mlsanityData to 14 Oct 2026

Surround-View Cameras based Holistic Visual Perception for Automated Driving

arXiv 2206.05542 ↗First posted 11 Jun 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The formation of eyes led to the big bang of evolution. The dynamics changed from a primitive organism waiting for the food to come into contact for eating food being sought after by visual sensors. The human eye is one of the most sophisticated developments of evolution, but it still has defects. Humans have evolved a biological perception algorithm capable of driving cars, operating machinery, piloting aircraft, and navigating ships over millions of years. Automating these capabilities for computers is critical for various applications, including self-driving cars, augmented reality, and architectural surveying. Near-field visual perception in the context of self-driving cars can perceive the environment in a range of 0-10 meters and 360deg coverage around the vehicle. It is a critical decision-making component in the development of safer automated driving. Recent advances in computer vision and deep learning, in conjunction with high-quality sensors such as cameras and LiDARs, have fueled mature visual perception solutions. Until now, far-field perception has been the primary focus. Another significant issue is the limited processing power available for developing real-time applications. Because of this bottleneck, there is frequently a trade-off between performance and run-time efficiency. We concentrate on the following issues in order to address them: 1) Developing near-field perception algorithms with high performance and low computational complexity for various visual perception tasks such as geometric and semantic tasks using convolutional neural networks. 2) Using Multi-Task Learning to overcome computational bottlenecks by sharing initial convolutional layers between tasks and developing optimization strategies that balance tasks.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 48 of its 495 references that are in the map. First posted on arXiv 11 Jun 2022.

Builds on

48 of 495 references.

References · 48

  1. 2018YOLOv3: An Incremental Improvementcited by 2,659
  2. 2014Conditional Generative Adversarial Netscited by 2,162
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  4. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  5. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
  6. 2020Exploring Self-attention for Image Recognitioncited by 313
  7. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  8. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  9. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  10. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  11. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 144
  12. 2017DSSD : Deconvolutional Single Shot Detectorcited by 131
36 more
  1. 2017SfM-Net: Learning of Structure and Motion from Videocited by 89
  2. 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 63
  3. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 62
  4. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  5. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  6. 2017Houdini: Fooling Deep Structured Prediction Modelscited by 50
  7. 2020SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Drivingcited by 48
  8. 2017Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resizecited by 37
  9. 2019FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Drivingcited by 36
  10. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  11. 2014Generative Adversarial Networkscited by 33
  12. 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
  13. 2022SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Drivingcited by 32
  14. 2019A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D imagescited by 29
  15. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  16. 2019Challenges in Designing Datasets and Validation for Autonomous Drivingcited by 23
  17. 2020Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3cited by 22
  18. 2021Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learningcited by 20
  19. 2017UPSET and ANGRI : Breaking High Performance Image Classifierscited by 19
  20. 2018Monocular Fisheye Camera Depth Estimation Using Sparse LiDAR Supervisioncited by 19
  21. 2019FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Drivingcited by 18
  22. 2022Detecting Adversarial Perturbations in Multi-Task Perceptioncited by 15
  23. 2017Fast Scene Understanding for Autonomous Drivingcited by 14
  24. 2020Trained Trajectory based Automated Parking System using Visual SLAM on Surround View Camerascited by 14
  25. 2019Real-time Joint Object Detection and Semantic Segmentation Network for Automated Drivingcited by 12
  26. 2019Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Methodcited by 10
  27. 2018Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Losscited by 9
  28. 2019Feature Partitioning for Efficient Multi-Task Architecturescited by 9
  29. 2021An Online Learning System for Wireless Charging Alignment using Surround-view Fisheye Camerascited by 9
  30. 2018Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networkscited by 7
  31. 2016Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentationcited by 6
  32. 2019See More Than Once -- Kernel-Sharing Atrous Convolution for Semantic Segmentationcited by 6
  33. 20153D Reconstruction from Full-view Fisheye Cameracited by 5
  34. 2017Learning Universal Adversarial Perturbations with Generative Modelscited by 4
  35. 2019SoildNet: Soiling Degradation Detection in Autonomous Drivingcited by 4
  36. 2017Dense Transformer Networkscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023DarSwin: Distortion Aware Radial Swin Transformercited by 10
  2. 2024DarSwin-Unet: Distortion Aware Encoder-Decoder Architecturecited by 1