用追踪实现相机陷阱图像中的动物计数，支持多物种识别与验证。
PuTR-CouT: Counting-by-Tracking in Camera-Trap Image Sequences
- 基于Transformer的关联机制，弱监督生成伪追踪标签进行序列计数。
- 在iWildCam 2021上性能优于改进版MaxBoxCount，支持多物种计数。
- 适用于需要个体数量估计的生态监测场景，可提供追踪轨迹验证。
相机陷阱图像中的物种识别已广泛研究，但物种丰度或密度估计等关键生态建模任务仍需个体计数。然而，多数数据集缺乏计数标注，且帧率低（通常~1帧/秒），使序列级追踪与计数尤为困难。本文提出PuTR-CouT，一种基于Transformer的追踪-计数框架，利用静态背景和短时爆发等结构先验，在弱监督下生成合成追踪数据以构建伪标签。该追踪器跨帧关联检测结果，用于物种级计数。同时，我们改进了iWildCam 2021挑战赛领先方案所用的MaxBoxCount启发式方法，创下当前最高得分记录。在iWildCam 2021基准测试中，PuTR-CouT表现媲美改进版MaxBoxCount，且具备多物种预测与轨迹级验证能力。
原文摘要 · Abstract (English)
Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation also require counting individual animals. However, the lack of counting labels in most datasets and low frame rates (typically ~1 frame per second) make sequence-level tracking and count estimation particularly challenging. In this work, we present PuTR-CouT, a counting-by-tracking framework built on a transformer-based learned association mechanism for sequence-level animal counting in camera trap images. To address the scarcity of annotated tracking data, we generate synthetic training data by exploiting structural priors, such as static backgrounds and short temporal bursts, to heuristically create pseudo-tracking labels in a weakly supervised manner. The resulting tracker associates detections across frames, using these tracks to estimate per-species counts. We also refine the MaxBoxCount heuristic used by the top solutions of the iWildCam 2021 challenge as a strong baseline, setting the highest score reported to date. When evaluated on the iWildCam 2021 benchmark, our framework PuTR-CouT delivers competitive counting results compared to the improved MaxBoxCount, with the added capability of multi-species predictions and track-level verification.
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。