola-Jones detectors, each detectortrained on face data taken from a single viewpoint, which appears that a monolithic approach to face detection is unlearnable with existing classifier trained on all poses.

Part and appearance sharing: Recursive Compositional Models for multi-view

This work proposes Recursive Compositional Models for simultaneous multi-view multi-object detection and parsing, and uses appearance-sharing so that RCMs for the same object, but different viewpoints, share similar appearance cues which helps efficient learning.

Output-Sensitive Algorithms for Computing Nearest-Neighbour Decision Boundaries

Output-sensitive algorithms for computing this decision boundary for point sets on the line and in ℝ2 are developed, which is the best possible when parameterizing with respect to n and k.