构建大规模合成数据集，提升多视角人群计数与定位的评估真实性。
SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization
- 构建50个合成场景，支持最多1000人、多视角视频流。
- 提出新基线模型，在新数据集上性能全面超越现有方法。
- 助力真实场景迁移，推动实际应用落地。
现有多视角人群计数与定位方法通常在小场景、有限人数、视角和帧数的数据集上评估，导致模型易过拟合，评估不具代表性。为此，本文提出大规模合成基准数据集 SynMVCrowd，包含50个合成场景，涵盖大量多视角帧与摄像头视角，人群数量最高达1000人，更贴近真实大场景应用需求。同时，设计强健的多视角人群计数与定位基线模型，在 SynMVCrowd 上显著优于所有对比方法。进一步实验表明，借助该基准训练可有效提升模型在新真实场景中的域迁移能力。本研究推动多视角及单图像人群计数与定位向实际应用迈进。代码与数据已公开于：https://github.com/zqyq/SynMVCrowd。
原文摘要 · Abstract (English)
Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods impractical, as small datasets are easily overfit by these methods. To avoid these issues, 3DROM proposes a data augmentation method. Instead, in this paper, we propose a large synthetic benchmark, SynMVCrowd, for more practical evaluation and comparison of multi-view crowd counting and localization tasks. The SynMVCrowd benchmark consists of 50 synthetic scenes with a large number of multi-view frames and camera views and a much larger crowd number (up to 1000), which is more suitable for large-scene multi-view crowd vision tasks. Besides, we propose strong multi-view crowd localization and counting baselines that outperform all comparison methods on the new SynMVCrowd benchmark. Moreover, we prove that better domain transferring multi-view and single-image counting performance could be achieved with the aid of the benchmark on novel new real scenes. As a result, the proposed benchmark could advance the research for multi-view and single-image crowd counting and localization to more practical applications. The codes and datasets are here: https://github.com/zqyq/SynMVCrowd.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。