arXiv subjects

Yifu Zhang

Publications and source records attributed to Yifu Zhang.

28 records · Page 2Linked to original sources

arXiv2021

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT.

cs.CV↗

arXiv2021

VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment. In contrast to previous efforts which require to establish cross-view correspondence based on noisy 2D pose estimates, it directly estimates and tracks 3D poses from a 3D voxel-based representation constructed from multi-view images. We first discretize the 3D space by regular voxels and compute a feature vector for each voxel by averaging the body joint heatmaps that are inversely projected from all views. We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint. Similarly, a Re-ID feature is computed for each voxel which is used to track the estimated 3D poses over time. The main advantage of the approach is that it avoids making any hard decisions based on individual images. The approach can robustly estimate and track 3D poses even when people are severely occluded in some cameras. It outperforms the state-of-the-art methods by a large margin on three public datasets including Shelf, Campus and CMU Panoptic.

cs.CV↗

arXiv2020

Type II Finite time blow-up for the three dimensional energy critical heat equation

We consider the following Cauchy problem for three dimensional energy critical heat equation \begin{equation*} \begin{cases} u_t=Δu+u^{5},~&\mbox{ in } \ {\mathbb R}^3 \times (0,T),\\ u(x,0)=u_0(x),~&\mbox{ in } \ {\mathbb R}^3. \end{cases} \end{equation*} We construct type II finite time blow-up solution $u(x,t)$ with the blow-up rates $ \| u\|_{L^\infty} \sim (T-t)^{-k}$, where $ k=1,2,... $. This gives a rigorous proof of the formal computations by Filippas, Herrero and Velazquez \cite{fhv}. This is the first instance of type II finite time blow-up for three dimensional energy critical heat equation.

math.AP↗

arXiv2020

Distributed bilayered control for transient frequency safety and system stability in power grids

This paper considers power networks governed by swing nonlinear dynamics and subject to disturbances. We develop a bilayered control strategy for a subset of buses that simultaneously guarantees transient frequency safety of each individual bus and asymptotic stability of the entire network. The bottom layer is a model predictive controller that, based on periodically sampled system information, optimizes control resources to have transient frequency evolve close to a safe desired interval. The top layer is a real-time controller assisting the bottom-layer controller to guarantee transient frequency safety is actually achieved. We show that control signals at both layers are Lipschitz in the state and do not jeopardize stability of the network. Furthermore, we carefully characterize the information requirements at each bus necessary to implement the controller and employ saddle-point dynamics to introduce a distributed implementation that only requires information exchange with up to 2-hop neighbors in the power network. Simulations on the IEEE 39-bus power network illustrate our results.

eess.SY↗

arXiv2019

Model predictive control for transient frequency regulation of power networks

This paper introduces a control strategy to simultaneously achieve asymptotic stabilization and transient frequency regulation of power networks. The control command is generated by iteratively solving an open-loop control cost minimization problem with stability and transient frequency constraints. To deal with the non-convexity of the stability constraint, we propose a convexification strategy that uses a reference trajectory based on the system's current state. We also detail how to employ network partitions to implement the proposed control strategy in a distributed way, where each region only requires system information from neighboring regions to execute its controller.

eess.SY↗

arXiv2018

Double-layered distributed transient frequency control with regional coordination for power networks

This paper proposes a control strategy for power systems with a two-layer structure that achieves global stabilization and, at the same time, delimits the transient frequencies of targeted buses to a desired safe interval. The first layer is a model predictive control that, in a receding horizon fashion, optimally allocates the power resources while softly respecting transient frequency constraints. As the first layer control requires solving an optimization problem online, it only periodically samples the system state and updates its action. The second layer control, however, is implemented in real time, assisting the first layer to achieve frequency invariance and attractivity requirements.We show that the controllers designed at both layers are Lipschitz in the state. Furthermore, through network partition, they can be implemented in a distributed fashion, only requiring system information from neighboring partitions. Simulations on the IEEE 39-bus network illustrate our results.

eess.SY↗

arXiv2018

Distributed Transient Frequency Control for Power Networks with Stability and Performance Guarantees

This paper proposes a distributed strategy regulated on a subset of individual buses in a power network described by the swing equations to achieve transient frequency control while preserving asymptotic stability. Transient frequency control refers to the ability to maintain the transient frequency of each bus of interest in a given safe region, provided it is initially in it, and ii) if it is initially not, then drive the frequency to converge to this region within a finite time, with a guaranteed convergence rate. Building on Lyapunov stability and set invariance theory, we formulate the stability and the transient frequency requirements as two separate constraints for the control input. Our design synthesizes a controller that satisfies both constraints simultaneously. The controller is distributed and Lipschitz, guaranteeing the existence and uniqueness of the trajectories of the closed-loop system. We further bound its magnitude and demonstrate its robustness against measurement inaccuracies. Simulations on the IEEE 39-bus power network illustrate our results.

eess.SY↗

arXiv2018

Transient frequency control with regional cooperation for power networks

This paper proposes a centralized and a distributed sub-optimal control strategy to maintain in safe regions the real-time transient frequencies of a given collection of buses, and simultaneously preserve asymptotic stability of the entire network. In a receding horizon fashion, the centralized control input is obtained by iteratively solving an open-loop optimization aiming to minimize the aggregate control effort over controllers regulated on individual buses with transient frequency and stability constraints. Due to the non-convexity of the optimization, we propose a convexification technique by identifying a reference control input trajectory. We then extend the centralized control to a distributed scheme, where each subcontroller can only access the state information within a local region. Simulations on a IEEE-39 network illustrate our results.

eess.SY↗

arXiv2018

Distributed transient frequency control in power networks

Modern power networks face increasing challenges in controlling their transient frequency behavior at acceptable levels due to low inertia and highly-dynamic units. This paper presents a distributed control strategy regulated on a subset of buses in a power network to maintain their transient frequencies in safe regions while preserving asymptotic stability of the overall system. Building on Lyapunov stability and set invariance theory, we formulate the transient frequency requirement and the asymptotic stability requirement as two separate constraints for the control input. Hereby, for each bus of interest, we synthesize a controller satisfying both constraints simultaneously. The controller is distributed and Lipschitz, guaranteeing the existence and uniqueness of the trajectories of the closed-loop system. Simulations on the IEEE 39-bus power network illustrate the results.

eess.SY↗

arXiv2010

A new sufficient condition for sum-rate tightness in quadratic Gaussian multiterminal source coding

This work considers the quadratic Gaussian multiterminal (MT) source coding problem and provides a new sufficient condition for the Berger-Tung sum-rate bound to be tight. The converse proof utilizes a set of virtual remote sources given which the MT sources are block independent with a maximum block size of two. The given MT source coding problem is then related to a set of two-terminal problems with matrix-distortion constraints, for which a new lower bound on the sum-rate is given. Finally, a convex optimization problem is formulated and a sufficient condition derived for the optimal BT scheme to satisfy the subgradient based Karush-Kuhn-Tucker condition. The set of sum-rate tightness problems defined by our new sufficient condition subsumes all previously known tight cases, and opens new direction for a more general partial solution.

cs.IT↗