Robust Class Similarity Measure for Traffic Sign Recognition

Ruta, Andrzej; Li, Yongmin; Liu, Xiaohui

doi:10.1109/tits.2010.2051427

Cited by 58 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ruta et al [26] proposed a sign recognition method based on similarity measurement learning from example pairs. Yuan et al [27] developed color global and local oriented edge magnitude pattern features for traffic sign description and applied an SVM for recognition.…”

Section: A Studies On Traffic Sign Detection and Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial-Related Traffic Sign Inspection for Inventory Purposes Using Mobile Laser Scanning Data

Wen

Luo

et al. 2016

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper presents a spatial-related traffic sign inspection process for sign type, position, and placement using mobile laser scanning (MLS) data acquired by a RIEGL VMX-450 system and presents its potential for traffic sign inventory applications. First, the paper describes an algorithm for traffic sign detection in complicated road scenes based on the retroreflectivity properties of traffic signs in MLS point clouds. Then, a point cloud-to-image registration process is proposed to project the traffic sign point clouds onto a 2-D image plane. Third, based on the extracted traffic sign points, we propose a traffic sign position and placement inspection process by creating geospatial relations between the traffic signs and road environment. For further inventory applications, we acquire several spatial-related inventory measurements. Finally, a traffic sign recognition process is conducted to assign sign type. With the acquired sign type, position, and placement data, a spatial-associated sign network is built. Experimental results indicate satisfactory performance of the proposed detection, recognition, position, and placement inspection algorithms. The experimental results also prove the potential of MLS data for automatic traffic sign inventory applications.

show abstract

Section: A Studies On Traffic Sign Detection and Recognitionmentioning

confidence: 99%

“…Similar to the evaluation criteria used in [26], TP ("correctly detected") represents the percentage of the correctly detected testing samples in the reference data. "Partially detected" represents the percentage of the testing samples that are partially detected.…”

Section: ) Quantitative Assessment Of the Proposed Detection Algorithmmentioning

confidence: 99%

Spatial-Related Traffic Sign Inspection for Inventory Purposes Using Mobile Laser Scanning Data

Wen

Luo

et al. 2016

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…They proposed a traffic sign detection algorithm using a novel application of maximally stable extremal regions (MSERs), and proved that the MSERs were robust to variations in both lighting and contrast. In addition, some recent systems utilize the sliding window paradigm [9], [10], [12] to detect traffic sign regions. For example, as presented in [10], the original image is resized by a scaling factor s i to obtain the image corresponding to the pyramid level i.…”

Section: A Related Researchmentioning

confidence: 99%

Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms

Yuan

Guo

Hao

et al. 2015

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

The majority of existing traffic sign detection systems utilize color or shape information, but the methods remain limited in regard to detecting and segmenting traffic signs from a complex background. In this paper, we propose a novel graphbased traffic sign detection approach that consists of a saliency measure stage, a graph-based ranking stage, and a multithreshold segmentation stage. Because the graph-based ranking algorithm with specified color and saliency combines the information of color, saliency, spatial, and contextual relationship of nodes, it is more discriminative and robust than the other systems in terms of handling various illumination conditions, shape rotations, and scale changes from traffic sign images. Furthermore, the proposed multithreshold segmentation algorithm focuses on all the nodes with a nonzero ranking score, which can effectively solve problems such as complex background, occlusion, various illumination conditions, and so on. The results for three public traffic sign sets show that our proposed approach leads to better performance than the current state-of-the-art methods. Moreover, the results are satisfactory even for images containing traffic signs that have been rotated or undergone occlusion, as well as for images that were photographed under different weather and illumination conditions. Index Terms-Graph-based image analysis, graph-based image segmentation, traffic sign detection.

show abstract

“…These methods employ machine learning to accommodate to the average appearance of a sign type. In contrast, Ruta et al [10] proposes to exploit similarities between the sample and reference images. Instead of using structural information, key feature counting is employed in [3], where signs are classified using a modified version of Bag of Words (BoW).…”

Section: Module 1: Single Image Classificationmentioning

confidence: 99%

Robust classification system with reliability prediction for semi-automatic traffic-sign inventory systems

Hazelhoff¹,

Creusen²

2013

2013 IEEE Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Inventories of traffic signs are acquired from street-level images in a semi-automated fashion, employing object detection and classification techniques. This is a challenging task, as signs are captured from different viewpoints and under various weather conditions. Furthermore, many similar signs exist, only differing in minor details, and moreover, sign-like objects occur frequently. Consequently, current state-of-the-art systems are unable to reach the required quality level, implying the need for manual corrections. This involves checking all classification results to correct the small minority of misclassifications. This paper presents a classification approach aiming at both high recognition scores and predicting the reliability of the classification output, enabling selective manual intervention. Two reliability prediction methods are compared, analyzing either the classifier scores, or matching the input samples with predefined templates. Large-scale experiments performed for three sign classes, each containing numerous sign types, show that over 80% of the correctly classified results can be marked as reliable, while not marking any misclassifications as reliable. Hence, our research shows that a reliable prediction is possible and that manual invention can be concentrated to the about 25% remaining samples only. Overall, 92.7% of the 8, 159 signs are classified correctly.

show abstract

Robust Class Similarity Measure for Traffic Sign Recognition

Cited by 58 publications

References 28 publications

Spatial-Related Traffic Sign Inspection for Inventory Purposes Using Mobile Laser Scanning Data

Spatial-Related Traffic Sign Inspection for Inventory Purposes Using Mobile Laser Scanning Data

Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms

Robust classification system with reliability prediction for semi-automatic traffic-sign inventory systems

Contact Info

Product

Resources

About