Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics implicitly by correlating novel input and memorized data utilizing ConvNets. We show how ConvNets suffer from architectural restrictions for this task. Based on these findings, we then provide solutions to various issues on exploiting spatio-temporal correlations in a sequence of sensor recordings by presenting a novel Recurrent Neural Network unit utilizing Transformer mechanisms. Within this unit, object encodings are tracked across consecutive frames by correlating key-query pairs derived from sensor inputs and memory states, respectively. We then use resulting tracking patterns to obtain scene dynamics and regress velocities. In a last step, the memory state of the Recurrent Neural Network is projected based on extracted velocity estimates to resolve aforementioned spatio-temporal misalignment.
The Chinese University of Hong Kong（香港中文大学）；MEGVII Technology（旷视科技）；SmartMore（思谋科技）
Multi-object tracking (MOT) requires detecting and associating objects through frames. Unlike tracking via detected bounding boxes or tracking objects as points, we propose tracking objects as pixel-wise distributions. We instantiate this idea on a transformer-based architecture, P3AFormer, with pixel-wise propagation, prediction, and association. P3AFormer propagates pixel-wise features guided by flow information to pass messages between frames. Furthermore, P3AFormer adopts a meta-architecture to produce multi-scale object feature maps. During inference, a pixel-wise association procedure is…
Department of Electrical and Computer Engineering University of Texas at Austin, USA（德克萨斯大学奥斯汀分校电气与计算机工程系，美国）
Handling object interaction is a fundamental challenge in practical multi-object tracking, even for simple interactive effects such as one object temporarily occluding another. We formalize the problem of occlusion in tracking with two different abstractions. In object-wise occlusion, objects that are occluded by other objects do not generate measurements. In measurement-wise occlusion, a previously unstudied approach, all objects may generate measurements but some measurements may be occluded by others. While the relative validity of each abstraction depends on the situation and sensor, measu…
In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background. The framework consists of two submodels, a global attention model and a local segmentation model. The global model generates a region of interests (ROI) that the object may lie in the new frame based on the past object segmentation maps, while the local model segments the new image in the ROI. Each model uses a LSTM structure to model the temporal dynamics of the motion and appearance, respectively. To circumvent the dependency of the training data between th…
The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking, e.g., Long Short Term Memory (LSTM), only deal with single object, while Re-IDentification (Re-ID) based approaches exhaustively compare object appearances. Both approaches are computationally costly when they are scaled to a large number of objects, making it very difficult for real-time MOT. To address these problems, we propose a highly efficient Deep Neural Network (DNN) that simultaneously models association a…
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching property fundamentally suffers from the intermediate interruptions in a video, such as object occlusions, fast camera movements, and abrupt light changes. Moreover, it typically overlooks temporal information beyond the two frames for matching. In this paper, we investigate an alternative by treating object association as clip-wise matching. Our new perspecti…
The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they usually fork a light branch from the backbone network for segmentation. Although efficient, directly fusing backbone features without considering the negative influence of background clutter tends to introduce false-negative predictions, lagging the segmentation accuracy. To mitigate this problem, we propose an attention retrieval network (ARN) to perform so…
Carnegie Mellon University（卡内基梅隆大学）；Xi’an Jiaotong University（西安交通大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Fudan University（复旦大学）；Kyoto University（京都大学）
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID). Because of the indefinite number of targets among video frames, both subtasks are very difficult to scale up efficiently in end-to-end Deep Neural Networks (DNNs). In this paper, we design an end-to-end DNN tracking approach, Flow-Fuse-Tracker (FFT), that addresses the above issues with two efficient techniques: target flowing and target fusing. Specifically, in target flowing, a FlowTracker DNN module learns t…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；German Research Center for Artificial Intelligence（德国人工智能研究中心）；Leibniz University Hannover（汉诺威莱布尼茨大学）；Oldenburg University（奥尔登堡大学）
Multi-Camera Multi-Object Tracking is currently drawing attention in the computer vision field due to its superior performance in real-world applications such as video surveillance in crowded scenes or in wide spaces. In this work, we propose a mathematically elegant multi-camera multiple object tracking approach based on a spatial-temporal lifted multicut formulation. Our model utilizes state-of-the-art tracklets produced by single-camera trackers as proposals. As these tracklets may contain ID-Switch errors, we refine them through a novel pre-clustering obtained from 3D geometry projections.…
