Effectiveness of aerial and ISERV-ISS RGB photos for real-time urban floodwater mapping: case of Calgary 2013 flood

Zhang, Ying; Canisius, Francis; Zhen, Chuiqing; Feng, Boyu; Crawford, Peter; Huang, Lucia

doi:10.1117/1.jrs.13.044521

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, numerous studies focus on flash flood risk in spatial dimension rather than temporal. Thus, determining how to effectively integrate real-time information to establish a dynamic flash flood risk assessment model in the future is currently a hot issue (Adams et al, 2019, Shirisha et al, 2019, Zhang et al, 2019a, Zhang et al, 2019b. There is no doubt that flash flood assessment will be strengthened by collaboration with other disciplines, such as radar technology and remote sensing.…”

Section: Improvementmentioning

confidence: 99%

Assessment of flash flood risk based on improved analytic hierarchy process method and integrated maximum likelihood clustering algorithm

Lin

Chen

et al. 2020

Journal of Hydrology

119

View full text Add to dashboard Cite

Section: Improvementmentioning

confidence: 99%

Assessment of flash flood risk based on improved analytic hierarchy process method and integrated maximum likelihood clustering algorithm

Lin

Chen

et al. 2020

Journal of Hydrology

119

View full text Add to dashboard Cite

“…For real-time mapping of floodwater distribution, airborne imagery (including data from sensors mounted on both aircraft and unmanned aerial vehicles (UAVs)) has advantages over satellite optical data since its spatial resolution is typically higher [26], acquisition times can be flexible to provide data during critical times of the flood event, and acquisitions can be made from under cloud layers if necessary. Historically, aircraft are the primary sensor platform for acquisition.…”

Section: Introductionmentioning

confidence: 99%

Automated Extraction of Visible Floodwater in Dense Urban Areas from RGB Aerial Photos

Zhang

Crawford

2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Rapid response mapping of floodwater extents in urbanized areas, while essential for early damage assessment and rescue operations, also presents significant image interpretation challenges. Images from visible band (red–green–blue (RGB)) remote sensors are the most common and cost-effective for real-time applications. Based on an understanding of the differing characteristics of turbid floodwater and urban land surface classes, a robust method was developed and automatized to extract visible floodwater using RGB band digital numbers. The methodology was applied to delineate visible floodwater distribution from very high-resolution aerial image data acquired during the 2013 Calgary flood event. The methodology development involved segment- and pixel-based feature analysis, rule development, automated feature extraction, and result validation processing. The accuracies for the visible floodwater class were above 0.8394% and the overall accuracies were above 0.9668% at both pixel and segment levels for three test sites with diverse urban landscapes.

show abstract

“…A collection of studies for mapping floodwater have been explored using the data from various SAR sensors, such as ALOS-PALSAR [6], Sentinel-1 [7], Radarsat-2 [8], TerraSAR-X [5], and COSMO-SkyMed [9], reflecting the usefulness and activeness of this research field. On the other hand, due to the side-looking nature of such sensors, SAR data suffers from the effects of corner reflection [10], double bounce [11], layover, and shadowing [5], which still pose challenges to detecting floodwater in urban areas [12]. In the meantime, multispectral optical imagery from various satellite sensors such as Landsat [13], Sentinel-2 [14], PlanetScope [15], SPOT-5 [16], and Worldview-2 [17] is another widely used data source for flood mapping owing to its abundance of spectral information and global coverage.…”

mentioning

confidence: 99%

“…In light of the respective advantages of SAR and optical sensors, the integrated use of multitemporal [15], [20] and multimodal [19], [21] satellite data also gained attention recently, although some specific types of data may often be unavailable during floods [15] and image registration problems always exist [20]. Noteworthily, the aerial imagery from airplanes [12], [18] and, in recent years, unmanned aerial vehicles (UAVs) [2], [22] exhibited strengths in the aspects of very high spatial resolution and flexible acquisition time during disaster events [12], which can provide a critical profile of flooded areas insusceptible to cloud cover under complex This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ urban landscapes for emergency response [23].…”

mentioning

confidence: 99%

Enhancement of Urban Floodwater Mapping From Aerial Imagery With Dense Shadows via Semisupervised Learning

Wang

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Timely and accurate mapping of floodwater in urban areas from aerial imagery is critical to support emergency response and rescue work. However, massive shadows cast by buildings and trees over dense built-up urban areas can cause a significant underestimation of flood outcomes, and few studies for flood monitoring explore this in current state-of-the-art approaches. Meanwhile, recent deep learning (DL) algorithms have reported superior performance in flood mapping over conventional machine learning methods. Nevertheless, acquiring a large amount of training data remains challenging in the DL paradigm. In this study, to exploit the potential of the DL algorithm in detecting all visible (including shadowed and nonshadowed) floodwater with limited training samples from aerial imagery, we designed a modified fully convolutional network and combined it with a deep semisupervised learning framework integrating consistency regularization and RandMix strategy into the floodwater detection workflow. Besides, the testtime augmentation technique was leveraged to improve the model performance in the evaluation phase. Extensive experiments on the 2013 Calgary flood demonstrated the effectiveness of our approach on extracting visible floodwater in urban areas with dense shadows. Notably, our method could accurately detect more floodwater with a largely reduced number of labeled training samples, which is a considerable enhancement in the applicability and availability of DL algorithms for flood monitoring in densely shadowed urban areas.

show abstract

Effectiveness of aerial and ISERV-ISS RGB photos for real-time urban floodwater mapping: case of Calgary 2013 flood

Cited by 6 publications

References 26 publications

Assessment of flash flood risk based on improved analytic hierarchy process method and integrated maximum likelihood clustering algorithm

Assessment of flash flood risk based on improved analytic hierarchy process method and integrated maximum likelihood clustering algorithm

Automated Extraction of Visible Floodwater in Dense Urban Areas from RGB Aerial Photos

Enhancement of Urban Floodwater Mapping From Aerial Imagery With Dense Shadows via Semisupervised Learning

Contact Info

Product

Resources

About