This paper introduces a new real-time traffic light recognition system for on-vehicle camera applications. This approach has been tested with good results in urban scenes. Thanks to the use of our generic “Adaptive Templates” it would be possible to recognize different kinds of traffic lights from various countries. This approach is mainly based on a spot detection algorithm therefore able to detect lights from a high distance with the main advantage of being not so sensitive to motion blur and illumination variations. The detected spots together with other shape analysis form strong hypothesis we feed our Adaptive Templates Matcher with. Even though it is still in progress, our system was validated in real conditions in our prototype vehicle and also using registered video sequences. The authors noticed a high rate of correctly recognized traffic lights and very few false alarms. Processing is performed in real-time on 640x480 images using a 2.9GHz single core desktop computer.

Real Time Visual Traffic Lights Recognition Based on Spot Light Detection and Adaptive Traffic Lights Templates

Traffic Light Detection with Color and Edge Information

Traffic light recognition is an essential task for an advanced driving assistance system (ADAS) as well as for autonomous vehicles. Recently, deep-learning has become increasingly popular in vision-based object recognition owing to its high performance of classification. In this study, we investigate how to design a deep-learning based high-performance traffic light detection system. Two main components of the recognition system are investigated: the color space of the input video and the network model of deep learning. We apply six color spaces (RGB, normalized RGB, Ruta’s RYG, YCbCr, HSV, and CIE Lab) and three types of network models (based on the Faster R-CNN and R-FCN models). All combinations of color spaces and network models are implemented and tested on a traffic light dataset with 1280×720 resolution. Our simulations show that the best performance is achieved with the combination of RGB color space and Faster R-CNN model. These results can provide a comprehensive guideline for designing a traffic light detection system.

/pdf/an-efficient-color-space-for-deep-learning-based-traffic-3fyrbjii6x.pdf

An Efficient Color Space for Deep-Learning Based Traffic Light Recognition

Autonomous terrestrial vehicles must be capable of perceiving traffic lights and recognizing their current states to share the streets with human drivers. Most of the time, human drivers can easily identify the relevant traffic lights. To deal with this issue, a common solution for autonomous cars is to integrate recognition with prior maps. However, additional solution is required for the detection and recognition of the traffic light. Deep learning techniques have showed great performance and power of generalization including traffic related problems. Motivated by the advances in deep learning, some recent works leveraged some state-of-the-art deep detectors to locate (and further recognize) traffic lights from 2D camera images. However, none of them combine the power of the deep learning-based detectors with prior maps to recognize the state of the relevant traffic lights. Based on that, this work proposes to integrate the power of deep learning-based detection with the prior maps used by our car platform IARA (acronym for Intelligent Autonomous Robotic Automobile) to recognize the relevant traffic lights of predefined routes. The process is divided in two phases: an offline phase for map construction and traffic lights annotation; and an online phase for traffic light recognition and identification of the relevant ones. The proposed system was evaluated on five test cases (routes) in the city of Vitoria, each case being composed of a video sequence and a prior map with the relevant traffic lights for the route. Results showed that the proposed technique is able to correctly identify the relevant traffic light along the trajectory.

Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars

Traffic light recognition using high-definition map features

Traffic light recognition is being intensively researched for the purpose of reducing traffic accidents at intersections and realizing autonomous driving. However, conventional vision-based approaches have several limitations due to full image scanning, always-on operation, various different types of traffic lights, and complex driving environments. In particular, it might be impossible to recognize a relevant traffic light among multiple traffic lights at multiple intersections. To overcome such limitations, we propose an effective architecture that integrates a vision system with an accurate positioning system and an extended digital map. The recognition process is divided into four stages and we suggest an extended methodology for each stage. These stages are: ROI generation, detection, classification, and tracking. The 3D positions of traffic lights and slope information obtained from an extended digital map enable ROIs to be generated accurately, even on slanted roads, while independent design and implementation of individual recognition modules for detection and classification allow for selection according to the type of traffic light face. Such a modular architecture gives the system simplicity, flexibility, and maintainable algorithms. In addition, adaptive tracking that exploits the distance to traffic lights allows for seamless state estimation through smooth data association when measurements change from long to short ranges. Evaluation of the proposed system occurred at six test sites and utilized two different types of traffic lights, seven states, sloped roads, and various environmental complexities. The experimental results show that the proposed system can recognize traffic lights with 98.68% precision, 92.73% recall, and 95.52% accuracy in the 10.02–81.21 m range.

Sangwoo Jeong

Papers

Traffic light recognition exploiting map and localization at every stage