mlsanityData to 14 Oct 2026

Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera

arXiv 2306.11822 ↗First posted 20 Jun 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Cutting-edge connected vehicle (CV) technologies have drawn much attention in recent years. The real-time traffic data captured by a CV can be shared with other CVs and data centers so as to open new possibilities for solving diverse transportation problems. However, imagery captured by onboard cameras in a connected environment, are not sufficiently investigated, especially for safety and health-oriented visual perception. In this paper, a bidirectional process of image synthesis and decomposition (BPISD) approach is proposed, and thus a novel self-supervised multi-task learning framework, to simultaneously estimate depth map, atmospheric visibility, airlight, and PM2.5 mass concentration, in which depth map and visibility are considered highly associated with traffic safety, while airlight and PM2.5 mass concentration are directly correlated with human health. Both the training and testing phases of the proposed system solely require a single image as input. Due to the innovative training pipeline, the depth estimation network can manage various levels of visibility conditions and overcome inherent problems in current image-synthesis-based depth estimation, thereby generating high-quality depth maps even in low-visibility situations and further benefiting accurate estimations of visibility, airlight, and PM2.5 mass concentration. Extensive experiments on the synthesized data from the KITTI and real-world data collected in Beijing demonstrate that the proposed method can (1) achieve performance competitive in depth estimation as compared with state-of-the-art methods when taking clear images as input; (2) predict vivid depth map for images contaminated by various levels of haze; and (3) accurately estimate visibility, airlight, and PM2.5 mass concentrations. Beneficial applications can be developed based on the presented work to improve traffic safety, air quality, and public health.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 95 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

40 of 95 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  7. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  8. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  9. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  10. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  11. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  12. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 314
28 more
  1. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  2. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  3. 2016Single-Image Depth Perception in the Wildcited by 180
  4. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  5. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  6. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  7. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  8. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  9. 2018Densely Connected Pyramid Dehazing Networkcited by 145
  10. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  11. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  12. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  13. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  14. 2018Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazingcited by 79
  15. 2018Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimationcited by 78
  16. 2017Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimationcited by 70
  17. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  18. 2017Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistencycited by 40
  19. 2016Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networkscited by 36
  20. 2019Unsupervised High-Resolution Depth Learning From Videos With Dual Networkscited by 26
  21. 2018GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networkscited by 21
  22. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  23. 2017Depth estimation using structured light flow -- analysis of projected pattern flow on an object's surface --cited by 9
  24. 2021Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priorscited by 8
  25. 2021Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videoscited by 7
  26. 2019SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networkscited by 5
  27. 2021DMRVisNet: Deep Multi-head Regression Network for Pixel-wise Visibility Estimation Under Foggy Weathercited by 5
  28. 2018Expressway visibility estimation based on image entropy and piecewise stationary time series analysiscited by 2

Built on by

Not cited yet.