Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work the problem of conflicting performance between accuracy and robustness. We first conduct a systematic comparison among existing methods and analyze their restrictions in terms of accuracy and robustness. Specifically, 4 formulations-offline classification (OFC), offline regression (OFR), online classification (ONC), and online regression (ONR)-are considered, categorized by the existence of online update and the types of supervision signal. To account for the problem, we resort to the idea of ensemble and propose a dual-modal framework for target localization, consisting of robust localization suppressing distractors via ONR and the accurate localization attending to the target center precisely via OFC. To yield a final representation (i.e, bounding box), we propose a simple but effective score voting strategy to involve adjacent predictions such that the final representation does not commit to a single location. Operating beyond the real-time demand, our proposed method is further validated on 8 datasets-VOT2018, VOT2019, OTB2015, NFS, UAV123, LaSOT, TrackingNet, and GOT-10k, achieving state-of-the-art performance.
We demonstrate an object tracking method for 3D images with fixed computational cost and state-of-the-art performance. Previous methods predicted transformation parameters from convolutional layers. We instead propose an architecture that does not include either flattening of convolutional features or fully connected layers, but instead relies on equivariant filters to preserve transformations between inputs and outputs (e.g. rot./trans. of inputs rotate/translate outputs). The transformation is then derived in closed form from the outputs of the filters. This method is useful for applications requiring low latency, such as real-time tracking. We demonstrate our model on synthetically augmented adult brain MRI, as well as fetal brain MRI, which is the intended use-case.
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior works, most of them are tailored to fit specific types of FSL algorithms and may sacrifice running speed. In this work, we propose a generalized two-stage framework that is capable of employing a large variety of FSL algorithms while presenting faster adaptation speed. The first stage uses a Siamese Regional Proposal Network to efficiently propose the potential candidates and the second stage reformulates the task of classifying these candidates to a few-shot classification problem. Following such a coarse-to-fine pipeline, the first stage proposes informative sparse samples for the second stage, where a large variety of FSL algorithms can be conducted more conveniently and efficiently. As substantiation of the second stage, we systematically investigate several forms of optimization-based few-shot learners from previous works with different objective functions, optimization methods, or solution space. Beyond that, our framework also entails a direct application of the majority of other FSL algorithms to visual tracking, enabling mutual communication between researchers on these two topics. Extensive experiments on the major benchmarks, VOT2018, OTB2015, NFS, UAV123, TrackingNet, and GOT-10k are conducted, demonstrating a desirable performance gain and a real-time speed.
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.
Object tracking is a key aspect in many applications such as augmented reality in medicine (e.g. tracking a surgical instrument) or robotics. Squared planar markers have become popular tools for tracking since their pose can be estimated from their four corners. While using a single marker and a single camera limits the working area considerably, using multiple markers attached to an object requires estimating their relative position, which is not trivial, for high accuracy tracking. Likewise, using multiple cameras requires estimating their extrinsic parameters, also a tedious process that must be repeated whenever a camera is moved. This work proposes a novel method to simultaneously solve the above-mentioned problems. From a video sequence showing a rigid set of planar markers recorded from multiple cameras, the proposed method is able to automatically obtain the three-dimensional configuration of the markers, the extrinsic parameters of the cameras, and the relative pose between the markers and the cameras at each frame. Our experiments show that our approach can obtain highly accurate results for estimating these parameters using low resolution cameras. Once the parameters are obtained, tracking of the object can be done in real time with a low computational cost. The proposed method is a step forward in the development of cost-effective solutions for object tracking.
The ability of an autonomous vehicle to perform 3D tracking is essential for safe planing and navigation in cluttered environments. The main challenges for multi-object tracking (MOT) in autonomous driving applications reside in the inherent uncertainties regarding the number of objects, when and where the objects may appear and disappear, and uncertainties regarding objects' states. Random finite set (RFS) based approaches can naturally model these uncertainties accurately and elegantly, and they have been widely used in radar-based tracking applications. In this work, we developed an RFS-based MOT framework for 3D LiDAR data. In partiuclar, we propose a Poisson multi-Bernoulli mixture (PMBM) filter to solve the amodal MOT problem for autonomous driving applications. To the best of our knowledge, this represents a first attempt for employing an RFS-based approach in conjunction with 3D LiDAR data for MOT applications with comprehensive validation using challenging datasets made available by industry leaders. The superior experimental results of our PMBM tracker on public Waymo and Argoverse datasets clearly illustrate that an RFS-based tracker outperforms many state-of-the-art deep learning-based and Kalman filter-based methods, and consequently, these results indicate a great potential for further exploration of RFS-based frameworks for 3D MOT applications.
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph. This framework is similar to the two-stage object detector Faster RCNN, and can solve the MOT problem in a data-driven way. For proposal generation, we propose an iterative graph clustering method to reduce the computational cost while maintaining the quality of the generated proposals. For proposal scoring, we deploy a trainable graph-convolutional-network (GCN) to learn the structural patterns of the generated proposals and rank them according to the estimated quality scores. For trajectory inference, a simple deoverlapping strategy is adopted to generate tracking output while complying with the constraints that no detection can be assigned to more than one track. We experimentally demonstrate that the proposed method achieves a clear performance improvement in both MOTA and IDF1 with respect to previous state-of-the-art on two public benchmarks. Our code is available at https://github.com/daip13/LPC_MOT.git.
Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convolutional neural network to match objects in adjacent video frames. It learns the patchwise correlation features instead of pixel features. PatchNet is very compact, running at just 58MFLOPs, $5\times$ simpler than MobileNetV2. We demonstrate its application on two tasks, video object detection and visual object tracking. On ImageNet VID, PatchNet reduces the flops of R-FCN ResNet-101 by 5x and EfficientDet-D0 by 3.4x with less than 1% mAP loss. On OTB2015, PatchNet reduces SiamFC and SiamRPN by 2.5x with no accuracy loss. Experiments on Jetson Nano further demonstrate 2.8x to 4.3x speed-ups associated with flops reduction. Code is open sourced at https://github.com/RalphMao/PatchNet.
A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform. The object association leverages quasi-dense similarity learning to identify objects in various poses and viewpoints with appearance cues only. After initial 2D association, we further utilize 3D bounding boxes depth-ordering heuristics for robust instance association and motion-based 3D trajectory prediction for re-identification of occluded vehicles. In the end, an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation. Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios. On the Waymo Open benchmark, we establish the first camera-only baseline in the 3D tracking and 3D detection challenges. Our quasi-dense 3D tracking pipeline achieves impressive improvements on the nuScenes 3D tracking benchmark with near five times tracking accuracy of the best vision-only submission among all published methods. Our code, data and trained models are available at https://github.com/SysCV/qd-3dt.
Estimating the states of surrounding traffic participants stays at the core of autonomous driving. In this paper, we study a novel setting of this problem: model-free single-object tracking (SOT), which takes the object state in the first frame as input, and jointly solves state estimation and tracking in subsequent frames. The main purpose for this new setting is to break the strong limitation of the popular "detection and tracking" scheme in multi-object tracking. Moreover, we notice that shape completion by overlaying the point clouds, which is a by-product of our proposed task, not only improves the performance of state estimation but also has numerous applications. As no benchmark for this task is available so far, we construct a new dataset LiDAR-SOT and corresponding evaluation protocols based on the Waymo Open dataset. We then propose an optimization-based algorithm called SOTracker involving point cloud registration, vehicle shapes, correspondence, and motion priors. Our quantitative and qualitative results prove the effectiveness of our SOTracker and reveal the challenging cases for SOT in point clouds, including the sparsity of LiDAR data, abrupt motion variation, etc. Finally, we also explore how the proposed task and algorithm may benefit other autonomous driving applications, including simulating LiDAR scans, generating motion data, and annotating optical flow. The code and protocols for our benchmark and algorithm are available at https://github.com/TuSimple/LiDAR_SOT/. A video demonstration is at https://www.youtube.com/watch?v=BpHixKs91i8.
This paper focused on the design of an optimized object tracking technique which would minimize the processing time required in the object detection process while maintaining accuracy in detecting the desired moving object in a cluttered scene. A Kalman filter based cropped image is used for the image detection process as the processing time is significantly less to detect the object when a search window is used that is smaller than the entire video frame. This technique was tested with various sizes of the window in the cropping process. MATLAB was used to design and test the proposed method. This paper found that using a cropped image with 2.16 multiplied by the largest dimension of the object resulted in significantly faster processing time while still providing a high success rate of detection and a detected center of the object that was reasonably close to the actual center.
Robotic manipulation of unknown objects is an important field of research. Practical applications occur in many real-world settings where robots need to interact with an unknown environment. We tackle the problem of reactive grasping by proposing a method for unknown object tracking, grasp point sampling and dynamic trajectory planning. Our object tracking method combines Siamese Networks with an Iterative Closest Point approach for pointcloud registration into a method for 6-DoF unknown object tracking. The method does not require further training and is robust to noise and occlusion. We propose a robotic manipulation system, which is able to grasp a wide variety of formerly unseen objects and is robust against object perturbations and inferior grasping points.
Multiple object tracking is a challenging problem in computer vision due to difficulty in dealing with motion prediction, occlusion handling, and object re-identification. Many recent algorithms use motion and appearance cues to overcome these challenges. But using appearance cues increases the computation cost notably and therefore the speed of the algorithm decreases significantly which makes them inappropriate for online applications. In contrast, there are algorithms that only use motion cues to increase speed, especially for online applications. But these algorithms cannot handle occlusions and re-identify lost objects. In this paper, a novel online multiple object tracking algorithm is presented that only uses geometric cues of objects to tackle the occlusion and reidentification challenges simultaneously. As a result, it decreases the identity switch and fragmentation metrics. Experimental results show that the proposed algorithm could decrease identity switch by 40% and fragmentation by 28% compared to the state of the art online tracking algorithms. The code is also publicly available.
