Near Real-time Map Building with Multi-class Image Set Labeling and Classification of Road Conditions Using Convolutional Neural Networks

Ramanna, Sheela; Sengoz, Cenker; Kehler, Scott; Pham, D.L.

doi:10.1080/08839514.2021.1935590

Cited by 14 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing approaches for weather and road condition estimation can be roughly categorized based on the acquisition setting (fixed vs. vehicle-mounted sensors), the sensor(s) used, and the algorithmic approaches (physics-based vs. data-driven). These tasks can be further approached from the viewpoint of automotive applications, which rely on one or more vehicle-mounted sensors 7,8,15 , or from the perspective of road infrastructure management, which relies instead on distributed, fixed sensors 6,13,14 . The present study falls in the latter group, on which we will focus our attention in the remainder of this section.…”

Section: Related Workmentioning

confidence: 99%

“…Outdoor and surveillance cameras provide a ready-to-use, scalable alternative, with minimal installation costs 6,9,16 . However, detecting road conditions from outdoor cameras is challenging, due to the large distance between the camera and the road surface, as well as the wide range of illumination conditions observed in the wild.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, frames need to be manually labelled as most cameras are located too far from RWIS stations. For this reason, semi-supervised techniques have been proposed to lower the cost associated to manual annotation 6 .…”

Section: Related Workmentioning

confidence: 99%

“…Deep learning-based techniques, such as CNNs, have proven to be a robust alternative in many related applications 6,7,14,15 . Unlike physics-based methods, they do not require calibrated camera sensors, and can be trained to achieve robustness to varying acquisition and illumination conditions, which is essential to effectively leverage existing camera networks.…”

Section: Related Workmentioning

confidence: 99%

“…Unlike physics-based methods, they do not require calibrated camera sensors, and can be trained to achieve robustness to varying acquisition and illumination conditions, which is essential to effectively leverage existing camera networks. The vast majority of existing works are based on fine-tuning a state-of-the-art CNN to perform a frame-by-frame classification, and do not take into account the temporal correlation between subsequent frames [6][7][8][13][14][15] .…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Self-supervised and semi-supervised learning for road condition estimation from distributed road-side cameras

Garcea

Blanco

Croci³

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Monitoring road conditions, e.g., water build-up due to intense rainfall, plays a fundamental role in ensuring road safety while increasing resilience to the effects of climate change. Distributed cameras provide an easy and affordable alternative to instrumented weather stations, enabling diffused and capillary road monitoring. Here, we propose a deep learning-based solution to automatically detect wet road events in continuous video streams acquired by road-side surveillance cameras. Our contribution is two-fold: first, we employ a convolutional Long Short-Term Memory model (convLSTM) to detect subtle changes in the road appearance, introducing a novel temporally consistent data augmentation to increase robustness to outdoor illumination conditions. Second, we present a contrastive self-supervised framework that is uniquely tailored to surveillance camera networks. The proposed technique was validated on a large-scale dataset comprising roughly 2000 full day sequences (roughly 400K video frames, of which 300K unlabelled), acquired from several road-side cameras over a span of two years. Experimental results show the effectiveness of self-supervised and semi-supervised learning, increasing the frame classification performance (measured by the Area under the ROC curve) from 0.86 to 0.92. From the standpoint of event detection, we show that incorporating temporal features through a convLSTM model both improves the detection rate of wet road events (+ 10%) and reduces false positive alarms ($$-$$ - 45%). The proposed techniques could benefit also other tasks related to weather analysis from road-side and vehicle-mounted cameras.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Self-supervised and semi-supervised learning for road condition estimation from distributed road-side cameras

Garcea

Blanco

Croci³

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Yuan

2021

Data Sci. Eng.

217

View full text Add to dashboard Cite

Intelligent transportation (e.g., intelligent traffic light) makes our travel more convenient and efficient. With the development of mobile Internet and position technologies, it is reasonable to collect spatio-temporal data and then leverage these data to achieve the goal of intelligent transportation, and here, traffic prediction plays an important role. In this paper, we provide a comprehensive survey on traffic prediction, which is from the spatio-temporal data layer to the intelligent transportation application layer. At first, we split the whole research scope into four parts from bottom to up, where the four parts are, respectively, spatio-temporal data, preprocessing, traffic prediction and traffic application. Later, we review existing work on the four parts. First, we summarize traffic data into five types according to their difference on spatial and temporal dimensions. Second, we focus on four significant data preprocessing techniques: map-matching, data cleaning, data storage and data compression. Third, we focus on three kinds of traffic prediction problems (i.e., classification, generation and estimation/forecasting). In particular, we summarize the challenges and discuss how existing methods address these challenges. Fourth, we list five typical traffic applications. Lastly, we provide emerging research challenges and opportunities. We believe that the survey can help the partitioners to understand existing traffic prediction problems and methods, which can further encourage them to solve their intelligent transportation applications.

show abstract

Recent computer vision applications for pavement distress and condition assessment

Hakea

Fakhr

2023

Automation in Construction

View full text Add to dashboard Cite

Near Real-time Map Building with Multi-class Image Set Labeling and Classification of Road Conditions Using Convolutional Neural Networks

Cited by 14 publications

References 34 publications

Self-supervised and semi-supervised learning for road condition estimation from distributed road-side cameras

Self-supervised and semi-supervised learning for road condition estimation from distributed road-side cameras

A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Recent computer vision applications for pavement distress and condition assessment

Contact Info

Product

Resources

About