Parallax Inference for Robust Temporal Monocular Depth Estimation in Unstructured Environments.

Estimating the distance to objects is crucial for autonomous vehicles, but cost, weight or power constraints sometimes prevent the use of dedicated depth sensors. In this case, the distance has to be estimated from on-board mounted RGB cameras, which is a complex task especially for environments such as natural outdoor landscapes. In this paper, we present a new depth estimation method suitable for use in such landscapes. First, we establish a bijective relationship between depth and the visual parallax of two consecutive frames and show how to exploit it to perform motion-invariant pixel-wise depth estimation. Then, we detail our architecture which is based on a pyramidal convolutional neural network where each level refines an input parallax map estimate by using two customized cost volumes. We use these cost volumes to leverage the visual spatio-temporal constraints imposed by motion and make the network robust for varied scenes. We benchmarked our approach both in test and generalization modes on public datasets featuring synthetic camera trajectories recorded in a wide variety of outdoor scenes. Results show that our network outperforms the state of the art on these datasets, while also performing well on a standard depth estimation benchmark.

An anonymised longitudinal GPS location dataset to understand changes in activity-travel behaviour between pre- and post-COVID periods.

Collecting GPS data using mobile devices is essential to understanding human mobility. However, getting this type of data is tricky because of some specific features of mobile operating systems, the high-power consumption of mobile devices, and users' privacy concerns. Therefore, data of this kind are rarely publicly available for scientific purposes, while private companies that own the data are often reluctant to share it. Here we present a large anonymous longitudinal dataset of Activity Point Location (APL) generated from mobile devices' GPS tracking. The GPS data were collected by using the Google Location History (GLH), accessible in the Google Maps application. Our dataset, named AnLoCOV hereafter, includes anonymised data from 338 persons with corresponding socio-demographics over approximately ten years (2012-2022), thus covering pre- and post-COVID periods, and calculates over 2 million weekly-classified APL extracted from approximately 16 million GPS tracking points in Ecuador. Furthermore, we made our models publicly available to enable advanced analysis of human mobility and activity spaces based on the collected datasets.

Scaling up SoccerNet with multi-view spatial localization and re-identification.

Soccer videos are a rich playground for computer vision, involving many elements, such as players, lines, and specific objects. Hence, to capture the richness of this sport and allow for fine automated analyses, we release SoccerNet-v3, a major extension of the SoccerNet dataset, providing a wide variety of spatial annotations and cross-view correspondences. SoccerNet's broadcast videos contain replays of important actions, allowing us to retrieve a same action from different viewpoints. We annotate those live and replay action frames showing same moments with exhaustive local information. Specifically, we label lines, goal parts, players, referees, teams, salient objects, jersey numbers, and we establish player correspondences between the views. This yields 1,324,732 annotations on 33,986 soccer images, making SoccerNet-v3 the largest dataset for multi-view soccer analysis. Derived tasks may benefit from these annotations, like camera calibration, player localization, team discrimination and multi-view re-identification, which can further sustain practical applications in augmented reality and soccer analytics. Finally, we provide Python codes to easily download our data and access our annotations.

Survey and Synthesis of State of the Art in Driver Monitoring.

Road vehicle accidents are mostly due to human errors, and many such accidents could be avoided by continuously monitoring the driver. Driver monitoring (DM) is a topic of growing interest in the automotive industry, and it will remain relevant for all vehicles that are not fully autonomous, and thus for decades for the average vehicle owner. The present paper focuses on the first step of DM, which consists of characterizing the state of the driver. Since DM will be increasingly linked to driving automation (DA), this paper presents a clear view of the role of DM at each of the six SAE levels of DA. This paper surveys the state of the art of DM, and then synthesizes it, providing a unique, structured, polychotomous view of the many characterization techniques of DM. Informed by the survey, the paper characterizes the driver state along the five main dimensions-called here "(sub)states"-of drowsiness, mental workload, distraction, emotions, and under the influence. The polychotomous view of DM is presented through a pair of interlocked tables that relate these states to their indicators (e.g., the eye-blink rate) and the sensors that can access each of these indicators (e.g., a camera). The tables factor in not only the effects linked directly to the driver, but also those linked to the (driven) vehicle and the (driving) environment. They show, at a glance, to concerned researchers, equipment providers, and vehicle manufacturers (1) most of the options they have to implement various forms of advanced DM systems, and (2) fruitful areas for further research and innovation.

