Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives

Jensen, Morten Bornø; Philipsen, Mark Philip; Møgelmose, Andreas; Moeslund, Thomas B.; Trivedi, Mohan M.

doi:10.1109/tits.2015.2509509

Cited by 206 publications

(106 citation statements)

References 62 publications

(206 reference statements)

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…Several methods have been developed to map particular types of objects from street-level imagery: manholes [12], telecom assets [10], road signs [29], and traffic lights [30,31]. These methods rely on position triangulation from individual camera views to geolocate the considered road furniture elements.…”

Section: Related Workmentioning

confidence: 99%

Automatic Discovery and Geotagging of Objects from Street View Imagery

2018

View full text Add to dashboard Cite

Abstract:Many applications, such as autonomous navigation, urban planning, and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper, we propose the automatic detection and computation of the coordinates of recurring stationary objects of interest using street view imagery. Our processing pipeline relies on two fully convolutional neural networks: the first segments objects in the images, while the second estimates their distance from the camera. To geolocate all the detected objects coherently we propose a novel custom Markov random field model to estimate the objects' geolocation. The novelty of the resulting pipeline is the combined use of monocular depth estimation and triangulation to enable automatic mapping of complex scenes with the simultaneous presence of multiple, visually similar objects of interest. We validate experimentally the effectiveness of our approach on two object classes: traffic lights and telegraph poles. The experiments report high object recall rates and position precision of approximately 2 m, which is approaching the precision of single-frequency GPS receivers.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Discovery and Geotagging of Objects from Street View Imagery

2018

View full text Add to dashboard Cite

show abstract

“…The channels subsampled corresponds to a halving of the dimensions. [4] The training is done using 3,728 positives TL samples with a resized resolution of 25x25, and 5,772 frames without any TLs and hard negatives generated from 1 execution of bootstrapping on the 5 night training clips from the LISA TL dataset [11]. Examples of these hard negatives are seen in Figure 2.…”

Section: Learning-based Detectormentioning

confidence: 99%

“…The data is generated from a 5min and 12s long video sequence containing 25 physical TLs split between 5 different types: go, go left, warning, stop, and stop left. [11] The mDs are decreased in the last two iteration in Table 1 as the training time increases significantly when the nOctUp and treeDepth are increased. As the training have been done on multiple different computers, the average training time, defined in Table 1, is calculated from calculated the average training time from the computer being involved in all 6 iterations for the most comparable results.…”

Section: Parameter Optimizationmentioning

confidence: 99%

“…The parameter sweep was done using MATLAB R2015b on Windows 7 Enterprise, both 64-bit. Each detections will be quantified in accordance to the VIVA-challenge [9], where the Area-Under-Curve(AUC) of a Precision-Recall curve(PR-curve) generated from the ACF results is used as the final evaluation metric [11]. Furthermore, the true positive criteria in the VIVA-challenge defines a detection as one that is overlapping with an annotation with more than 50 %., as defined in Equation (1).…”

Section: Parameter Optimizationmentioning

confidence: 99%

“…In this paper, we will do a comprehensive analysis of three central parameters for the ACF object detector, applied on the night data from freely available LISA Traffic Light Dataset used in the VIVA-challenge [11]. The contributions of this paper are thus threefold:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Data‐driven protection levels for camera and 3D map‐based safe urban localization

Gupta

Gao

2021

Navigation

View full text Add to dashboard Cite

Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives

Cited by 206 publications

References 62 publications

Automatic Discovery and Geotagging of Objects from Street View Imagery

Automatic Discovery and Geotagging of Objects from Street View Imagery

Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights

Data‐driven protection levels for camera and 3D map‐based safe urban localization

Contact Info

Product

Resources

About