RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes

Jin, Jiongchao; Fatemi, Arezou; Lira, Wallace; Yu, Feng; Leng, Biao; Ma, Rui; Mahdavi-Amiri, Ali; Zhang, Hao

doi:10.1109/iccvw54120.2021.00330

Cited by 16 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [ 31 ] presented a novel image transformation algorithm capable of adding or removing rain-induced artifacts, simulating driving scenarios in transitioning from clear to rainy weather. However, this dataset lacked image interference caused by raindrops on car windshields and could not quantify the adjustments to different raindrop parameters, somewhat limiting its functionality.…”

Section: Related Workmentioning

confidence: 99%

Development of an Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

Hsiang,

Chen

2024

Sensors

View full text Add to dashboard Cite

Given that sensor-based perception systems are utilized in autonomous vehicle applications, it is essential to validate such systems to ensure their robustness before they are deployed. In this study, we propose a comprehensive simulation-based process to verify and enhance the robustness of sensor-based perception systems in relation to corruption. Firstly, we introduce a methodology and scenario-based corruption generation tool for creating a variety of simulated test scenarios. These scenarios can effectively mimic real-world traffic environments, with a focus on corruption types that are related to safety concerns. An effective corruption similarity filtering algorithm is then proposed to eliminate corruption types with high similarity and identify representative corruption types that encompass all considered corruption types. As a result, we can create efficient test scenarios for corruption-related robustness with reduced testing time and comprehensive scenario coverage. Subsequently, we conduct vulnerability analysis on object detection models to identify weaknesses and create an effective training dataset for enhancing model vulnerability. This improves the object detection models’ tolerance to weather and noise-related corruptions, ultimately enhancing the robustness of the perception system. We use case studies to demonstrate the feasibility and effectiveness of the proposed procedures for verifying and enhancing robustness. Furthermore, we investigate the impact of various “similarity overlap threshold” parameter settings on scenario coverage, effectiveness, scenario complexity (size of training and testing datasets), and time costs.

show abstract

Section: Related Workmentioning

confidence: 99%

Development of an Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

Hsiang,

Chen

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The model parameters and performance are directly determined by the rainy image quality, especially in data‐driven methodologies. In contrast to general image annotation, manually labelling raindrops in images is nearly impossible due to their small size and scattered distributions (Jin et al, 2021). Therefore, rainy and rain‐free image pairs are intractable to obtain.…”

Section: Challenges In Video‐based Rainfall Monitoringmentioning

confidence: 99%

A review of video‐based rainfall measurement methods

Yan

Chen

et al. 2023

WIREs Water

View full text Add to dashboard Cite

Accurate and high spatiotemporal resolution rainfall observations are essential for hydrological forecasting and flood management, especially in urban hydrological applications. However, it is difficult for traditional rainfall gauges, weather radars, and satellites to accurately estimate rainfall while simultaneously capturing the spatial and temporal variability of rainfall well. In this context, video‐based rainfall measurement, a novel method, has the advantages of real‐time performance and low cost and may thus provide a new way to establish rainfall observation networks with high spatial and temporal resolution. In recent years, different algorithms have been developed to recognize raindrops and estimate rainfall from rainfall videos. It has been demonstrated that video‐based rainfall measurement methods can provide comprehensive rainfall information with fine spatial and temporal granularity. However, raindrop visibility and the depth of field effects are difficult to address. The motion blur effect of raindrops may result in substantial errors and uncertainties. A fundamental problem of video‐based rainfall measurements lies in locating raindrops and accurately calculating their actual size. Moreover, the effectiveness of deep learning‐based video rainfall measurement models is greatly influenced by the diversity of the training data. Therefore, enhancing the high robustness and accuracy of video‐based rainfall measurement algorithms and increasing the computational efficiency are paramount to further development, which are prerequisites for their application in practical rainfall monitoring and developing multicamera monitoring networks.This article is categorized under: Science of Water > Methods Science of Water > Hydrological Processes

show abstract

“…Reference [30] makes a contribution by introducing a dedicated dataset for rainy road street scene images. The images include distortions caused by water droplets on camera lenses, as well as visual interference from fog and road reflections.…”

Section: Related Workmentioning

confidence: 99%

Development of An Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

Hsiang,

Chen

2023

Preprint

View full text Add to dashboard Cite

Since sensor-based perception systems are used in autonomous vehicle applications, validating such systems is imperative to guarantee the robustness of the systems before they are being put to use. In this study, a comprehensive corruption-related simulation-based robustness verification and enhancement process for sensor-based perception systems is proposed. Firstly, we present a methodology and scenario-based corruption generation tools for creating diverse simulated test scenarios that can analogously represent real-world traffic environments, especially considering corruption types related to safety concern. Then, an effective corruption similarity filtering algorithm is proposed to remove corruption types with high similarity and identify the representative corruption types to represent all considered corruption types. As a result, we can generate efficient corruption-related robustness test scenarios with less testing time and good scenario coverage. Subsequently, we perform the vulnerability analysis of object detection models to identify model weaknesses and construct an effective training dataset for model vulnerability enhancement. This enhances the tolerance of object detection models to weather and noise-related corruptions, ultimately improving the robustness of the perception system. We employ case studies to demonstrate the feasibility and effectiveness of the proposed robustness verification and enhancement procedures. Additionally, we explore the impact of different "similarity overlap threshold" parameter settings on scenario coverage, effectiveness, scenario complexity (size of training and testing datasets), and time costs.

show abstract

RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes

Cited by 16 publications

References 40 publications

Development of an Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

Development of an Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

A review of video‐based rainfall measurement methods

Development of An Effective Corruption-Related Scenario-Based Testing Approach for Robustness Verification and Enhancement of Perception Systems in Autonomous Driving

Contact Info

Product

Resources

About