Detecting symbols on road surface for mapping and localization using OCR

Schreiber, Markus; Poggenhans, Fabian; Stiller, Christoph

doi:10.1109/itsc.2014.6957755

Cited by 10 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous researchers used various image processing techniques to recognize road markings and signs [1,2,3,4]. For example, Foucher et al [5] presented a method of detection and recognition of lane, crosswalks, arrows, and several related road markings, all painted on the road.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

Vokhidov

Hong

Kang

et al. 2016

Sensors

View full text Add to dashboard Cite

Automobile driver information as displayed on marked road signs indicates the state of the road, traffic conditions, proximity to schools, etc. These signs are important to insure the safety of the driver and pedestrians. They are also important input to the automated advanced driver assistance system (ADAS), installed in many automobiles. Over time, the arrow-road markings may be eroded or otherwise damaged by automobile contact, making it difficult for the driver to correctly identify the marking. Failure to properly identify an arrow-road marker creates a dangerous situation that may result in traffic accidents or pedestrian injury. Very little research exists that studies the problem of automated identification of damaged arrow-road marking painted on the road. In this study, we propose a method that uses a convolutional neural network (CNN) to recognize six types of arrow-road markings, possibly damaged, by visible light camera sensor. Experimental results with six databases of Road marking dataset, KITTI dataset, Málaga dataset 2009, Málaga urban dataset, Naver street view dataset, and Road/Lane detection evaluation 2013 dataset, show that our method outperforms conventional methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Text-based road-signs are recognized by an optical character recognition (OCR) method [1,10,11]. The system can recognize any random text word that might appear.…”

Section: Related Workmentioning

confidence: 99%

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

Vokhidov

Hong

Kang

et al. 2016

Sensors

View full text Add to dashboard Cite

show abstract

“…Optical Character Recognition (OCR) is an important task that has been studied in academia for a long period [85,7]. It has undergone remarkable development in the last decade, contributing to many applications like autonomous driving [87,71], car license plate recognition [99,51], GPT models [74,28], etc. Various datasets [31,19,88,89] and downstream tasks are included within this field, such as text image recognition [75,39,93,14], detection [104,49,40,82], segmentation [88,89,105,66], super-resolution [9,83,48,102], as well as some generation tasks, including text image editing [86,76,92,57,36], document layout generation [54,22,20,38,32], font generation [30,21,35,52], etc.…”

Section: Related Workmentioning

confidence: 99%

Application of Microsoft Agent in Humanized Courseware

Chen

Zheng

Chen

2013

AMR

View full text Add to dashboard Cite

Traditional courseware is lack of humanity. Proposes to use Agent technology achieve the humanized design in courseware. Microsoft Agent with its lively and clear human features has had a significant influence upon traditional human-computer interaction. This paper introduces the related technologies of Microsoft Agent, and discussed the realization of the principles and the design process of the Microsoft Agent in authorware . The paper gives the Agent script design structure, the human feedback of humanized courseware and the notes in the process. Microsoft Agent enhanced the expression and presentation effect of courseware by lively images of anthropomorphic expression, speech and action.

show abstract

“…Ego-lane and host lane are names given to the lane where the vehicle is positioned. Ego-lane analysis comprises multiple tasks related to the host lane, such as lane estimation (LE) [5], lane departure warning (LDW) [6], lane change detection [7], lane marking type (LMT) classification [8], road markings detection and classification [9], and detection of adjacent lanes, also known as multiple lanes detection [10,11], etc. In general, different sensors have been used to address these issues: monocular [12] and stereo [13] cameras, LiDAR [14], and Sensor-fusion [15].…”

Section: Introductionmentioning

confidence: 99%

Ego-Lane Analysis System (ELAS): Dataset and algorithms

Berriel¹,

Aguiar²,

Souza³

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

Decreasing costs of vision sensors and advances in embedded hardware boosted lane related research detection, estimation, tracking, etc. in the past two decades. The interest in this topic has increased even more with the demand for advanced driver assistance systems (ADAS) and self-driving cars. Although extensively studied independently, there is still need for studies that propose a combined solution for the multiple problems related to the ego-lane, such as lane departure warning (LDW), lane change detection, lane marking type (LMT) classification, road markings detection and classification, and detection of adjacent lanes (i.e., immediate left and right lanes) presence. In this paper, we propose a real-time Ego-Lane Analysis System (ELAS) capable of estimating ego-lane position, classifying LMTs and road markings, performing LDW and detecting lane change events. The proposed vision-based system works on a temporal sequence of images. Lane marking features are extracted in perspective and Inverse Perspective Mapping (IPM) images that are combined to increase robustness. The final estimated lane is modeled as a spline using a combination of methods (Hough lines with Kalman filter and spline with particle filter). Based on the estimated lane, all other events are detected.To validate ELAS and cover the lack of lane datasets in the literature, a new dataset with more than 20 different scenes (in more than 15,000 frames) and considering a variety of scenarios (urban road, highways, traffic, shadows, etc.) was created. The dataset was manually annotated and made publicly available to enable evaluation of several events that are of interest for the research community (i.e., lane estimation, change, and centering; road markings; intersections; LMTs; crosswalks and adjacent lanes). Moreover, the system was also validated quantitatively and qualitatively on other public datasets. ELAS achieved high detection rates in all real-world events and proved to be ready for real-time applications.

show abstract

Detecting symbols on road surface for mapping and localization using OCR

Cited by 10 publications

References 16 publications

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

Application of Microsoft Agent in Humanized Courseware

Ego-Lane Analysis System (ELAS): Dataset and algorithms

Contact Info

Product

Resources

About