Incident and Traffic-Bottleneck Detection Algorithm in High-Resolution Remote Sensing Imagery

Kahaki, Seyed Mostafa Mousavi; Nordin, Jan; Ashtari, Amir Hossein

doi:10.5614/itbj.ict.2012.6.2.4

Cited by 6 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, we interpret these findings to predict that incidents within a mile upstream of key bottlenecks do not significantly change the traffic delay during a no-notice evacuation. These findings agree with previous traffic flow research [36,37] that minor traffic incidents upstream of bottlenecks cause insignificant impact.…”

Section: Figure 3 Incident Impact By Locationsupporting

confidence: 93%

The Impact of Traffic Incident Locations on a Metropolitan Evacuation

Bahaaldin¹,

Fries²,

Chowdhury³

2016

IJT

View full text Add to dashboard Cite

show abstract

Section: Figure 3 Incident Impact By Locationsupporting

confidence: 93%

The Impact of Traffic Incident Locations on a Metropolitan Evacuation

Bahaaldin¹,

Fries²,

Chowdhury³

2016

IJT

View full text Add to dashboard Cite

show abstract

“…The rails are intersected at point O 1 , and the sleepers are intersected at point O 2 . The Hough transform is a commonly used method for line detecting [41,42,43]. Here, we also used it to detect the two most significant straight rail lines and to determine their vanishing point O 1 .…”

Section: Methodsmentioning

confidence: 99%

High-Speed Railway Intruding Object Image Generating with Generative Adversarial Networks

Guo

Geng

Zhu

et al. 2019

Sensors

View full text Add to dashboard Cite

Foreign object intrusion is a great threat to high-speed railway safety operations. Accurate foreign object intrusion detection is particularly important. As a result of the lack of intruding foreign object samples during the operational period, artificially generated ones will greatly benefit the development of the detection methods. In this paper, we propose a novel method to generate railway intruding object images based on an improved conditional deep convolutional generative adversarial network (C-DCGAN). It consists of a generator and multi-scale discriminators. Loss function is also improved so as to generate samples with a high quality and authenticity. The generator is extracted in order to generate foreign object images from input semantic labels. We synthesize the generated objects to the railway scene. To make the generated objects more similar to real objects, on scale in different positions of a railway scene, a scale estimation algorithm based on the gauge constant is proposed. The experimental results on the railway intruding object dataset show that the proposed C-DCGAN model outperforms several state-of-the-art methods and achieves a higher quality (the pixel-wise accuracy, mean intersection-over-union (mIoU), and mean average precision (mAP) are 80.46%, 0.65, and 0.69, respectively) and diversity (the Fréchet-Inception Distance (FID) score is 26.87) of generated samples. The mIoU of the real-generated pedestrian pairs reaches 0.85, and indicates a higher scale of accuracy for the generated intruding objects in the railway scene.

show abstract

“…The proximity index, therefore, could be used to explore the nearness of transport facilities to any metric. This approach may be used alongside any spatial data gathered through various practices and research methodologies (e.g., sensor-based big data [58][59][60], remote sensing imagery [61][62][63]).…”

Section: Indices For Terminal Evaluationmentioning

confidence: 99%

Proximity Indexing of Public Transport Terminals in Metro Manila

2021

View full text Add to dashboard Cite

Despite the extensive transit network in Metro Manila, intermodal connections between public transportation services are still fragmented. In response, authorities proposed various multimodal transport terminals around the periphery of the metropolis. However, there is a need to understand how these proposed terminals will impact existing transportation infrastructure and services as well as the current travel demand. This paper proposes a method that quantifies the nearness of any subject to any metric of interest, or in this case, the location of the terminal based on its proximity to existing transit supply and demand at different points in the transport network. It involves a simple methodology that requires only the spatial distribution of relevant transport planning data (e.g., public transport services, public transport passenger activity). It was found that the spatial distribution of the transport terminals in the study area is more closely related to the transit supply. Using the same methodology, several potential locations in Metro Manila (e.g., central terminal, terminal along a major junction) were assessed to see whether these are viable sites for a multimodal terminal. One scenario configuration was found to be better integrated with where trips start and/or end, while another seemed to improve integration of the existing railways.

show abstract

Incident and Traffic-Bottleneck Detection Algorithm in High-Resolution Remote Sensing Imagery

Cited by 6 publications

References 32 publications

The Impact of Traffic Incident Locations on a Metropolitan Evacuation

The Impact of Traffic Incident Locations on a Metropolitan Evacuation

High-Speed Railway Intruding Object Image Generating with Generative Adversarial Networks

Proximity Indexing of Public Transport Terminals in Metro Manila

Contact Info

Product

Resources

About