Have i reached the intersection: A deep learning-based approach for intersection detection from monocular cameras

Bhatt, Dhaivat; Sodhi, Danish; Pal, Arghya; Balasubramanian, Vineeth N; Krishna, M. Ghanashyam

doi:10.1109/iros.2017.8206317

Cited by 28 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By analysing the various types of intersections, we found that there are 14 unique types of junctions. We also note that intersection detection task is discussed in several domains such as autonomous vehicles [ 84 ], driver assistance systems [ 85 ], and transformation of maps to digital datasets [ 86 ]. Although it is significant for navigation systems [ 7 ], it is not addressed in any of them.…”

Section: Environment Mappingmentioning

confidence: 99%

“…For BVIP, however, the type of intersection is also important, so this approach has limited use. Looking at the problem as a multi-classification intersection type problem, Bhatt et al [ 84 ] used CNN and LSTM networks to classify sequences of frames (video) into three classes non-intersection, a T-junction, a cross junction. Oeljeklaus et al [ 92 ] utilized a common encoder for semantic segmentation and recognition of road topology tasks.…”

Section: Environment Mappingmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Review of Urban Navigation Systems for Visually Impaired People

El-taher

Taha

Courtney

et al. 2021

Sensors

View full text Add to dashboard Cite

Blind and Visually impaired people (BVIP) face a range of practical difficulties when undertaking outdoor journeys as pedestrians. Over the past decade, a variety of assistive devices have been researched and developed to help BVIP navigate more safely and independently. In addition, research in overlapping domains are addressing the problem of automatic environment interpretation using computer vision and machine learning, particularly deep learning, approaches. Our aim in this article is to present a comprehensive review of research directly in, or relevant to, assistive outdoor navigation for BVIP. We breakdown the navigation area into a series of navigation phases and tasks. We then use this structure for our systematic review of research, analysing articles, methods, datasets and current limitations by task. We also provide an overview of commercial and non-commercial navigation applications targeted at BVIP. Our review contributes to the body of knowledge by providing a comprehensive, structured analysis of work in the domain, including the state of the art, and guidance on future directions. It will support both researchers and other stakeholders in the domain to establish an informed view of research progress.

show abstract

Section: Environment Mappingmentioning

confidence: 99%

Section: Environment Mappingmentioning

confidence: 99%

A Systematic Review of Urban Navigation Systems for Visually Impaired People

El-taher

Taha

Courtney

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…They used road boundaries and height profiles to determine the best match by a minimum goodness-of-fit measure. As the superiority of deep neural networks emerges, Bhatt et al [2] proposed an end-to-end Long-term Recursive Convolutional Network (LRCN) and considered intersection detection as a binary classification task on the frame sequence. In the work of Bhattacharyya et al [9], a method of spatial-temporal analysis of traffic conditions at urban intersections based on stereo vision and 3D digital maps was introduced.…”

Section: Intersection Detectionmentioning

confidence: 99%

“…Due to the importance of road intersections, recent studies have been focused on representation of intersections by exploiting recurrent sequences [2], producing HD maps [3], analysis of driving behavior at intersections by tracking strategies [4], or planning horizons [5]. However, this research either barely considers the intersection into larger designated areas or insufficiently uses vehicular sensors to re-identify the intersection in conjunction with the topological map.…”

Section: Introductionmentioning

confidence: 99%

Traffic Intersection Re-Identification Using Monocular Camera Sensors

Liu

Deng

Huang

et al. 2020

Sensors

View full text Add to dashboard Cite

Perception of road structures especially the traffic intersections by visual sensors is an essential task for automated driving. However, compared with intersection detection or visual place recognition, intersection re-identification (intersection re-ID) strongly affects driving behavior decisions with given routes, yet has long been neglected by researchers. This paper strives to explore intersection re-ID by a monocular camera sensor. We propose a Hybrid Double-Level re-identification approach which exploits two branches of Deep Convolutional Neural Network to accomplish multi-task including classification of intersection and its fine attributes, and global localization in topological maps. Furthermore, we propose a mixed loss training for the network to learn the similarity of two intersection images. As no public datasets are available for the intersection re-ID task, based on the work of RobotCar, we propose a new dataset with carefully-labeled intersection attributes, which is called “RobotCar Intersection” and covers more than 30,000 images of eight intersections in different seasons and day time. Additionally, we provide another dataset, called “Campus Intersection” consisting of panoramic images of eight intersections in a university campus to verify our updating strategy of topology map. Experimental results demonstrate that our proposed approach can achieve promising results in re-ID of both coarse road intersections and its global pose, and is well suited for updating and completion of topological maps.

show abstract

“…In [16], a road intersection detection module has been proposed as binary classification, using the Long-Term Recurrent Convolutional Network (LRCN) architecture to identify relative changes in outdoor features and eventually detecting intersections. In [17], the authors proposed an architecture that combines CNN, Bidirectional LSTM [16] and Siamese [18] style distance function learning for junction recognition in videos. In this work, the authors evaluated their approach on different data-sets spanning various experimental scenarios.…”

Section: A Background and Motivationmentioning

confidence: 99%

Unsupervised Learning for Subterranean Junction Recognition Based on 2D Point Cloud

Mansouri

Pourkamali-Anaraki

Arranz

et al. 2020

2020 28th Mediterranean Conference on Control and Automation (MED)

View full text Add to dashboard Cite

This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for high level mission planners to navigate an aerial platform in unknown areas or robot homing missions. The framework utilizes spectral clustering, which is capable of uncovering hidden structures from connected data points lying on non-linear manifolds. The spectral clustering algorithm computes a spectral embedding of the original 2D point cloud by utilizing the eigen decomposition of a matrix that is derived from the pairwise similarities of these points. We validate the developed framework using multiple data-sets, collected from multiple realistic simulations, as well as from real flights in underground environments, demonstrating the performance and merits of the proposed methodology.

show abstract

Have i reached the intersection: A deep learning-based approach for intersection detection from monocular cameras

Cited by 28 publications

References 10 publications

A Systematic Review of Urban Navigation Systems for Visually Impaired People

A Systematic Review of Urban Navigation Systems for Visually Impaired People

Traffic Intersection Re-Identification Using Monocular Camera Sensors

Unsupervised Learning for Subterranean Junction Recognition Based on 2D Point Cloud

Contact Info

Product

Resources

About