Deep Intersection Classification Using First and Third Person Views

Takeda, Koji; Kanji, Tanaka

doi:10.1109/ivs.2019.8813859

Cited by 13 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, the most suitable comparisons concerning the work in [6] are those that consider sequences starting from 20m up to the intersection, see Figure 7a. A second comparison can be made with the results of [17]. In both cases, our approach improved the performances of these contributions.…”

Section: B Evaluation Methods and Resultsmentioning

confidence: 91%

“…Works in this category include the approach in [16] with a network called IntersectNet, where a sequence of 16 images was passed through an ensemble of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), combined to set up a three-types intersection classifier (four road-crossing and T-junctions) using a simple average-pooling fusion layer. A similar ensemble coupled with a more elaborated integration network was used in the work proposed in [17]. Here the authors suggest to use two sets of images relative to the intersection processed with DNN and RNN respectively.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Model Guided Road Intersection Classification

Ballardini,

Hernández,

Sotelo

2021

Preprint

View full text Add to dashboard Cite

Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable number of traffic accidents and fatalities. Detecting and understanding the scene configuration of these usually crowded areas is then of extreme importance for both autonomous vehicles and modern Advanced Driver Assistance Systems (ADAS) aimed at preventing road crashes and increasing the safety of vulnerable road users. This work investigates intersection classification from RGB images using well-consolidate neural network approaches along with a method to enhance the results based on the teacher/student training paradigm. An extensive experimental activity aimed at identifying the best input configuration and evaluating different network parameters on both the well-known KITTI dataset and the new KITTI-360 sequences shows that our method outperforms current state-of-the-art approaches on a per-frame basis and prove the effectiveness of the proposed learning scheme.

show abstract

Section: B Evaluation Methods and Resultsmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 99%

Model Guided Road Intersection Classification

Ballardini,

Hernández,

Sotelo

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…They were able to recognize six types of intersections. Koji and Kanji [ 93 ] used two types of input. First, they used images before an intersection of Third-Person Vision (TPV) and sequences of images while an intersection is passed First-person vision (FPV).…”

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

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

“…Together with the KITTI dataset, our proposal address this issue, as we believe that much more data and research is needed in this field. The work presented in [ 23 ] maintains a similar approach about temporal integration, but instead of detecting whether the intersection is reached, it tries to classify them into seven basic typologies. For this purpose, their system uses two data sources that the authors called Input-F and Input-T. Input-T is an RGB image taken just before reaching the intersection, and Input-F is a sequence of images taken while crossing the intersection.…”

Section: Related Workwordmentioning

confidence: 99%

Urban Intersection Classification: A Comparative Analysis

Ballardini

Hernández

Carrasco

et al. 2021

Sensors

View full text Add to dashboard Cite

Understanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on the detection and classification of urban intersections as seen from onboard front-facing cameras. Different methodologies aimed at classifying intersection geometries have been assessed to provide a comprehensive evaluation of state-of-the-art techniques based on Deep Neural Network (DNN) approaches, including single-frame approaches and temporal integration schemes. A detailed analysis of most popular datasets previously used for the application together with a comparison with ad hoc recorded sequences revealed that the performances strongly depend on the field of view of the camera rather than other characteristics or temporal-integrating techniques. Due to the scarcity of training data, a new dataset is created by performing data augmentation from real-world data through a Generative Adversarial Network (GAN) to increase generalizability as well as to test the influence of data quality. Despite being in the relatively early stages, mainly due to the lack of intersection datasets oriented to the problem, an extensive experimental activity has been performed to analyze the individual performance of each proposed systems.

show abstract

Deep Intersection Classification Using First and Third Person Views

Cited by 13 publications

References 43 publications

Model Guided Road Intersection Classification

Model Guided Road Intersection Classification

A Systematic Review of Urban Navigation Systems for Visually Impaired People

Urban Intersection Classification: A Comparative Analysis

Contact Info

Product

Resources

About