Asynchronous Semantic Background Subtraction.

The method of Semantic Background Subtraction (SBS), which combines semantic segmentation and background subtraction, has recently emerged for the task of segmenting moving objects in video sequences. While SBS has been shown to improve background subtraction, a major difficulty is that it combines two streams generated at different frame rates. This results in SBS operating at the slowest frame rate of the two streams, usually being the one of the semantic segmentation algorithm. We present a method, referred to as "Asynchronous Semantic Background Subtraction" (ASBS), able to combine a semantic segmentation algorithm with any background subtraction algorithm asynchronously. It achieves performances close to that of SBS while operating at the fastest possible frame rate, being the one of the background subtraction algorithm. Our method consists in analyzing the temporal evolution of pixel features to possibly replicate the decisions previously enforced by semantics when no semantic information is computed. We showcase ASBS with several background subtraction algorithms and also add a feedback mechanism that feeds the background model of the background subtraction algorithm to upgrade its updating strategy and, consequently, enhance the decision. Experiments show that we systematically improve the performance, even when the semantic stream has a much slower frame rate than the frame rate of the background subtraction algorithm. In addition, we establish that, with the help of ASBS, a real-time background subtraction algorithm, such as ViBe, stays real time and competes with some of the best non-real-time unsupervised background subtraction algorithms such as SuBSENSE.

Multi-Timescale Drowsiness Characterization Based on a Video of a Driver's Face.

Drowsiness is a major cause of fatal accidents, in particular in transportation. It is therefore crucial to develop automatic, real-time drowsiness characterization systems designed to issue accurate and timely warnings of drowsiness to the driver. In practice, the least intrusive, physiology-based approach is to remotely monitor, via cameras, facial expressions indicative of drowsiness such as slow and long eye closures. Since the system's decisions are based upon facial expressions in a given time window, there exists a trade-off between accuracy (best achieved with long windows, i.e., at long timescales) and responsiveness (best achieved with short windows, i.e., at short timescales). To deal with this trade-off, we develop a multi-timescale drowsiness characterization system composed of four binary drowsiness classifiers operating at four distinct timescales (5 s, 15 s, 30 s, and 60 s) and trained jointly. We introduce a multi-timescale ground truth of drowsiness, based on the reaction times (RTs) performed during standard Psychomotor Vigilance Tasks (PVTs), that strategically enables our system to characterize drowsiness with diverse trade-offs between accuracy and responsiveness. We evaluated our system on 29 subjects via leave-one-subject-out cross-validation and obtained strong results, i.e., global accuracies of 70%, 85%, 89%, and 94% for the four classifiers operating at increasing timescales, respectively.

Probabilistic Framework for the Characterization of Surfaces and Edges in Range Images, with Application to Edge Detection.

We develop a powerful probabilistic framework for the local characterization of surfaces and edges in range images. We use the geometrical nature of the data to derive an analytic expression for the joint probability density function (pdf) for the random variables used to model the ranges of a set of pixels in a local neighborhood of an image. We decompose this joint pdf by considering independently the cases where two real world points corresponding to two neighboring pixels are locally on the same real world surface or not. In particular, we show that this joint pdf is linked to the Voigt pdf and not to the Gaussian pdf as it is assumed in some applications. We apply our framework to edge detection and develop a locally adaptive algorithm that is based on a probabilistic decision rule. We show in an objective evaluation that this new edge detector performs better than prior art edge detectors. This proves the benefits of the probabilistic characterization of the local neighborhood as a tool to improve applications that involve range images.

ViBe: a universal background subtraction algorithm for video sequences.

This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel. We describe our method in full details (including pseudo-code and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques.