相关论文: Generalizable Multi-Camera 3D Pedestrian Detection

We present a robust multi-camera gymnast tracking, which has been applied at international gymnastics championships for gymnastics judging. Despite considerable progress in multi-camera tracking algorithms, tracking gymnasts presents unique…

Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of single camera as…

This thesis is devoted to marker-less 3D human motion tracking in calibrated and synchronized multicamera systems. Pose estimation is based on a 3D model, which is transformed into the image plane and then rendered. Owing to elaborated…

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc. Direct estimation of 3D pose, body shape or motion on…

In this paper, we propose a privacy-enhancing technique leveraging an inherent property of automatic pedestrian detection algorithms, namely, that the training of deep neural network (DNN) based methods is generally performed using curated…

Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics. However, human-centric real-life scenarios are extremely diverse and complicated, and humans have intricate motions and…

Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly…

The ability to efficiently utilize crowdsourced visual data carries immense potential for the domains of large scale dynamic mapping and autonomous driving. However, state-of-the-art methods for crowdsourced 3D mapping assume prior…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

In this paper, we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea, we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting…

Monocular 3D human pose estimation has made progress in recent years. Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.e., the coordinates based on the center of the target person.…

Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles. To enable collaborative…

In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage. Namely, the inherent…

This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera. The pedestrians are located in each frame using a standard human detector, which are then tracked in subsequent frames.…

We present a generative approach to forecast long-term future human behavior in 3D, requiring only weak supervision from readily available 2D human action data. This is a fundamental task enabling many downstream applications. The required…

This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios. Using images from a monocular camera alone, we devise pairwise costs for object tracks, based on several 3D cues such as…

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view…

We present an approach to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we…

3D human pose estimation involves reconstructing the human skeleton by detecting the body joints. Accurate and efficient solutions are required for several real-world applications including animation, human-robot interaction, surveillance,…

In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly…