Unsupervised person re-identification (ReID) has recently gained significant attention from researchers. ReID matches images of the same person from different camera views in various scenes without any labels. Existing clustering methods primarily rely on a fixed threshold (the maximum distance between sample points and clustering centroids) and overlook the importance of adjusting this threshold during continuous model optimization. This mismatch between clustering thresholds and inter- or intra-class spacing reduces clustering accuracy. To address this issue, this study proposes an Adaptive Clustering and Weighted Regularization Contrastive Learning (ACWRCL) framework for unsupervised person ReID. The ACWRCL framework comprises two main components: (1) the Clustering Threshold Adaptive Adjustment (CTAA) module, and (2) the Weighted Regularization Contrastive Learning (WRCL) module. The CTAA module dynamically adjusts the clustering threshold to align with model optimization, ensuring that the threshold remains within an appropriate range to prevent under- or over-robustness in the clustering model. The WRCL module uses the similarity ratio between the query sample and the clustering centroid relative to the overall similarity of all samples with the same labels as the query sample. This ratio is used as the weight in the loss function to penalize incorrect clustering and improve pseudo-label generation accuracy. Extensive experiments on public ReID datasets—Market-1501, MSMT17, Veri776, CUHK03, and PersonX—demonstrate the effectiveness of the proposed method.

Recently, deep learning-based intelligent vehicle control systems have played an important role in real-time road conditions assessment applications. It relies primarily on unmanned aerial vehicles (UAVs) for specific target retrieval, especially Cloth-Changing Person Re-identification (CC-ReID) technology, to provide support for road observations and environmental monitoring. Existing CC-ReID methods mainly focus on the invariant features of the front and rear views that are independent of clothing; among them, global color enhancement is a commonly used strategy. However, this method usually reduces the chromatism between the target foreground and background, which can easily lead to the loss of features unrelated to clothing and reduce the model's performance. To solve this problem, this paper proposes a data augmentation framework with Local Invariant Feature Transformation and Clothing Adversarial Parsing (LIFTCAP) for CC-ReID. The proposed framework is equipped with a Local Invariant Feature Transition (LIFT) module and a Clothes Adversarial Parsing (CAP) module. The former aims to extract invariant features for the same person with different clothes using the local transition manners. CAP is devoted to finding adversarial associations and parsing contour differences between clothing styles. Subsequently, a feature correlation strategy is alternately implemented between the two modules to complete the optimization procedure. Extensive experiments were conducted on the public CC-ReID datasets (LTCC and PRCC), demonstrating the superiority of our proposed method over the latest methods. Furthermore, our method achieved competitive performance, particularly on a surveillance video dataset (CCVID). In addition, based on the LIFTCAP strategy, the proposed algorithm can achieve a time efficiency as low as O(n) for detecting specific targets when deployed on a UAV server (Feisi X200) for real-time road conditions assessment and monitoring applications.

Cloth-changing Person Re-Identification (CC-ReID) is a challenging data modeling task that involves identifying specific pedestrians wearing different outfits. Existing methods primarily focus on altering clothing color and directly reconstructing appearance to extract features independent of the clothes. Real pedestrians differ in height, body shape, etc. Such methods are prone to losing the intrinsic information of the original sample (i.e., the person identity) owing to the absence of contextual phenomena (e.g., texture structure and local correlation), which decreases the recognition performance. To address this problem, we propose a framework called HPRNet, or ”Human Parsing Reconstruction with Non-Local Multi-Scale Perception Network,” which includes a non-local weighted multi-scale perception (NWMP) module and a parsing reconstruction exploration (PRE) module. In particular, the proposed NWMP module effectively captures the global receptive field of a sample and obtains a contextual correlation between non-neighboring pixels within the sample image. The PRE module was used to achieve a more accurate reconstruction of human body components with a clothing parsing model to better distinguish features related to or unrelated to clothes. Extensive experiments were conducted on CC-ReID public datasets (LTCC, PRCC, and CCVID) to demonstrate the effectiveness and competitiveness of the proposed method with state-of-the-art (SOTA) baselines for this complex modeling task.

Unsupervised person re-identification (Re-ID) has garnered significant attention because of its data-friendly nature, as it does not require labeled data. Existing approaches primarily address this challenge by employing feature-clustering techniques to generate pseudo-labels. In addition, camera-proxy-based methods have emerged because of their impressive ability to cluster sample identities. However, these methods often blur the distinctions between individuals within inter-camera views, which is crucial for effective person re-ID. To address this issue, this study introduces an inter-camera-identity-difference-based contrastive learning framework for unsupervised person Re-ID. The proposed framework comprises two key components: (1) a different sample cross-view close-range penalty module and (2) the same sample cross-view long-range constraint module. The former aims at penalizing excessive similarity among different subjects across inter-camera views, whereas the latter mitigates the challenge of excessive dissimilarity among the same subject across camera views. To validate the performance of our method, we conducted extensive experiments on three existing person Re-ID datasets (Market-1501, MSMT17, and PersonX). The results demonstrate the effectiveness of the proposed method, which shows a promising performance. The code is available at https://github.com/hooldylan/IIDCL .