Exploiting 3D semantic scene priors for online traffic light interpretation

Barnes, Dan; Maddern, Will; Posner, Ingmar

doi:10.1109/ivs.2015.7225746

Cited by 36 publications

(37 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For traffic light regulated intersections, state-of-the-art approaches vary between combining computer vision-based methods with prior scene information to improve detection accuracy while reducing the search space within the image [2,9,13,18].…”

Section: Introductionmentioning

confidence: 99%

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

Radwan

Winterhalter

Dornhege

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

Radwan

Winterhalter

Dornhege

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

“…Recall/True positive rate: We express the percentage number of detected traffic lights by the true positive rate, or also called recall defined as P T P = TP TP+FN , where a true positive (TP) is counted for an overlap threshold IoU larger than 0.3 or 0.5 according to Formula (2). False positives (FP) are counted for predictions not overlapping with a ground truth by the defined overlap threshold.…”

Section: B Metricsmentioning

confidence: 99%

Detecting Traffic Lights by Single Shot Detection

Müller

Dietmayer

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

Recent improvements in object detection are driven by the success of convolutional neural networks (CNN). They are able to learn rich features outperforming hand-crafted features. So far, research in traffic light detection mainly focused on hand-crafted features, such as color, shape or brightness of the traffic light bulb. This paper presents a deep learning approach for accurate traffic light detection in adapting a single shot detection (SSD) approach. SSD performs object proposals creation and classification using a single CNN. The original SSD struggles in detecting very small objects, which is essential for traffic light detection. By our adaptations it is possible to detect objects much smaller than ten pixels without increasing the input image size. We present an extensive evaluation on the DriveU Traffic Light Dataset (DTLD). We reach both, high accuracy and low false positive rates. The trained model is real-time capable with ten frames per second on a Nvidia Titan Xp. Code has been made available at https://github.com/julimueller/ tl_ssd.

show abstract

“…The popular combination of Histogram of Oriented Gradients (HoG) features and SVM classifier were introduced in [24], but additionally also relying on prior maps with very precise knowledge of the TL locations. The learning-based ACF detector has previously been used for TLs, where features are extracted as summed blocks of pixels in 10 different channels created from the original input RGB frame.…”

Section: Learning-basedmentioning

confidence: 99%

Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights

Jensen

Philipsen

Moeslund

et al. 2016

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Determining the optimal parameters for a given detection algorithm is not straightforward and what ends up as the final values is mostly based on experience and heuristics. In this paper we investigate the influence of three basic parameters in the widely used Aggregate Channel Features (ACF) object detector applied for traffic light detection. Additionally, we perform an exhaustive search for the optimal parameters for the night time data from the LISA Traffic Light Dataset. The optimized detector reaches an Area-Under-Curve of 66.63 % on calculated precision-recall curve.

show abstract

Exploiting 3D semantic scene priors for online traffic light interpretation

Cited by 36 publications

References 12 publications

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

Detecting Traffic Lights by Single Shot Detection

Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights

Contact Info

Product

Resources

About