Traffic Sign Recognition Using a Multi-Task Convolutional Neural Network

Luo, Huiwu; Yang, Yi; Tong, Bei; Wu, Fuchao; Fan, Bin

doi:10.1109/tits.2017.2714691

Cited by 174 publications

(91 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…1). Deep learning approaches have set the benchmark on many popular object detection datasets, such as PASCAL VOC [17] and COCO [18], and have been widely applied in autonomous driving, including detecting traffic lights [19]- [22], road signs [23]- [25], people [26]- [28], or vehicles [29]- [33], to name a few. State-of-the-art deep object detection networks follow one of two approaches: the two-stage or the one-stage object detection pipelines.…”

Section: Deep Object Detectionmentioning

confidence: 99%

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Feng

Haase-Schütz

Rosenbaum

et al. 2021

IEEE Trans. Intell. Transport. Syst.

811

338

View full text Add to dashboard Cite

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of "what to fuse", "when to fuse", and "how to fuse" remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/. 0.99 0.8 0.98 0.99 0.96 0.96 0.94 Vehicle Person Road sign Traffic light LiDAR Points Map Radar Points RGB Image

show abstract

Section: Deep Object Detectionmentioning

confidence: 99%

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Feng

Haase-Schütz

Rosenbaum

et al. 2021

IEEE Trans. Intell. Transport. Syst.

811

338

View full text Add to dashboard Cite

show abstract

“…The experiments are conducted under normal light condition and weak light condition, and the IE-MSER method of this paper is compared with recent advance methods such as HOG+SVM [34] , FCN (Fully Convolutional Network) [35] , RGB_MSER [36] , YCbCr_DtBs [37] . The results of detection time and recall are shown in Table.1.…”

Section: Experiments and Analysis In Detection Stagementioning

confidence: 99%

Real-Time Detection and Recognition of Road Traffic Signs using MSER and Random Forests

Kuang¹,

Fu²,

Liu³

2018

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Abstract-Real-time detection and recognition of road traffic signs plays an important role in advanced driving assistance system. Typically, the region of interest (ROI) method is effective in feature extraction but inefficient because it is sensitive to illumination changes. In this paper, we propose a maximally stable extremal regions (MSER) method with image enhancement to greatly improve ROI. Firstly, we employ gray world algorithm to process original images. And then potential areas of traffic signs are obtained through increasing the image contrast ratio and extracting the image-enhanced MSER. According to the characteristic variable and the geometry moment invariants, the geometric characteristics of traffic signs are extracted to obtain the ROIs. Finally, HSV-HOG-LBP feature is constructed and the random forests algorithm is used to identify the traffic signs. The experimental results show that our proposed method show strong robustness on illumination condition and rotation scale, and achieves a good performance by experiments with actual images and German traffic sign detection benchmark (GTSDB) data set.

show abstract

“…Selain informasi jarak, manusia mampu melakukan klasifikasi terhadap objek yang ada di jalan dengan mudah, seperti trotoar, pohon, pejalan kaki dan kendaraan lainnya di jalan. Dengan teknik pembelajaran, banyak penelitian telah dilakukan dengan menggunakan kecerdasan buatan dan berhasil melakukan pengenalan jalan [5] maupun menklasifikasikan objek-objek yang beragam, seperti rambu lalu lintas [6], pejalan kaki [7] dan lubang di jalan [8], namun metode pembelajaran seperti ini membutuhkan dataset dalam jumlah yang sangat banyak dan bervariasi, serta membutuhkan kemampuan komputasi yang tinggi sehingga sulit diaplikasikan pada komputer sederhana secara real-time.…”

Section: Pendahuluanunclassified

Implementasi Navigasi Kendaraan Dengan Menggunakan Embedded Pc Dan Deteksi Jalan Berbasis Metode Texture Filter

Mae

Susanto

2018

Computatio

View full text Add to dashboard Cite

Navigasi kendaraan adalah proses pengenalan jalan dan mengarahkan kendaraan pada lintasan yang diinginkan. Penelitian tentang navigasi kendaraan umumnya berfokus pada pengembangan Advanced Driver Assistance System (ADAS) untuk meningkatkan keselamatan dalam berkendaradengan tujuan jangka panjang untuk mewujudkan kendaraan otonom. Pada umumnya navigasi kendaraan dilakukan dengan menggunakan banyak jenis instrumen pengukuran yang berukuran besar dan sulit diaplikasikan pada kendaraan secara umum. Penelitian ini dilakukan untuk menguji ADAS dengan menggunakan instrumen sederhana dan mudah untuk dipasang pada kendaraan. Navigasi dimulai dengan proses deteksi sisi jalan dengan mengamati area jalan pada jarak 10m hingga 14m di depan kendaraan menggunakan teknik pengolahan citra. Hasil deteksi sisi jalan digunakan untuk menghasilkan rekomendasi arah gerak kendaraan yang diubah ke dalam bentuk rekomendasi putaran kemudi bagi pengemudi. Rekomendasi arah gerak kendaraan diperoleh melalui perhitungan sudut yang dibentuk oleh kendaraan terhadap titik tengah lajur jalan pada jarak yang telah ditentukan. Pengujian dilakukan secara real-time dengan menggunakan sebuah Embedded PCdapat mencapai waktu pengolahan citra 13,962 ms dengan tingkat keberhasilan deteksi jalan sebesar 89,7% dan estimasi tingkat kesesuaian data rekomendasi putaran kemudi sebesar 91,04% yang dibandingkan terhadap putaran kemudi oleh pengemudi

show abstract

Traffic Sign Recognition Using a Multi-Task Convolutional Neural Network

Cited by 174 publications

References 35 publications

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Real-Time Detection and Recognition of Road Traffic Signs using MSER and Random Forests

Implementasi Navigasi Kendaraan Dengan Menggunakan Embedded Pc Dan Deteksi Jalan Berbasis Metode Texture Filter

Contact Info

Product

Resources

About