Multi-object tracking remains challenging due to frequent occurrence of occlusions and outliers. In order to handle this problem, we propose an Approximation-Shrink Scheme for sequential optimization. This scheme is realized by introducing an Ambiguity-Clearness Graph to avoid conflicts and maintain sequence independent, as well as a sliding window optimization framework to constrain the size of state space and guarantee convergence. Based on this window-wise framework, the states of targets are clustered in a self-organizing manner. Moreover, we show that the traditional online and batch trac…
Maynooth International Engineering College（梅努斯国际工程学院）；FuZhou University（福州大学）
Multi-Object Tracking (MOT) has gained extensive attention in recent years due to its potential applications in traffic and pedestrian detection. We note that tracking by detection may suffer from errors generated by noise detectors, such as an imprecise bounding box before the occlusions, and observed that in most tracking scenarios, objects tend to move and lost within specific locations. To counter this, we present a novel tracker to deal with the bad detector and occlusions. Firstly, we proposed a location-wise sub-region recognition method which equally divided the frame, which we called …
SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking
Nanyang Technological University（南洋理工大学）；Singapore University of Technology and Design（新加坡科技设计大学）；University of Cologne（科隆大学）；SenseTime Research（商汤科技研究院）
In recent years, the multiple-stage strategy has become a popular trend for visual tracking. This strategy first utilizes a base tracker to coarsely locate the target and then exploits a refinement module to obtain more accurate results. However, existing refinement modules suffer from the limited transferability and precision. In this work, we propose a novel, flexible and accurate refinement module called Alpha-Refine, which exploits a precise pixel-wise correlation layer together with a spatial-aware non-local layer to fuse features and can predict three complementary outputs: bounding box,…
Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they cannot take advantage of feature from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResN…
Xi’an Jiaotong University（西安交通大学）；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；Wormpex AI Research（华如科技人工智能研究院）；University of Illinois at Chicago（芝加哥大学伊利诺伊分校）
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of the target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention. The self attention learns strong context information via spatial attention, and selectively emphasizes interdependent channel-wise features with channe…
Video-mapping is the process of coherent video-projection of images, animations or movies on static objects or buildings for shows. This paper focuses on the dynamic video-mapping of the suit of a puppet being moved by its puppeteer on the theater stage. This may allow changing the costume dynamically and simulate light interaction and more. Contrary to common video-mapping, the image warping cannot be done once, offline, before the show. It must be done in real-time, and considering a non-flat projection surface, so that the video-projected suit always maps perfectly the puppet, automatically…
This paper presents a new approach to accurately track a moving vehicle with a multiview setup of red-green-blue depth (RGBD) cameras. We first propose a correction method to eliminate a shift, which occurs in depth sensors when they become worn. This issue could not be otherwise corrected with the ordinary calibration procedure. Next, we present a sensor-wise filtering system to correct for an unknown vehicle motion. A data fusion algorithm is then used to optimally merge the sensor-wise estimated trajectories. We implement most parts of our solution in the graphic processor. Hence, the whole…
University of Science and Technology of China（中国科学技术大学）；Baidu Inc.（百度公司）
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the inherent receptive field, convolution based feature extraction inevitably mixes up the foreground features and the background features, resulting in ambiguities in the subsequent instance association. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. Our method generates a ne…
Southeast University（东南大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；JD Finance America Corporation（京东金融美国公司）；Tianjin University of Technology（天津理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Lab（鹏城实验室）
Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations. To address these issues, much effort has been made on segmentation-based tracking, which learns a pixel-wise object-aware template and can achieve higher accuracy than bounding-box template based tracking. However, existing segmentation-based trackers are ineffective in learning the spatio-temporal correspondence across frames due to no use of the rich temporal …
This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments. In this paper, we treat the MOT task as a two-stage task including human detection and trajectory matching. Specifically, we designed an improved human detector and associated most of detection to guarantee the integrity of the motion trajectory. We also propose a location-wise matching matrix to obtain more accurate trace matching. Without any model merging, our method achieves 66.672 HOTA and 93.971 MOTA on the DanceTrack challenge dataset.
