Related papers: Bayesian Multiobject Tracking With Neural-Enhanced…
Recent multi-camera 3D object detectors usually leverage temporal information to construct multi-view stereo that alleviates the ill-posed depth estimation. However, they typically assume all the objects are static and directly aggregate…
Multi-object tracking (MOT) and trajectory prediction are two critical components in modern 3D perception systems that require accurate modeling of multi-agent interaction. We hypothesize that it is beneficial to unify both tasks under one…
Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective…
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation…
Multi-objective optimization aims to solve problems with competing objectives. Evaluating such problems is often slow or expensive, limiting the budget of evaluations. In many applications, historical data from related optimization tasks is…
The problem of multi-object tracking (MOT) consists in detecting and tracking all the objects in a video sequence while keeping a unique identifier for each object. It is a challenging and fundamental problem for robotics. In precision…
This paper presents a multi-sensor fusion strategy for a novel road-matching method designed to support real-time navigational features within advanced driving-assistance systems. Managing multihypotheses is a useful strategy for the…
3D multi-object tracking and trajectory prediction are two crucial modules in autonomous driving systems. Generally, the two tasks are handled separately in traditional paradigms and a few methods have started to explore modeling these two…
Object tracking is an ubiquitous problem that appears in many applications such as remote sensing, audio processing, computer vision, human-machine interfaces, human-robot interaction, etc. Although thoroughly investigated in computer…
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…
While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models…
Multi-Object Tracking (MOT) poses significant challenges in computer vision. Despite its wide application in robotics, autonomous driving, and smart manufacturing, there is limited literature addressing the specific challenges of running…
3D multi-object tracking is a key module in autonomous driving applications that provides a reliable dynamic representation of the world to the planning module. In this paper, we present our on-line tracking method, which made the first…
3D multi-object tracking (3D MOT) stands as a pivotal domain within autonomous driving, experiencing a surge in scholarly interest and commercial promise over recent years. Despite its paramount significance, 3D MOT confronts a myriad of…
Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to…
With the proliferation of low altitude unmanned aerial vehicles (UAVs), visual multi-object tracking is becoming a critical security technology, demanding significant robustness even in complex environmental conditions. However, tracking…
In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object…
Accurate prediction of future agent trajectories is a critical challenge for ensuring safe and efficient autonomous navigation, particularly in complex urban environments characterized by multiple plausible future scenarios. In this paper,…
We propose FutrTrack, a modular camera-LiDAR multi-object tracking framework that builds on existing 3D detectors by introducing a transformer-based smoother and a fusion-driven tracker. Inspired by query-based tracking frameworks,…
We introduce ForeSight, a novel joint detection and forecasting framework for vision-based 3D perception in autonomous vehicles. Traditional approaches treat detection and forecasting as separate sequential tasks, limiting their ability to…