SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments

Hu, Hanjiang; Yang, Banghua; Qiao, Zhijian; Zhao, Ding; Wang, Hesheng

doi:10.48550/arxiv.2011.04408

“…• We conduct extensive experiments to verify the effectiveness of our network structure and loss function. Experimental results [28] show that our method outperforms previous state-of-the-art methods on the KITTI dataset and our model generalizes well on the unseen SeasonDepth dataset [29] that contains multiple challenging environments without fine-tuning.…”

Section: Introductionmentioning

confidence: 79%

“…↓ means the lower the better while ↑ means the higher the better. Methods marked with ‡ indicate that the corresponding test results are taken from [29].…”

Section: Oursmentioning

confidence: 99%

See 1 more Smart Citation

Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving

Xiang¹,

Wang²,

An³

et al. 2022

Preprint

View full text Add to dashboard Cite

Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity issue. In this paper, we introduce a fully Visual Attention-based Depth (VADepth) network, where spatial attention and channel attention are applied to all stages. By continuously extracting the dependencies of features along the spatial and channel dimensions over a long distance, VADepth network can effectively preserve important details and suppress interfering features to better perceive the scene structure for more accurate depth estimates. In addition, we utilize geometric priors to form scale constraints for scale-aware model training. Specifically, we construct a novel scale-aware loss using the distance between the camera and a plane fitted by the ground points corresponding to the pixels of the rectangular area in the bottom middle of the image. Experimental results on the KITTI dataset show that this architecture achieves the state-of-theart performance and our method can directly output absolute depth without post-processing. Moreover, our experiments on the SeasonDepth dataset also demonstrate the robustness of our model to multiple unseen environments.

show abstract

“…are still prone to occlusion and are limited in their ability to detect distant objects [12]- [18]. Furthermore, the integration of automated vehicles into a mixed-autonomy transportation system, where they must interact with human-driven vehicles, pedestrians, complicated traffic rules, and various types of infrastructure, poses significant difficulties in making safe decisions [18]- [20]. These challenges remain a major obstacle to the large-scale deployment of automated driving technology in real-world scenarios.…”

Section: Introductionmentioning

confidence: 99%

The OpenCDA Open-Source Ecosystem for Cooperative Driving Automation Research

Xu

¹

,

Xiang

²

,

Han

³

et al. 2023

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Advances in Single-vehicle intelligence of automated driving has encountered great challenges because of limited capabilities in perception and interaction with complex traffic environments. Cooperative Driving Automation (CDA) has been considered a pivotal solution to next-generation automated driving and smart transportation. Though CDA has attracted much attention from both academia and industry, exploration of its potential is still in its infancy. In industry, companies tend to build their in-house data collection pipeline and research tools to tailor their needs and protect intellectual properties. Reinventing the wheels, however, wastes resources and limits the generalizability of the developed approaches since no standardized benchmarks exist. On the other hand, in academia, due to the absence of real-world traffic data and computation resources, researchers often investigate CDA topics in simplified and mostly simulated environments, restricting the possibility of scaling the research outputs to real-world scenarios. Therefore, there is an urgent need to establish an open-source ecosystem (OSE) to address the demands of different communities for CDA research, particularly in the early exploratory research stages, and provide the bridge to ensure an integrated development and testing pipeline that diverse communities can share. In this paper, we introduce the OpenCDA research ecosystem, a unified OSE integrated with a model zoo, a suite of driving simulators at various resolutions, large-scale real-world and simulated datasets, complete development toolkits for benchmark training/testing, and a scenario database/generator. We also demonstrate the effectiveness of OpenCDA OSE through example use cases, including cooperative 3D LiDAR detection, cooperative merge, cooperative camerabased map prediction, and adversarial scenario generation.

show abstract

“…of automated vehicles into a mixed-autonomy transportation system, where they must interact with human-driven vehicles, pedestrians, complicated traffic rules, and various types of infrastructure, poses significant difficulties in making safe decisions [16]- [18]. These challenges remain a major obstacle to the large-scale deployment of automated driving technology in real-world scenarios.…”

mentioning

confidence: 99%

The OpenCDA Open-source Ecosystem for Cooperative Driving Automation Research

Xu¹,

Xiang²,

Han³

et al. 2023

Preprint

View full text Add to dashboard Cite

Advances in Single-vehicle intelligence of automated driving has encountered great challenges because of limited capabilities in perception and interaction with complex traffic environments. Cooperative Driving Automation (CDA) has been considered a pivotal solution to next-generation automated driving and smart transportation. Though CDA has attracted much attention from both academia and industry, exploration of its potential is still in its infancy. In industry, companies tend to build their in-house data collection pipeline and research tools to tailor their needs and protect intellectual properties. Reinventing the wheels, however, wastes resources and limits the generalizability of the developed approaches since no standardized benchmarks exist. On the other hand, in academia, due to the absence of real-world traffic data and computation resources, researchers often investigate CDA topics in simplified and mostly simulated environments, restricting the possibility of scaling the research outputs to real-world scenarios. Therefore, there is an urgent need to establish an open-source ecosystem (OSE) to address the demands of different communities for CDA research, particularly in the early exploratory research stages, and provide the bridge to ensure an integrated development and testing pipeline that diverse communities can share. In this paper, we introduce the OpenCDA research ecosystem, a unified OSE integrated with a model zoo, a suite of driving simulators at various resolutions, large-scale real-world and simulated datasets, complete development toolkits for benchmark training/testing, and a scenario database/generator. We also demonstrate the effectiveness of OpenCDA OSE through example use cases, including cooperative 3D LiDAR detection, cooperative merge, cooperative camerabased map prediction, and adversarial scenario generation.

show abstract

SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments

Cited by 3 publications

References 67 publications

Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving

Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving

The OpenCDA Open-Source Ecosystem for Cooperative Driving Automation Research

The OpenCDA Open-source Ecosystem for Cooperative Driving Automation Research

Contact Info

Product

Resources

About