This paper presents a novel approach of representing dynamic visual scenes with static maps generated from video/image streams. Such representation allows easy visual assessment of motion in dynamic environments. These maps are 2D matrices calculated recursively, in a pixel-wise manner, that is based on the recently introduced concept of Eccentricity data analysis. Eccentricity works as a metric of a discrepancy between a particular pixel of an image and its normality model, calculated in terms of mean and variance of past readings of the same spatial region of the image. While Eccentricity maps carry temporal information about the scene, actual images do not need to be stored nor processed in batches. Rather, all the calculations are done recursively, based on a small amount of statistical information stored in memory, thus resulting in a very computationally efficient (processor- and memory-wise) method. The list of potential applications includes video-based activity recognition, intent recognition, object tracking, video description, and so on.
Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem, and thus are inherently more appropriate for the tracking task. However, Siamese trackers mainly use the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not an optimal choice in a deep similarity framework. We present a Multiple Features-Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. Since convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to obtain a richer and more efficient representation of the target. Moreover, we handle the target appearance variations by calibrating the deep features extracted from two different CNN models. Based on this advanced feature representation, our method achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks. The source code and trained models are available at https://github.com/zhenxili96/MFST.
Building footprints provide a useful proxy for a great many humanitarian applications. For example, building footprints are useful for high fidelity population estimates, and quantifying population statistics is fundamental to ~1/4 of the United Nations Sustainable Development Goals Indicators. In this paper we (the SpaceNet Partners) discuss efforts to develop techniques for precise building footprint localization, tracking, and change detection via the SpaceNet Multi-Temporal Urban Development Challenge (also known as SpaceNet 7). In this NeurIPS 2020 competition, participants were asked identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas. The competition centered around a brand new open source dataset of Planet Labs satellite imagery mosaics at 4m resolution, which includes 24 images (one per month) covering ~100 unique geographies. Tracking individual buildings at this resolution is quite challenging, yet the winning participants demonstrated impressive performance with the newly developed SpaceNet Change and Object Tracking (SCOT) metric. This paper details the top-5 winning approaches, as well as analysis of results that yielded a handful of interesting anecdotes such as decreasing performance with latitude.
Temporal semantic scene understanding is critical for self-driving cars or robots operating in dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. To this end, we present an approach and a point-centric evaluation metric. Our approach determines a semantic class for every point while modeling object instances as probability distributions in the 4D spatio-temporal domain. We process multiple point clouds in parallel and resolve point-to-instance associations, effectively alleviating the need for explicit temporal data association. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association aspects of the task. With this work, we aim at paving the road for future developments of temporal LiDAR panoptic perception.
In a complex road traffic scene, illegal lane intrusion of pedestrians or cyclists constitutes one of the main safety challenges in autonomous driving application. In this paper, we propose a novel object-level phase space reconstruction network (PSRNet) for motion time series classification, aiming to recognize lane intrusion actions that occur 150m ahead through a monocular camera fixed on moving vehicle. In the PSRNet, the movement of pedestrians and cyclists, specifically viewed as an observable object-level dynamic process, can be reconstructed as trajectories of state vectors in a latent phase space and further characterized by a learnable Lyapunov exponent-like classifier that indicates discrimination in terms of average exponential divergence of state trajectories. Additionally, in order to first transform video inputs into one-dimensional motion time series of each object, a lane width normalization based on visual object tracking-by-detection is presented. Extensive experiments are conducted on the THU-IntrudBehavior dataset collected from real urban roads. The results show that our PSRNet could reach the best accuracy of 98.0%, which remarkably exceeds existing action recognition approaches by more than 30%.
Visual tracking algorithms are naturally adopted in various applications, there have been several benchmarks and many tracking algorithms, more expected to appear in the future. In this report, I focus on single object tracking and revisit the details of tracker evaluation based on widely used OTB\cite{otb} benchmark by introducing a simpler, accurate, and extensible method for tracker evaluation and comparison. Experimental results suggest that there may not be an absolute winner among tracking algorithms. We have to perform detailed analysis to select suitable trackers for use cases.
One of the central tasks of multi-object tracking involves learning a distance metric that is consistent with the semantic similarities of objects. The design of an appropriate loss function that encourages discriminative feature learning is among the most crucial challenges in deep neural network-based metric learning. Despite significant progress, slow convergence and a poor local optimum of the existing contrastive and triplet loss based deep metric learning methods necessitates a better solution. In this paper, we propose cosine-margin-contrastive (CMC) and cosine-margin-triplet (CMT) loss by reformulating both contrastive and triplet loss functions from the perspective of cosine distance. The proposed reformulation as a cosine loss is achieved by feature normalization which distributes the learned features on a hypersphere. We then propose the MOTS R-CNN framework for joint multi-object tracking and segmentation, particularly targeted at improving the tracking performance. Specifically, the tracking problem is addressed through deep metric learning based on the proposed loss functions. We propose a scale-invariant tracking by using a multi-layer feature aggregation scheme to make the model robust against object scale variations and occlusions. The MOTS R-CNN achieves the state-of-the-art tracking performance on the KITTI MOTS dataset. We show that the MOTS R-CNN reduces the identity switching by $62\%$ and $61\%$ on cars and pedestrians, respectively in comparison to Track R-CNN.