An efficient automatic traffic sign detection and recognition method for smartphones

Shih, Po-Cheng; Tsai, Chi-Yi; Hsu, Chun‐Fei

doi:10.1109/cisp-bmei.2017.8301993

Cited by 7 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [113], after filtering by shape and resizing ROIs, HOG features are extracted and fed to a linear SVM. This structure is also found in other studies: authors in [114] send HOG results to a group of linear SVMs that are used (in a voting process) to obtain the final classification result, and in [112], authors apply HOG and fed it to a soft margin SVM after filtering by shape, resizing and converting [111], they use the final resized ROIs as feature vectors for a linear SVM.…”

Section: ) Algorithm Structuresupporting

confidence: 53%

“…However, being the input for the CNN of size 32 × 32 and having only two fully connected and three convolution layers, it is possible that any optimization was done. In [114] authors implement the whole data processing pipeline plus SVM on an Apple iPhone 6s, which has a dual-core 1.84 GHz Twister processor and 64GB ROM with 2GB RAM. They obtain 94.48% recall at 30 fps on 640 × 480 pixel images.…”

Section: ) Embedding Methods and Performancementioning

confidence: 99%

“…In [113], the RGB image is converted to the HSV color space, to better account for relationships between colors. Although these procedures are found in the original studies as preprocessing steps, similar methods are defined as part of the detection process in other studies, such as Red Blue Channel Enhancement (RBCE) found in [114]. Simpler strategies are also found, as in [115], where the authors simply convert the image to gray scale.…”

Section: ) Algorithm Structurementioning

confidence: 99%

“…More complex processes have been found, such as in [114], where authors apply Red/Blue Channel Enhancement, followed by Maximally Stable Extremal Regions (MSER) [118] to produce the generated ROIs. Then, they apply region merging and a shape/ratio filtering before obtaining the final ROIs.…”

Section: ) Algorithm Structurementioning

confidence: 99%

See 3 more Smart Citations

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Borrego-Carazo

Castells-Rufas

Biempica³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The advent of machine learning (ML) methods for the industry has opened new possibilities in the automotive domain, especially for Advanced Driver Assistance Systems (ADAS). These methods mainly focus on specific problems ranging from traffic sign and light recognition to pedestrian detection. In most cases, the computational resources and power budget found in ADAS systems are constrained while most machine learning methods are computationally intensive. The usual solution consists in adapting the ML models to comply with the memory and real-time (RT) requirements for inference. Some models are easily adapted to resource-constrained hardware, such as Support Vector Machines, while others, like Neural Networks, need more complex processes to fit into the desired hardware. The ADAS hardware (HW platforms) are diverse, from complex MPSoC CPUs down to classical MCUs, DPSs and application-specific FPGAs and ASICs or specific GPU platforms (such as the NVIDIA families Tegra or Jetson). Therefore, there is a tradeoff between the complexity of the ML model implemented and the selected platform that impacts the performance metrics: function results, energy consumption and speed (latency and throughput). In this paper, a survey in the form of systematic review is conducted to analyze the scope of the published research works that embed ML models into resource-constrained implementations for ADAS applications and what are the achievements regarding the ML performance, energy and speed trade-off. INDEX TERMS Machine learning, embedded software, automotive engineering, GPU, FPGA, ADAS. I. INTRODUCTION Safety is increasingly important for drivers and other users of the driving environment such as pedestrians, cyclists, bikers, scooters, etc. Only in 2016, road accidents in the European Union summed up to 25.600 fatalities and 1.4 million people injured [1]. Many measures are being taken by public institutions (improving road quality, enhancing driver consciousness and driving regulations, etc.) to improve these numbers. However, the cause of most of these accidents resides in human errors or distractions. For this reason, automotive firms are pushing up research on improving safety. The cornerstone of these advances are Advanced Driver Assistance Systems (ADAS). ADAS systems consist in several sensors, processing and actuators components that help drivers to avoid accidents and The associate editor coordinating the review of this manuscript and approving it for publication was Ye Duan.

show abstract

Section: ) Algorithm Structuresupporting

confidence: 53%

Section: ) Embedding Methods and Performancementioning

confidence: 99%

Section: ) Algorithm Structurementioning

confidence: 99%

Section: ) Algorithm Structurementioning

confidence: 99%

See 2 more Smart Citations

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Borrego-Carazo

Castells-Rufas

Biempica³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Various systems uses RFID and GSM module to transmit data and communicate with specific vehicles [3][4]. Specific software and algorithm is also developed to manage vehicles in roads and smart phones are also incorporated in this regard [5][6][7]. Image processing and face detection technologies are also incorporated to manage the system more effectively [8].…”

Section: Introductionmentioning

confidence: 99%

A Microcontroller Based Intelligent Traffic Control System

Arifin¹,

Razi²,

Haque³

et al. 2019

AJESA

View full text Add to dashboard Cite

A new microcontroller based intelligent traffic control system is proposed in this paper. Instead of changing traffic lights automatically for a given interval, this system allows passing the vehicles considering the number of vehicles on the roads. An Atmega 32 microcontroller and infrared sensors (IR sensors) are used to implement the traffic system. An algorithm is also developed for this purpose. The system is simulated and implemented also by constructing a test rig. The results from the simulation and experimental test rig confirm its appropriateness of using in the roads of different cities. No further processing scheme is required for this intelligent traffic control system.

show abstract

Intensive Survey About Road Traffic Signs Preprocessing, Detection and Recognition

Almuhajri

Suen

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

An efficient automatic traffic sign detection and recognition method for smartphones

Cited by 7 publications

References 12 publications

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Resource-Constrained Machine Learning for ADAS: A Systematic Review

A Microcontroller Based Intelligent Traffic Control System

Intensive Survey About Road Traffic Signs Preprocessing, Detection and Recognition

Contact Info

Product

Resources

About