HazardNet: Road Debris Detection by Augmentation of Synthetic Models
Not on the map. Why?
Abstract (arXiv)
We present an algorithm to detect unseen road debris using a small set of synthetic models. Early detection of road debris is critical for safe autonomous or assisted driving, yet the development of a robust road debris detection model has not been widely discussed. There are two main challenges to building a road debris detector: first, data collection of road debris is challenging since hazardous objects on the road are rare to encounter in real driving scenarios; second, the variability of road debris is broad, ranging from a very small brick to a large fallen tree. To overcome these challenges, we propose a novel approach to few-shot learning of road debris that uses semantic augmentation and domain randomization to augment real road images with synthetic models. We constrain the problem domain to uncommon objects on the road and allow the deep neural network, HazardNet, to learn the semantic meaning of road debris to eventually detect unseen road debris. Our results demonstrate that HazardNet is able to accurately detect real road debris when only trained on synthetic objects in augmented images.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 71 references that are in the map. First posted on arXiv 14 Mar 2023.
Builds on
54 of 71 references.
References · 54
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
- 2016Playing for Data: Ground Truth from Computer Gamescited by 816
- 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
- 2018Learning Dexterous In-Hand Manipulationcited by 643
- 2018Deep Visual Domain Adaptation: A Surveycited by 634
- 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
38 more
- 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
- 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
- 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
- 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
- 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
- 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
- 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
- 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
- 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
- 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
- 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
- 2018Zero-Shot Object Detectioncited by 189
- 2019Progressive Domain Adaptation for Object Detectioncited by 134
- 2020Exploring Categorical Regularization for Domain Adaptive Object Detectioncited by 130
- 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
- 2016Lost and Found: Detecting Small Road Hazards for Self-Driving Vehiclescited by 117
- 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 111
- 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
- 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
- 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
- 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
- 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75
- 2020Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detectioncited by 75
- 2017Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Taskcited by 66
- 2019Dont Even Look Once: Synthesizing Features for Zero-Shot Detectioncited by 58
- 2019Copy-and-Paste Networks for Deep Video Inpaintingcited by 57
- 2017On Pre-Trained Image Features and Synthetic Images for Deep Learningcited by 51
- 2017Synthesizing Training Data for Object Detection in Indoor Scenescited by 48
- 2018Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Conceptscited by 48
- 2018SPIGAN: Privileged Adversarial Learning from Simulationcited by 47
- 2018Effective Use of Synthetic Data for Urban Scene Semantic Segmentationcited by 41
- 2020Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Imagescited by 36
- 2018Zero-Shot Object Detection by Hybrid Region Embeddingcited by 32
- 2016Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modelingcited by 28
- 2018Zero-Shot Detectioncited by 27
- 2018Domain Randomization for Scene-Specific Car Detection and Pose Estimationcited by 23
- 2020Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Reviewcited by 20
- 2020Transferring and Regularizing Prediction for Semantic Segmentationcited by 17
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.