Semantic segmentation plays a pivotal role in environmental perception for autonomous driving. Video semantic segmentation (VSS) further takes temporal information into consideration for better scene parsing and tempo...
详细信息
Semantic segmentation plays a pivotal role in environmental perception for autonomous driving. Video semantic segmentation (VSS) further takes temporal information into consideration for better scene parsing and temporal consistency. Previous research on VSS is mostly dedicated to developing new techniques (e.g. optical flows, attention) to better mine temporal information. In this work, we contribute from a different angle by efficiently incorporating multi-scale temporal information. The dual spatial-temporal feature pyramid is proposed to enable the direct enhancement of multi-scale features for target frames and unlash the design of temporal information mining modules. It contains a spatial feature pyramid from a target frame and a spatial-temporal feature pyramid from multiple reference frames. Building on the dual feature pyramid, we further propose to decouple motional contexts and static contexts to fully leverage temporal information. Specifically, multi-scale motional contexts are mined with the introduced dedicated module and static contexts are enhanced by making temporally fused category-level representations interact with the target frame feature. The final segmentation maps are obtained by regarding the enhanced category-level representations as powerful feature classifiers to classify the target frame feature of rich motional contexts. Experimental results on two popular VSS benchmarks demonstrate that the proposed method with decent parameter and inference efficiency clearly outperforms previous advanced methods. IEEE
The performance and functionality of radio electronic equipment depends on various factors including external. One of them is electromagnetic interference, in particular ultra-wideband interference. The paper consider...
详细信息
In N-module motors, uniform carrier phase shifting (UCPS) by 2π/N between modules can effectively suppress torque harmonics caused by high-frequency switching of power devices. In multi-module motors with fractional-...
详细信息
This paper presents the results of a signal integrity analysis for a structure with double modal redundancy (MR) before and after failures. Two failure cases are considered: open circuit and short circuit. The study i...
详细信息
Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant *** numerous automatic detection techniques have been proposed,most o...
详细信息
Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant *** numerous automatic detection techniques have been proposed,most of them can only address part of the practical *** oscillation is heuristically defined as a visually apparent periodic ***,manual visual inspection is labor-intensive and prone to missed *** neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction *** this work,an exploration of the typical CNN models for visual oscillation detection is ***,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation *** feasibility and validity of this framework are verified utilizing extensive numerical and industrial *** with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and *** addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.
Pharmacists in conventional pharmacies and hospitals prepare and visually inspect medications before dispensing these medications to patients, thereby posing risks of exposure through skin contact or inhalation, as we...
详细信息
In this paper,the authors consider distributed convex optimization over hierarchical *** authors exploit the hierarchical architecture to design specialized distributed algorithms so that the complexity can be reduced...
详细信息
In this paper,the authors consider distributed convex optimization over hierarchical *** authors exploit the hierarchical architecture to design specialized distributed algorithms so that the complexity can be reduced compared with that of non-hierarchically distributed *** this end,the authors use local agents to process local functions in the same manner as other distributed algorithms that take advantage of multiple agents'computing ***,the authors use pseudocenters to directly integrate lower-level agents'computation results in each iteration step and then share the outcomes through the higher-level network formed by *** authors prove that the complexity of the proposed algorithm exponentially decreases with respect to the total number of *** support the proposed decomposition-composition method for agents and pseudocenters,the authors develop a class of *** operators are generalizations of the widely-used subgradient based operator and the proximal operator and can be used in distributed convex ***,these operators are closed with respect to the addition and composition operations;thus,they are suitable to guide hierarchically distributed design and ***,these operators make the algorithm flexible since agents with different local functions can adopt suitable operators to simplify their ***,numerical examples also illustrate the effectiveness of the method.
作者：
Ouyang, JinhuaChen, XuMechatronics
Automation and Control Systems Laboratory Department of Mechanical Engineering University of Washington SeattleWA98195 United States Mechatronics
Automation and Control Systems Laboratory Department of Mechanical Engineering University of Washington SeattleWA98195 United States
We present a system identification method based on recursive least-squares (RLS) and coprime collaborative sensing, which can recover system dynamics from non-uniform temporal data. Focusing on systems with fast input...
详细信息
Implementing model predictive control (MPC) in practice faces many subtle but prevalent problems, including modeling errors, solver errors, and actuator faults. In essence, the real control input applied to the system...
详细信息
暂无评论