Multi-view traffic sign detection, recognition, and 3D localisation

By Radu Timofte, Karel Zimmermann, Luc Van Gool. Machine Vision and Applications, 2011

435 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3b788fd0817336b3db3e111fa2ff50b665070e95

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Traffic sign detection for U.S. roads: Remaining challenges and a case for tracking (2014, background): “The earliest approaches [4]–[7] were model-based and relied on static knowledge of traffic sign appearance, such as shape or color.”
Improved YOLOv5 network for real-time multi-scale traffic sign detection (2021, background): “Keywords AF-FPN, data augmentation, multi-scale targets, YOLOv5 1 Introduction The traffic sign recognition system is the data foundation of intelligent transportation systems (ITS) and unmanned driving system, balancing the accuracy and real-time performance of the traffic sign detection and recogn”
Knowledge-based Recurrent Attentive Neural Network for Traffic Sign Detection (2018, background): “However, those state-of-the-art methods [10], [12] at several popular datasets [13], [14] are not excellent at handling with small road signs recognition problem in a crowded scene with many other attractors like pedestrians and other vehicles.”
Object Detection in 20 Years: A Survey (2019, background): “BelgianTSD [82] 2012 Consists of ∼7,300 static images, ∼120,000 video frames, and ∼11,000 traffic sign annotations of 269 types.”
Traffic sign recognition — How far are we from the solution? (2013, methodology): “To assess detection performance we use GTSD and BTSD.”
Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection (2018, methodology): “Color-based methods usually use normalized RGB [19], YUV [20], or HSI [21] color spaces with a designed threshold to extract the region of interest.”
CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition (2017, background): “It is a common practice to test the robustness of these systems with traffic datasets [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].”
A Survey of the Four Pillars for Small Object Detection: Multiscale Representation, Contextual Information, Super-Resolution, and Region Proposal (2022, methodology): “…[52]: CURE-TSD datasets consist of real-world data and synthetic virtual data, in which 49 challenge-free real-world video sequences are generated by combining 300 frames from BelgiumTs [60] and another 49 synthesized video sequences are generated with a game development tool Unreal Engine4.”
Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach (2020, methodology): “The simulation involves the public MNIST dataset [31], and the BelgiumTSC (Belgium Traffic Sign for Classification) vehicular dataset [32].”
Recognizing Text-Based Traffic Guide Panels with Cascaded Localization Network (2016, methodology): “For the system validation, several datasets have also been proposed, including the German traffic sign detection benchmark [20], the German traffic sign recognition benchmark [21], and the Belgian traffic sign dataset [22].”
Traffic Sign Recognition via Multi-Modal Tree-Structure Embedded Multi-Task Learning (2017, background): “• German TSR Benchmark (GTSRB)1 [4], [39] • KUL Belgium Traffic Sign Classification Data set (BelgiumTSC)2 [40] • Swedish Traffic Signs Data set (STS Data set)3 [41] • RUG Traffic Sign Image Database (RUG Data set)4 [42] • Stereopolis Database5 [43] • LISA Traffic Sign Data set (LISA Data set)6 [1].”
PRADA: Protecting Against DNN Model Stealing Attacks (2018, background): “Using an appropriate δ threshold, it detects quickly T RAMER , P APERNOT and C OLOR attacks while avoiding false positives for benign queries across the tested datasets: MNIST, USPS, GTSRB (+ sequence), BTS and random queries.”