mlsanityData to 7 Oct 2026

Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks

arXiv 2403.16338 ↗First posted 25 Mar 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous driving systems require extensive data collection schemes to cover the diverse scenarios needed for building a robust and safe system. The data volumes are in the order of Exabytes and have to be stored for a long period of time (i.e., more than 10 years of the vehicle's life cycle). Lossless compression doesn't provide sufficient compression ratios, hence, lossy video compression has been explored. It is essential to prove that lossy video compression artifacts do not impact the performance of the perception algorithms. However, there is limited work in this area to provide a solid conclusion. In particular, there is no such work for fisheye cameras, which have high radial distortion and where compression may have higher artifacts. Fisheye cameras are commonly used in automotive systems for 3D object detection task. In this work, we provide the first analysis of the impact of standard video compression codecs on wide FOV fisheye camera images. We demonstrate that the achievable compression with negligible impact depends on the dataset and temporal prediction of the video codec. We propose a radial distortion-aware zonal metric to evaluate the performance of artifacts in fisheye images. In addition, we present a novel method for estimating affine mode parameters of the latest VVC codec, and suggest some areas for improvement in video codecs for the application to fisheye imagery.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

19 of 35 references.

References · 19

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  3. 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 41
  4. 2020Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systemscited by 34
  5. 2022Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challengescited by 33
  6. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  7. 2021Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Camerascited by 24
  8. 2020Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baselinecited by 21
  9. 2023FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detectioncited by 21
  10. 2021Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learningcited by 20
  11. 2021BEVDetNet: Bird's Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Drivingcited by 17
  12. 2020Trained Trajectory based Automated Parking System using Visual SLAM on Surround View Camerascited by 14
7 more
  1. 2019Real-time Joint Object Detection and Semantic Segmentation Network for Automated Drivingcited by 12
  2. 2019Optical Flow augmented Semantic Segmentation networks for Automated Drivingcited by 11
  3. 2019NeurAll: Towards a Unified Visual Perception Model for Automated Drivingcited by 11
  4. 2020On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architecturescited by 11
  5. 2019Capsule Neural Network based Height Classification using Low-Cost Automotive Ultrasonic Sensorscited by 5
  6. 2022Does Video Compression Impact Tracking Accuracy?cited by 4
  7. 2022Robust Deep Neural Object Detection and Segmentation for Automotive Driving Scenario with Compressed Image Datacited by 1

Built on by

Not cited yet.