Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city. The challenge is how to model long-term temporal dependencies in an efficient manner. Some recent works employ Recurrent Neural Networks (RNN) to obtain good performance, which, however, requires a large amount of training data. In this paper, we proposed a novel tracking method that integrates the auto-tuning Kalman method for prediction and the Gated Recurrent Unit (GRU) and achieves a near-optimum with a small amount of training data. Experimental results show that our new algorithm can achieve competitive performance on the challenging MOT benchmark, and faster and more robust than the state-of-the-art RNN-based online MOT algorithms.
PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking
Department of Electrical and Computer Engineering, University of California San Diego（电气与计算机工程系，加州大学圣地亚哥分校）；Department of Electrical and Systems Engineering, University of Pennsylvania（电气与系统工程系，宾夕法尼亚大学）
Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Framework
Daimler Truck AG, Research and Advanced Development（戴姆勒卡车股份公司，研发与高级发展部门）；Institute for Intelligent Systems, University of Applied Sciences（应用科学大学智能系统研究所）；Center for Artificial Intelligence, Baden-Württemberg Cooperative State University (DHBW)（巴登-符腾堡州立合作大学人工智能中心）
Learning a Neural Association Network for Self-supervised Multi-Object Tracking
University of Bonn（波恩大学）；Monash University（莫纳什大学）；University of Edinburgh（爱丁堡大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所）
Engineering an Efficient Object Tracker for Non-Linear Motion
Department of Computer Science, Faculty of Mathematics, University of Belgrade（计算机科学系，数学系，贝尔格莱德大学）；Department of Signals and Systems, School of Electrical Engineering, University of Belgrade（信号与系统系，电气工程学院，贝尔格莱德大学）；Center for Bussiness Decision Making, Faculty of Organizational sciences, University of Belgrade（商业决策中心，组织科学系，贝尔格莱德大学）
The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object. In this paper, we present a new robust state-of-the-art tracker, which can combine the advantages of motion and appearance information, along with camera-motion compensation, and a more accurate Kalman filter state vector. Our new trackers BoT-SORT, and BoT-SORT-ReID rank first in the datasets of MOTChallenge [29, 11] on both MOT17 and MOT20 test sets, in terms of all the main MOT metrics: MOTA, IDF1, and HOTA. For MOT17: 80.5 MOTA, 80.2 IDF1, and 65.…
Concordia University（康考迪亚大学）；Chalmers University of Technology（查尔姆斯理工大学）；University of Arkansas（阿肯色大学）
This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extensio…
Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子通信研究院）；National Center for High-Performance Computing（国家高性能计算中心）
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 place in the NuScenes Tracking Challenge, held at the AI Driving Olympics Workshop at NeurIPS 2019. Our method estimates the object states by adopting a Kalman Filter. We initialize the state covariance as well as the process and observation noise covariance with statistics from the training set. We also use the stochastic information from the Kalman Filter in …
National Taiwan University（台湾大学）；National Tsing Hua University（清华大学）
The paper presents a new method, SearchTrack, for multiple object tracking and segmentation (MOTS). To address the association problem between detected objects, SearchTrack proposes object-customized search and motion-aware features. By maintaining a Kalman filter for each object, we encode the predicted motion into the motion-aware feature, which includes both motion and appearance cues. For each object, a customized fully convolutional search engine is created by SearchTrack by learning a set of weights for dynamic convolutions specific to the object. Experiments demonstrate that our SearchT…
LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds
School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University（人工智能与先进计算学院，西安交通大学利物浦大学）；Momoni AI；Department of Automation, Shanghai Jiaotong University（自动化学院，上海交通大学）；College of Science and Engineering, James Cook University（科学与工程学院，詹姆斯库克大学）；School of Engineering, Swinburne University of Technology（工程学院，斯威灵斯大学）
Baidu Inc.（百度公司）；Huazhong University of Science and Technology（华中科技大学）；The University of Hong Kong（香港大学）
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitable changing of detection scores leads to object missing after tracking. We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories. The simple and generic data association strategy shows effectiveness under both 2D and 3D settings. In 3D scenarios, it is much easier for the tracker to predict obj…
Centre Suisse d’Electronique et Microtechnique（瑞士电子与微技术中心）；The Smith-Kettlewell Eye Research Institute（史密斯-凯特维尔眼研究所）
