arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.09162cs.CV
收藏

基于对齐和幻觉的部分人再认同

Partial Person Re-identification with Alignment and Hallucination

Imperial College London(帝国理工学院)

Sara Iodice, Krystian Mikolajczyk

摘要:

部分人重新识别涉及匹配行人帧,其中在对应图像中仅身体的一部分可见。这反映了实际的CCTV监控场景,其中通常无法获得完整的人视图。缺失的身体部位使比较非常具有挑战性,因为视图的显著未对准和不同比例。我们提出了部分匹配网络(PMN),它可以检测身体关节,对齐部分视图,并根据帧中的信息和人的学习模型对缺失的部分进行幻觉。然后将对齐和重建的视图组合成联合表示并用于匹配图像。我们评估了我们的方法,并在三个不同的数据集上与其他方法进行了比较,证明了显着的改进。

英文摘要:

Partial person re-identification involves matching pedestrian frames where only a part of a body is visible in corresponding images. This reflects practical CCTV surveillance scenario, where full person views are often not available. Missing body parts make the comparison very challenging due to significant misalignment and varying scale of the views. We propose Partial Matching Net (PMN) that detects body joints, aligns partial views and hallucinates the missing parts based on the information present in the frame and a learned model of a person. The aligned and reconstructed views are then combined into a joint representation and used for matching images. We evaluate our approach and compare to other methods on three different datasets, demonstrating significant improvements.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