A Large-scale Simulation Dataset: Boost the Detection Accuracy for Special Weather Conditions

Liu, Dongfang; Cui, Yiming; Cao, Zhiwen; Chen, Yingjie

doi:10.1109/ijcnn48605.2020.9206716

Cited by 22 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recognition of the particular micro-Doppler spectra [293] and multi-layer deep learning approaches [292] are used in pedestrian detection tasks in bad weather. Thermal datasets specifically targeting pedestrian [294] or large scale simulation dataset [291] are also being established to make sure that ADS can complete this essential job with the interruption of weather. While conventional Gaussian mixture probability hypothesis density filter based tracker is being utilized in deep learning vehicle tracking framework [297] to improve the performance, radar tracking [296] and color-based vision lane tracking system on unmarked roads [295] also show the robustness and can help ADS maintain functionalities while in adverse conditions even if they were not particularly designed for those conditions.…”

Section: Othersmentioning

confidence: 99%

See 1 more Smart Citation

Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey

Zhang¹,

Carballo²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automated Driving Systems (ADS) open up a new domain for the automotive industry and offer new possibilities for future transportation with higher efficiency and comfortable experiences. However, autonomous driving under adverse weather conditions has been the problem that keeps autonomous vehicles (AVs) from going to level 4 or higher autonomy for a long time. This paper assesses the influences and challenges that weather brings to ADS sensors in an analytic and statistical way, and surveys the solutions against inclement weather conditions. Stateof-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported. External auxiliary solutions like V2X technology, weather conditions coverage in currently available datasets, simulators, and experimental facilities with weather chambers are distinctly sorted out. By pointing out all kinds of major weather problems the autonomous driving field is currently facing, and reviewing both hardware and computer science solutions in recent years, this survey contributes a holistic overview on the obstacles and directions of ADS development in terms of adverse weather driving conditions.

show abstract

Section: Othersmentioning

confidence: 99%

“…Researchers collected weather data that are common in their area of living or use simulation [291] to build their own weather datasets. The University of Michigan collected four-season LiDAR data using a Segway robot on the campus at an early stage [327].…”

Section: Tools 101 Data Setsmentioning

confidence: 99%

Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey

Zhang¹,

Carballo²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Geo-localization is an important task in computer vision as it holds valuable potentials for applications such as autonomous driving [1] and robot navigation [2]. When working under the region with poor GPS signals, mobile agents require a supplementary localization for operation and geo-localization is a helpful addition to GPS [3].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Attention Fusion for Geo-Localization

Yan

Cui

Chen³

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geolocalization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: https://github.com/YanLiqi/HAF.

show abstract

“…Despite the existing performance gap to humans, deep-learning-based computer vision methods have become essential advancement of real-world systems. A particularly challenging and emerging application is autonomous driving, which requires system performance with extreme reliability [25,24,6,26]. However, leveraging the power of deep learning for autonomous driving is nontrivial, due to the lack of datasets.…”

Section: Introductionmentioning

confidence: 99%