Exploring Self-Supervised Vision Transformers for Gait Recognition in the Wild.

The manner of walking (gait) is a powerful biometric that is used as a unique fingerprinting method, allowing unobtrusive behavioral analytics to be performed at a distance without subject cooperation. As opposed to more traditional biometric authentication methods, gait analysis does not require explicit cooperation of the subject and can be performed in low-resolution settings, without requiring the subject's face to be unobstructed/clearly visible. Most current approaches are developed in a controlled setting, with clean, gold-standard annotated data, which powered the development of neural architectures for recognition and classification. Only recently has gait analysis ventured into using more diverse, large-scale, and realistic datasets to pretrained networks in a self-supervised manner. Self-supervised training regime enables learning diverse and robust gait representations without expensive manual human annotations. Prompted by the ubiquitous use of the transformer model in all areas of deep learning, including computer vision, in this work, we explore the use of five different vision transformer architectures directly applied to self-supervised gait recognition. We adapt and pretrain the simple ViT, CaiT, CrossFormer, Token2Token, and TwinsSVT on two different large-scale gait datasets: GREW and DenseGait. We provide extensive results for zero-shot and fine-tuning on two benchmark gait recognition datasets, CASIA-B and FVG, and explore the relationship between the amount of spatial and temporal gait information used by the visual transformer. Our results show that in designing transformer models for processing motion, using a hierarchical approach (i.e., CrossFormer models) on finer-grained movement fairs comparatively better than previous whole-skeleton approaches.

Learning Gait Representations with Noisy Multi-Task Learning.

Gait analysis is proven to be a reliable way to perform person identification without relying on subject cooperation. Walking is a biometric that does not significantly change in short periods of time and can be regarded as unique to each person. So far, the study of gait analysis focused mostly on identification and demographics estimation, without considering many of the pedestrian attributes that appearance-based methods rely on. In this work, alongside gait-based person identification, we explore pedestrian attribute identification solely from movement patterns. We propose DenseGait, the largest dataset for pretraining gait analysis systems containing 217 K anonymized tracklets, annotated automatically with 42 appearance attributes. DenseGait is constructed by automatically processing video streams and offers the full array of gait covariates present in the real world. We make the dataset available to the research community. Additionally, we propose GaitFormer, a transformer-based model that after pretraining in a multi-task fashion on DenseGait, achieves 92.5% accuracy on CASIA-B and 85.33% on FVG, without utilizing any manually annotated data. This corresponds to a +14.2% and +9.67% accuracy increase compared to similar methods. Moreover, GaitFormer is able to accurately identify gender information and a multitude of appearance attributes utilizing only movement patterns. The code to reproduce the experiments is made publicly.

WildGait: Learning Gait Representations from Raw Surveillance Streams.

The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a self-supervised learning framework, WildGait, which consists of pre-training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world surveillance streams to learn useful gait signatures. We collected and compiled the largest pretraining dataset to date of anonymized walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We make the dataset available to the research community. Our results surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data.

Chemical modeling of groundwater quality in the aquifer of Seini town - Someș Plain, Northwestern Romania.

This paper presented a groundwater quality monitoring in Seini town, North-West of Romania, by assessing 18 physicochemical parameters (pH, EC, COD, turbidity, ht, NH4+, NO2-, NO3-, Cl-, Al, Fe, Mn, Pb, Zn, Cd, Cr, Ni and As) from 12 private dug wells and 5 private drilled wells, each with unique characteristics and used as a drinking water source. The pollution, quality status and risk assessment of drinking water sources were assessed, by pollution, quality and risk indices. Statistical methodology and cluster analysis were applied in order to elaborate and improve upon a mathematical model. 2 D and 3 D mathematical models were elaborated to show the functions that better describe the dependence between a set of physicochemical parameters. Heavy metal pollution index (HPI) and heavy metal evaluation index (HEI) results indicated that the studied drinking water sources presented no heavy metal contamination. Human health risk assessment indices showed that the consumption of studied waters presented no non-carcinogenic risk at heavy metals, but potential non-carcinogenic risk at NO3-. The water quality index (WQI) classifies the majority of samples as waters with excellent quality and the minority of samples in waters with poor and very poor quality. By geostatistical techniques, the spatial patterns of the main physicochemical indicators were established for both the surface of the aquifer and its depth. The aim of the water quality study was to establish the toxicity degree of water, its influence on human health and to inform the population regarding the use of individual water sources.