Localization in the Crowd with Topological Constraints
Localization in the Crowd with Topological Constraints
复制标题
DOI：
10.1609/aaai.v35i2.16170
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Shahira Abousamra;Minh Hoai;D. Samaras;Chao Chen
中科院分区：
文献类型：
--
作者：
Shahira Abousamra;Minh Hoai;D. Samaras;Chao Chen
我们解决了人群定位的问题，即，预测与拥挤场景中的人相对应的点。由于各种挑战，定位方法容易出现空间语义错误，即，预测同一个人内的多个点或在杂乱区域中折叠多个点。我们提出了一个拓扑方法针对这些语义错误。我们引入了一个拓扑约束，教模型的原因点的空间排列。为了加强这一约束，我们定义了持久性损失的持久性同源性理论的基础上。损失比较了似然图的地形景观和地面实况的拓扑。拓扑推理提高了定位算法的质量，特别是在杂乱区域附近。在多个公共基准测试中，我们的方法优于以前的本地化方法。此外，我们证明了我们的方法在提高人群计数任务的性能的潜力。
We address the problem of crowd localization, i.e., the prediction of dots corresponding to people in a crowded scene. Due to various challenges, a localization method is prone to spatial semantic errors, i.e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region. We propose a topological approach targeting these semantic errors. We introduce a topological constraint that teaches the model to reason about the spatial arrangement of dots. To enforce this constraint, we define a persistence loss based on the theory of persistent homology. The loss compares the topographic landscape of the likelihood map and the topology of the ground truth. Topological reasoning improves the quality of the localization algorithm especially near cluttered regions. On multiple public benchmarks, our method outperforms previous localization methods. Additionally, we demonstrate the potential of our method in improving the performance in the crowd counting task.