A system for traffic sign detection, tracking, and recognition using color, shape, and motion information

By C. Bahlmann, Y. Zhu, Visvanathan Ramesh, M. Pellkofer, T. Koehler. IEEE Proceedings. Intelligent Vehicles Symposium, 2005., 2005

504 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/eedb1d70d3fd4c0ce5c9b6512a3bfe65e49df055

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

In Media Technology

In Human-Computer Interaction

Citations in the corpus

Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, background): “and Haar wavelet-like feature [208], [209], to further extract the traffic sign features.”
Cyber Threats Facing Autonomous and Connected Vehicles: Future Challenges (2017, background): “There are many other applications of cameras in CAVs such as lane detection [35], [36], traffic sign recognition [37], headlight detection [38], etc.”
Detection of traffic signs in real-world images: The German traffic sign detection benchmark (2013, background): “Both very problem-specific [4], [5], [6] as well as rather general object detection approaches [7], [8], [9] have been proposed for traffic sign detection.”
Overview of Environment Perception for Intelligent Vehicles (2017, background): “A Haar wavelet-like feature for traffic sign is another alternative [68], [84].”
Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition (2012, background): “(2005) present a holistic system covering all three processing steps. The classifier itself is claimed to operate with a correct classification rate of 94 % on images fr om 23 classes. Training was conducted on 4,000 traffic sign imag es featuring an unbalanced class frequency of 30 to 600 example s”
Multi-view traffic sign detection, recognition, and 3D localisation (2011, methodology): “through tracking [1,25,23,27], grouping using GPS information, consistency checks in stereo camera imagery, and/or active vision with high-res regions of interest detected within”
Respectful cameras: detecting visual markers in real-time to address privacy concerns (2007, methodology): “Avidan describes the use of a pixel-based method [27] where each pixel’s initial feature vector contains the RGB values, as well as two histograms of oriented gradients similar to those used in Scale Invariant Feature Transform (SIFT) features [28].”
The German Traffic Sign Recognition Benchmark: A multi-class classification competition (2011, background): “In [1], an integrated system for speed limit detection, tracking, and recognition is presented.”