Embedding Deep Metric for Person Re-identification: A Study Against Large Variations

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)’s capability of feature extraction.

行人重识别（Person Re-identification）因姿态、光照、遮挡及拍摄视角存在显著差异而极具挑战性。尽管当前的卷积神经网络（Convolutional Neural Networks, CNN）具备特征提取能力，但受上述各类差异影响，行人数据在特征空间中呈现为高度弯曲的流形分布。