3D single object tracking is a key issue for autonomous following robot, where the robot should robustly track and accurately localize the target for efficient following. In this paper, we propose a 3D tracking method called 3D-SiamRPN Network to track a single target object by using raw 3D point cloud data. The proposed network consists of two subnetworks. The first subnetwork is feature embedding subnetwork which is used for point cloud feature extraction and fusion. In this subnetwork, we first use PointNet++ to extract features of point cloud from template and search branches. Then, to fus…
This paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition; skeleton detection and tracking errors, poor variety of the targeted actions, as well as person-wise and frame-wise action recognition. A point cloud deep-learning paradigm is introduced to the action recognition, and a unified framework along with a novel deep neural network architecture called Structured Keypoint Pooling is proposed. The proposed method sparsely aggregates keypoint features in a cascaded manner based on prior knowledge of the data structure (which is inherent…
Online 3D multi-object tracking (MOT) has witnessed significant research interest in recent years, largely driven by demand from the autonomous systems community. However, 3D offline MOT is relatively less explored. Labeling 3D trajectory scene data at a large scale while not relying on high-cost human experts is still an open research question. In this work, we propose Batch3DMOT which follows the tracking-by-detection paradigm and represents real-world scenes as directed, acyclic, and category-disjoint tracking graphs that are attributed using various modalities such as camera, LiDAR, and ra…
Hong Kong University of Science and Technology（香港科技大学）
A robust 3D object tracker which continuously tracks surrounding objects and estimates their trajectories is key for self-driving vehicles. Most existing tracking methods employ a tracking-by-detection strategy, which usually requires complex pair-wise similarity computation and neglects the nature of continuous object motion. In this paper, we propose to directly learn 3D object correspondences from temporal point cloud data and infer the motion information from correspondence patterns. We modify the standard 3D object detector to process two lidar frames at the same time and predict bounding…
Multiple Object Tracking (MOT) is an important task in computer vision. MOT is still challenging due to the occlusion problem, especially in dense scenes. Following the tracking-by-detection framework, we propose the Box-Plane Matching (BPM) method to improve the MOT performacne in dense scenes. First, we design the Layer-wise Aggregation Discriminative Model (LADM) to filter the noisy detections. Then, to associate remaining detections correctly, we introduce the Global Attention Feature Model (GAFM) to extract appearance feature and use it to calculate the appearance similarity between histo…
University of Surrey（萨里大学）；Jiangnan University（江南大学）
Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embedding functions via pair-wise offline training on large-scale video datasets. However, the Siamese paradigm uses one-shot learning to model the online tracking task, which impedes online adaptation in the tracking process. Additionally, the uncertainty of an online tracking response is not measured, leading to the problem of ignoring potential failures. In this paper, we advocate online adaptation in the tracking stag…
Columbia University（哥伦比亚大学）；Sony Group Corporation（索尼集团公司）
We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational bottleneck associated with its design, and at the same time, achieves state-of-the-art MOTA score of 73.20%. The model design is driven by a transformer based backbone instead of CNN, which is highly scalable with the input resolution. We also propose a drop-in replacement for Feed Forward Network of transformer encoder layer, by using Butterfly Transform Opera…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are c…
In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation information into reliable 3D point cloud data, potentially revolutionizing the autonomous vehicles and assistive robotic industry. A point cloud is a dense compilation of spatial data in 3D coordinates. It plays a vital role in modeling complex real-world scenes since it preserves structural information and avoids perspective distortion, unlike image data, which is the projection of a 3D structure on a 2D plane. In order…
We propose a data-driven approach to online multi-object tracking (MOT) that uses a convolutional neural network (CNN) for data association in a tracking-by-detection framework. The problem of multi-target tracking aims to assign noisy detections to a-priori unknown and time-varying number of tracked objects across a sequence of frames. A majority of the existing solutions focus on either tediously designing cost functions or formulating the task of data association as a complex optimization problem that can be solved effectively. Instead, we exploit the power of deep learning to formulate the…
3D motion tracking is a critical task in many computer vision applications. Existing 3D motion tracking techniques require either a great amount of knowledge on the target object or specific hardware. These requirements discourage the wide spread of commercial applications based on 3D motion tracking. 3D motion tracking systems that require no knowledge on the target object and run on a single low-budget camera require estimations of the object projection features (namely, area and position). In this paper, we define the object projection feature estimation problem and we present a novel 3D mo…
Erasmus MC（伊拉斯姆斯大学医学中心）；Delft University of Technology（代尔夫特理工大学）
Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by purging the bias information from learned representations. We however expect this strategy to harm the diversity of information in the representation, and thus limiting its prospective usage (e.g., interpretation). Therefore, we propose to mitigate the bias while keeping almost all information in the latent representations, which enables us to observe and int…
3D motion tracking is a critical task in many computer vision applications. Unsupervised markerless 3D motion tracking systems determine the most relevant object in the screen and then track it by continuously estimating its projection features (center and area) from the edge image and a point inside the relevant object projection (namely, inner point), until the tracking fails. Existing object projection feature estimation techniques are based on ray-casting from the inner point. These techniques present three main drawbacks: when the inner point is surrounded by edges, rays may not reach oth…
3D motion tracking is a critical task in many computer vision applications. Unsupervised markerless 3D motion tracking systems determine the most relevant object in the screen and then track it by continuously estimating its projection features (center and area) from the edge image and a point inside the relevant object projection (namely, inner point), until the tracking fails. Existing reliable object projection feature estimation techniques are based on ray-casting or grid-filling from the inner point. These techniques assume the edge image to be accurate. However, in real case scenarios, e…
Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；school of Computer Science and Engineering, Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；Chinese University of Hong Kong（香港中文大学）
Recent machine learning strategies for segmentation tasks have shown great ability when trained on large pixel-wise annotated image datasets. It remains a major challenge however to aggregate such datasets, as the time and monetary cost associated with collecting extensive annotations is extremely high. This is particularly the case for generating precise pixel-wise annotations in video and volumetric image data. To this end, this work presents a novel framework to produce pixel-wise segmentations using minimal supervision. Our method relies on 2D point supervision, whereby a single 2D locatio…
Leibniz Universität Hannover（汉诺威莱布尼茨大学）；Institute of Mechatronic Systems（机电系统研究所）
In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as well as thickness. However, existing approaches for OCT based laser ablation control rely on external tracking systems or invasively ablated artificial landmarks for tracking the pose of the OCT probe relative to the tissue. This can be superseded by estimating the scene flow cause…
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…
DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Department of Computer Science and Engineering, University of North Texas（北卡罗来纳州立大学计算机科学与工程系）；OPPO AI Center（OPPO人工智能中心）
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；The University of Warwick（华威大学）
Permutation testing is a non-parametric method for obtaining the max null distribution used to compute corrected $p$-values that provide strong control of false positives. In neuroimaging, however, the computational burden of running such an algorithm can be significant. We find that by viewing the permutation testing procedure as the construction of a very large permutation testing matrix, $T$, one can exploit structural properties derived from the data and the test statistics to reduce the runtime under certain conditions. In particular, we see that $T$ is low-rank plus a low-variance residu…
Manifold amount of video data gets generated every minute as we read this document, ranging from surveillance to broadcasting purposes. There are two roadblocks that restrain us from using this data as such, first being the storage which restricts us from only storing the information based on the hardware constraints. Secondly, the computation required to process this data is highly expensive which makes it infeasible to work on them. Compressive sensing(CS)[2] is a signal process technique[11], through optimization, the sparsity of a signal can be exploited to recover it from far fewer sample…
Dynamic Exploration on Segment-Proposal Graphs for Tubular Centerline Tracking
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences)（山东省人工智能研究院，齐鲁工业大学（山东省科学院））；School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学）；Department of Mathematics, Centre Borelli, ENS Paris-Saclay, CNRS, University Paris-Saclay（数学系，ENS巴黎-萨克雷中心，CNRS，巴黎-萨克雷大学）；Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences（放射肿瘤科，山东省肿瘤医院及研究所，山东第一医科大学，山东省医学科学院）；CEREMADE, University Paris Dauphine, Université-PSL, CNRS, UMR 7534（CEREMADE，巴黎-萨克雷大学，Université-PSL，CNRS，UMR 7534）
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we propose a differentiable forward rigid projection module that plays a key role in our instance-wise depth and motion learning. Second, we design an instance-wise photometric and geometric consistency loss that effectively decomposes background and moving object regions. Lastly, we introduce a new auto-annotation scheme to produce video instance segmentation m…
We propose a novel method for continuous-time feature tracking in event cameras. To this end, we track features by aligning events along an estimated trajectory in space-time such that the projection on the image plane results in maximally sharp event patch images. The trajectory is parameterized by $n^{th}$ order B-splines, which are continuous up to $(n-2)^{th}$ derivative. In contrast to previous work, we optimize the curve parameters in a sliding window fashion. On a public dataset we experimentally confirm that the proposed sliding-window B-spline optimization leads to longer and more acc…