We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate the motion flows in the image sequence. This temporal grouping can be considered a generalization of the data association techniques used by engineers to study motion sequences. Our temporal-grouping theory is expressed in terms of the Bayesian generalization of standard Kalman filtering. To implement the theory we derive a parallel network which shares some properties of cortical networks. Compute…
Object triangulation, 3-D object tracking, feature correspondence, and camera calibration are key problems for estimation from camera networks. This paper addresses these problems within a unified Bayesian framework for joint multi-object tracking and sensor registration. Given that using standard filtering approaches for state estimation from cameras is problematic, an alternative parametrisation is exploited, called disparity space. The disparity space-based approach for triangulation and object tracking is shown to be more effective than non-linear versions of the Kalman filter and particle…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
3D multi-object tracking (MOT) is essential to applications such as autonomous driving. Recent work focuses on developing accurate systems giving less attention to computational cost and system complexity. In contrast, this work proposes a simple real-time 3D MOT system with strong performance. Our system first obtains 3D detections from a LiDAR point cloud. Then, a straightforward combination of a 3D Kalman filter and the Hungarian algorithm is used for state estimation and data association. Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in 2D space and standardized 3D MOT e…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
3D multi-object tracking (MOT) is an essential component for many applications such as autonomous driving and assistive robotics. Recent work on 3D MOT focuses on developing accurate systems giving less attention to practical considerations such as computational cost and system complexity. In contrast, this work proposes a simple real-time 3D MOT system. Our system first obtains 3D detections from a LiDAR point cloud. Then, a straightforward combination of a 3D Kalman filter and the Hungarian algorithm is used for state estimation and data association. Additionally, 3D MOT datasets such as KIT…
Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage
Trinity College Dublin（都柏林圣三一学院）；School of Zoology, Trinity College Dublin（都柏林圣三一学院动物学学院）；Sigmedia Group, Electronic and Electrical Engineering, Trinity College Dublin（都柏林圣三一学院电子与电气工程系Sigmedia团队）
Accurate motion state estimation of Vulnerable Road Users (VRUs), is a critical requirement for autonomous vehicles that navigate in urban environments. Due to their computational efficiency, many traditional autonomy systems perform multi-object tracking using Kalman Filters which frequently rely on hand-engineered association. However, such methods fail to generalize to crowded scenes and multi-sensor modalities, often resulting in poor state estimates which cascade to inaccurate predictions. We present a practical and lightweight tracking system, SDVTracker, that uses a deep learned model f…
3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
Mercedes-Benz AG（梅赛德斯-奔驰股份公司）；University of Bonn（波恩大学）；Robert Bosch GmbH（罗伯特·博世有限公司）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）
SAMOFT: Robust Multi-Object Tracking via Region and Flow
School of Computer Science and Technology, Zhejiang Normal University（浙江师范大学计算机科学与技术学院）；Institute for Sustainable Industries and Liveable Cities, College of Engineering and Science, Victoria University（维多利亚大学可持续产业与宜居城市研究所、工程与科学学院）；School of Electrical Engineering and Computer Science, University of California at Merced（加州大学默塞德分校电子工程与计算机科学学院）
The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices. State estimation techniques that rely on non-linear filtering are a strong paradigm for solving the associated information fusion task. The de facto inference method in this space is the celebrated extended Kalman filter (EKF), which relies on first-order linearizations of both the dynamical and measurement model. This paper takes a critical look at the practical implications and limitations posed by the EKF, especially under faulty visual feature associations and the pres…
Most recent works on multi-target tracking with multiple cameras focus on centralized systems. In contrast, this paper presents a multi-target tracking approach implemented in a distributed camera network. The advantages of distributed systems lie in lighter communication management, greater robustness to failures and local decision making. On the other hand, data association and information fusion are more challenging than in a centralized setup, mostly due to the lack of global and complete information. The proposed algorithm boosts the benefits of the Distributed-Consensus Kalman Filter wit…
