Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Abstract

Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets challenge of changing clothing. In this paper, we focus on handling well the CC-ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications. Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn clothagnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID. GI-ReID adopts a two-stream architecture that consists of a image ReID-Stream and an auxiliary gait recognition stream (Gait-Stream). The Gait-Stream, that is discarded in the inference for high computational efficiency, acts as a regulator to encourage the ReID-Stream to capture cloth-invariant biometric motion features during the training. To get temporal continuous motion cues from a single image, we design a Gait Sequence Prediction (GSP) module for Gait-Stream to enrich gait information. Finally, a high-level semantics consistency over two streams is enforced for effective knowledge regularization. Experiments on multiple image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts. Codes are available at https://github.com/jinx-USTC/GI-ReID

Clothes-Changing Person Re-identification with RGB Modality Only

“…HACNN [31], PCB [40], and IANet [20]) and six clothes-changing re-id methods (i.e. SPT+ASE [49], GI-ReID [28], CESD [35], RCSANet [25], 3DSL [6], and FSAM [18]) on LTCC and PRCC in Tab. 2.…”

“…To this end, [52,55] attempts to use disentangled representation learning to decouple appearance and structural information from RGB images, and considers structural information as clothes-irrelevant features. In contrast, other researchers attempt to use multi-modality information (e.g., skeletons [35], silhouettes [18,28], radio signals [7], contour sketches [49], or 3D shape [6]) to model body shape and extract clothesirrelevant features. However, the training of disentangled representation learning is time-consuming, and multimodality-based methods need additional models or equipment to extract multi-modality information.…”