Person re-identification is an important task in forensics applications. Most existing person re-identification methods focus on matching persons captured by different true-color cameras. In practice, the captured pedestrian videos may be grayscale in some cases due to camera malfunction or special treatment for gray mode. In these cases, the person re-identification between true-color and grayscale pedestrian videos, which we call color to gray video person re-identification (CGVPR), will be needed. Since the color information that is very important to represent a pedestrian is usually intensity information and monochrome in grayscale videos, the CGVPR problem is very challenging. To relieve the difficulties in CGVPR, we propose an asymmetric within-video projection based Semicoupled Dictionary Pair Learning (SDPL) approach. SDPL simultaneously learns two within-video projection matrices, a pair of true-color and grayscale dictionaries, as well as a semi-coupled mapping matrix. The learned within-video projection matrices can make each video (true-color or grayscale) more compact. The learned dictionary pair and the mapping matrix can work together to bridge the gap between features of true-color and grayscale videos. To date there exists no true-color and grayscale pedestrian video dataset, so we contribute a new one, called true-color and grayscale video person re-identification dataset (CGVID). Our dataset is collected under a real-world scenario and consists of over 50K frames. Extensive evaluations demonstrate that the collected CGVID dataset is very challenging and can be used for further research on person re-identification. The experimental results show that our approach outperforms the compared methods on the CGVPR task.

Existing person re-identification methods usually directly calculate the similarities of person pictures regardless of their viewpoints. However, matching persons under different viewpoints is difficult since it is intrinsically hard to directly learn a representation which is geometrically invariant to large viewpoint variations. In this paper, we explicitly take viewpoint information into account and propose a novel Deep Residual Equivariant Mapping and Fine-grained Features (DREMFF) approach for viewpoint-robust person re-identification. Specifically, DREMFF hypothesizes that there exists inherent mapping between different viewpoints of a person, and consequently, the global representation discrepancy of a person under different viewpoints will be bridged through equivariant mapping by adaptively adding residuals to original representation according corresponding angle deviation. What's more, based on attention mechanism, DREMFF extracts fine-grained features for each image from multiple salient regions as well as different scales. These captured information is capable of providing assistant decision-making at lower granularities. The mapped global features and the learned fine-grained features work collaboratively to enable viewpoint-robust person re-identification. Experiments on three challenging benchmarks consistently demonstrate the effectiveness of the proposed approach.