The Hong Kong University of Science and Technology（香港科技大学）；Tongji University（同济大学）
Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds. Most traditional tracking approaches use filters (e.g., Kalman filter or particle filter) to predict object locations in a time sequence, however, they are vulnerable to extreme motion conditions, such as sudden braking and turning. In this letter, we propose PointTrackNet, an end-to-end 3-D object detection and tracking network, to generate foreground masks, 3-D bounding boxes, and point-wise tracking association displacements for each detected object. The network merely takes as in…
Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Renault SAS（雷诺股份有限公司）
In this paper, a multi-modal 360$^{\circ}$ framework for 3D object detection and tracking for autonomous vehicles is presented. The process is divided into four main stages. First, images are fed into a CNN network to obtain instance segmentation of the surrounding road participants. Second, LiDAR-to-image association is performed for the estimated mask proposals. Then, the isolated points of every object are processed by a PointNet ensemble to compute their corresponding 3D bounding boxes and poses. Lastly, a tracking stage based on Unscented Kalman Filter is used to track the agents along ti…
Huazhong University of Science and Technology（华中科技大学）；Tencent AI Lab（腾讯人工智能实验室）
We address the problem of semi-supervised video object segmentation (VOS), where the masks of objects of interests are given in the first frame of an input video. To deal with challenging cases where objects are occluded or missing, previous work relies on greedy data association strategies that make decisions for each frame individually. In this paper, we propose a novel approach to defer the decision making for a target object in each frame, until a global view can be established with the entire video being taken into consideration. Our approach is in the same spirit as Multiple Hypotheses T…
Robotics, Perception and Learning Lab Royal Institute of Technology (KTH)（皇家理工学院（KTH）机器人、感知与学习实验室）
This paper studies the problem of detection and tracking of general objects with long-term dynamics, observed by a mobile robot moving in a large environment. A key problem is that due to the environment scale, it can only observe a subset of the objects at any given time. Since some time passes between observations of objects in different places, the objects might be moved when the robot is not there. We propose a model for this movement in which the objects typically only move locally, but with some small probability they jump longer distances, through what we call global motion. For filteri…
Automated tracking of animal movement allows analyses that would not otherwise be possible by providing great quantities of data. The additional capability of tracking in realtime - with minimal latency - opens up the experimental possibility of manipulating sensory feedback, thus allowing detailed explorations of the neural basis for control of behavior. Here we describe a new system capable of tracking the position and body orientation of animals such as flies and birds. The system operates with less than 40 msec latency and can track multiple animals simultaneously. To achieve these results…
Indian Statistical Institute（印度统计学院）；University of Dayton（代顿大学）
In this paper we propose a novel approach for detecting and tracking objects in videos with variable background i.e. videos captured by moving cameras without any additional sensor. In a video captured by a moving camera, both the background and foreground are changing in each frame of the image sequence. So for these videos, modeling a single background with traditional background modeling methods is infeasible and thus the detection of actual moving object in a variable background is a challenging task. To detect actual moving object in this work, spatio-temporal blobs have been generated in…
Stanford Vision and Learning Laboratory, Stanford University（斯坦福大学视觉与学习实验室）
Robots navigating autonomously need to perceive and track the motion of objects and other agents in its surroundings. This information enables planning and executing robust and safe trajectories. To facilitate these processes, the motion should be perceived in 3D Cartesian space. However, most recent multi-object tracking (MOT) research has focused on tracking people and moving objects in 2D RGB video sequences. In this work we present JRMOT, a novel 3D MOT system that integrates information from RGB images and 3D point clouds to achieve real-time, state-of-the-art tracking performance. Our sy…
