Evaluation of Video Coding for Machines Without Ground Truth

Fischer K, Hofbauer M, Kuhn C, Steinbach E, Kaup A (2022)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2022

Event location: Singapore SG

URI: https://arxiv.org/abs/2205.06519

DOI: 10.1109/ICASSP43922.2022.9747633

Open Access Link: https://arxiv.org/abs/2205.06519

Abstract

In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annota-tions are required for a comprehensive evaluation. However, existing video datasets with detailed annotations are severely limited in size and video quality. Thus, current methods have to either evaluate their codecs on still images or on already compressed data. To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines. Through extensive evaluation, this paper shows that the proposed ground-truth-agnostic evaluation method results in an acceptable absolute measurement error below 0.7 percentage points on the Bjøntegaard Delta Rate compared to using the true ground truth for midrange bitrates. We evaluate on the three tasks of semantic segmentation, instance segmentation, and object detection. Lastly, we utilize the  ground-truth-agnostic method to measure the coding performances of the VVC compared against HEVC on the Cityscapes sequences. This reveals that the coding position has a significant influence on the task performance.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Fischer, K., Hofbauer, M., Kuhn, C., Steinbach, E., & Kaup, A. (2022). Evaluation of Video Coding for Machines Without Ground Truth. In Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, SG.

MLA:

Fischer, Kristian, et al. "Evaluation of Video Coding for Machines Without Ground Truth." Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore 2022.

BibTeX: Download