東京大学 · Engineering
Deeksha Arya 교수의 연구실은 도로 손상 자동 감지 기술 개발을 핵심으로 하며, 특히 스마트폰 기반 캐리어를 활용한 저비용 도로 상태 모니터링 시스템을 연구하고 있습니다. 다국적 데이터 기반의 딥러닝 모델 개발과 함께, 데이터 공유의 어려움을 해결하기 위한 연합학습(Federated Learning) 기반의 분산 학습 기법을 적용하여 보다 보편적이고 개인정보를 고려한 모델 설계에 기여하고 있습니다. 특히, 다양한 국가의 도로 환경에 적합한 보편적 모델 개발과 실용적 응용을 목표로 하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
This data article provides details for the RDD2020 dataset comprising 26,336 road images from India, Japan, and the Czech Republic with more than 31,000 instances of road damage. The dataset captures four types of road damage: longitudinal cracks, transverse cracks, alligator cracks, and potholes; and is intended for developing deep learning-based methods to detect and classify road damage automatically. The images in RDD2020 were captured using vehicle-mounted smartphones, making it useful for
This paper summarizes the Global Road Damage Detection Challenge (GRDDC), a Big Data Cup organized as a part of the IEEE International Conference on Big Data’2020. The Big Data Cup challenges involve a released dataset and a well-defined problem with clear evaluation metrics. The challenges run on a data competition platform that maintains a leaderboard for the participants. In the presented case, the data constitute 26336 road images collected from India, Japan, and the Czech Republic to propos
Abstract The data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled
This paper summarizes the Crowdsensing-based Road Damage Detection Challenge (CRDDC), a Big Data Cup organized as a part of the IEEE International Conference on Big Data’2022. The Big Data Cup challenges involve a released dataset and a well-defined problem with clear evaluation metrics. The challenges run on a data competition platform that maintains a real-time online evaluation system for the participants. In the presented case, the data constitute 47,420 road images collected from India, Jap
Many municipalities and road authorities seek to implement automated evaluation of road damage. However, they often lack technology, know-how, and funds to afford state-of-the-art equipment for data collection and analysis of road damages. Although some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions. This work makes the following contributions i
Deep learning is widely used for road damage detection, but it requires extensive, diverse, and well-labeled data. Centralized model training can be difficult due to large data transfers, storage needs, and computational resources. Data privacy concerns can also hinder data sharing among clients, leaving them to train models on their own data, leading to less robust models. Federated learning (FL) addresses these problems by training models without data sharing, only exchanging model parameters
The RDD2020 dataset contains 26336 road images collected from India, Japan, and the Czech Republic with more than 31000 instances of road damage. The dataset contains annotation for four damage categories: Longitudinal Cracks(D00), Transverse Cracks(D10), Alligator Cracks(D20), and Potholes(D40); and is intended for developing deep learning-based methods to detect and classify road damage automatically. The images in RDD2020 were captured using vehicle-mounted smartphones, making it useful for m
Description The Road Damage Dataset, RDD2022, is released as a part of the Crowdsensing-based Road Damage Detection Challenge (CRDDC'2022), an IEEE BigData Cup. It comprises <strong>47,420 road images</strong> from six countries, <strong>Japan, India, the Czech Republic, Norway, the United States, and China. </strong> The images have been annotated with more than <strong>55,000</strong> instances of road damage. Four types of road damage, namely longitudinal cracks, transverse cracks, alligator
This paper summarizes the Optimized Road Damage Detection Challenge (ORDDC’2024), a Big Data Cup featured at the IEEE International Conference on Big Data 2024. Building on previous competitions, ORDDC’2024 aims to enhance the automatic detection and classification of road damage from images. It introduces two novel contributions: first, a standardized platform for model deployment that ensured consistent performance evaluation across all participants; second, an emphasis on inference speed as a
With the evolution of computing from using personal computers to use of online Internet of Things (IoT) services and applications, security risks have also evolved as a major concern. The use of Fog computing enhances reliability and availability of the online services due to enhanced heterogeneity and increased number of computing servers. However, security remains an open challenge. Various trust models have been proposed to measure the security strength of available service providers. We util
The doctoral work summarized here is an application of Artificial Intelligence (AI) for social good. The successful implementation would contribute towards low-cost, faster monitoring of road conditions across different nations, resulting in safer roads for everyone. Additionally, the study provides recommendations for re-using the road image data and the Deep Learning models released by any country for detecting road damage in other countries.
