Traffic Sign Recognition and Localization for Databases of Traffic Signs

Kršák, Emil; Toth, Stefan

doi:10.2478/v10198-011-0039-2

Cited by 11 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main colours that used for the traffic signs are a red, a blue and a yellow. With this in mind, the detection methods can be divided to three main parts: colour-based method, shapebased method and hybrid method which combine the different kinds of methods together [1][2][3][4][5].…”

Section: Detection Methods Of the Vertical Traffic Signsmentioning

confidence: 99%

Signal processing - object detection methods with usage of optical correlator

Solus

Ovseník

Turán

2016

2016 26th International Conference Radioelektronika (RADIOELEKTRONIKA)

View full text Add to dashboard Cite

This article describes the vertical traffic signs recognition (VTSR) system. In this system the Cambridge optical correlator is used as an image comparator in the recognition stage. In our case, the Cambridge optical correlator compares detected traffic signs with reference traffic signs. One step of the VTSR system is the traffic signs detection process. Traffic signs detection is used to locate the area of the traffic sign from the complicated captured image background. The process of location of the traffic sign might be based on different methods.

show abstract

Section: Detection Methods Of the Vertical Traffic Signsmentioning

confidence: 99%

Signal processing - object detection methods with usage of optical correlator

Solus

Ovseník

Turán

2016

2016 26th International Conference Radioelektronika (RADIOELEKTRONIKA)

View full text Add to dashboard Cite

show abstract

“…In order to include signs found in crowded locations, Benesova et al [16] proposed an alternative approach of triangulating traffic sign positions using dedicated hand held devices. For extending to a real-time use-case, an approximate method was also proposed [17]. Another real-time traffic sign positioning method was proposed by Welzel et al [18], using only a monocular color camera and GPS.…”

Section: Related Workmentioning

confidence: 99%

Monocular Vision based Crowdsourced 3D Traffic Sign Positioning with Unknown Camera Intrinsics and Distortion Coefficients

Chawla,

Jukola,

Arani

et al. 2020

Preprint

View full text Add to dashboard Cite

Autonomous vehicles and driver assistance systems utilize maps of 3D semantic landmarks for improved decision making. However, scaling the mapping process as well as regularly updating such maps come with a huge cost. Crowdsourced mapping of these landmarks such as traffic sign positions provides an appealing alternative. The state-of-theart approaches to crowdsourced mapping use ground truth camera parameters, which may not always be known or may change over time. In this work, we demonstrate an approach to computing 3D traffic sign positions without knowing the camera focal lengths, principal point, and distortion coefficients a priori. We validate our proposed approach on a public dataset of traffic signs in KITTI. Using only a monocular color camera and GPS, we achieve an average single journey relative and absolute positioning accuracy of 0.26 m and 1.38 m, respectively.

show abstract

“…In terms of traffic sign localisation and pose estimation, the research [22] utilises the 3D model to estimate the poses of the traffic signs based on the PWP3D method [18]. Krsák and Toth [23] proposed a TSR system with an algorithm to estimate the 3D position of the traffic sign by the mobile vehicle location received from GPS. In actual, the long distance between the vehicle and the sign leads to inaccurate 3D localisation.…”

Section: Related Workmentioning

confidence: 99%

Homography‐based traffic sign localisation and pose estimation from image sequence

2019

View full text Add to dashboard Cite

This study proposes a vision‐based method for traffic sign attribute estimation, i.e. 3D position and pose, from image sequences by binocular or monocular cameras. The method starts with acquiring robust feature correspondences based on homography constraints from image pairs. Then the objective function is designed to integrate the feature correspondences to optimise the parameters of the traffic sign plane in the 3D coordinate. Finally, the sign plane is utilised for attribute estimation. In addition, the authors provide an extension for the raw KITTI dataset, which can be utilised for 3D tasks of traffic sign localisation and pose estimation. In the experiments, three popular methods are employed for comparisons based on the publicly available BelgiumTS and KITTI datasets. The results show that the authors’ method based on SIFT and SURF features can locate the traffic signs with a mean error of ∼0.44 and 0.51 m in the BelgiumTS and KITTI datasets, respectively, and estimate the pose with a mean error of ∼14.45° in the KITTI dataset.

show abstract

Traffic Sign Recognition and Localization for Databases of Traffic Signs

Cited by 11 publications

References 11 publications

Signal processing - object detection methods with usage of optical correlator

Signal processing - object detection methods with usage of optical correlator

Monocular Vision based Crowdsourced 3D Traffic Sign Positioning with Unknown Camera Intrinsics and Distortion Coefficients

Homography‐based traffic sign localisation and pose estimation from image sequence

Contact Info

Product

Resources

About