Zhenping Sun
YOU?
Author Swipe
View article: Road Similarity-Based BEV-Satellite Image Matching for UGV Localization
Road Similarity-Based BEV-Satellite Image Matching for UGV Localization Open
To address the challenge of autonomous UGV localization in GNSS-denied off-road environments,this study proposes a matching-based localization method that leverages BEV perception image and satellite map within a road similarity space to a…
View article: Regulation of cytoskeleton dynamics and its interplay with force in plant cells
Regulation of cytoskeleton dynamics and its interplay with force in plant cells Open
The plant cytoskeleton is an intricate network composed of actin filaments and microtubules. The cytoskeleton undergoes continuous dynamic changes that provide the basis for rapidly responding to intrinsic and extrinsic stimuli, including …
View article: SceneTracker: Long-term Scene Flow Estimation Network
SceneTracker: Long-term Scene Flow Estimation Network Open
Considering that scene flow estimation has the capability of the spatial domain to focus but lacks the coherence of the temporal domain, this study proposes long-term scene flow estimation (LSFE), a comprehensive task that can simultaneous…
View article: Extended Guided Filter: Simultaneous Noise Suppression and Details Enhancement
Extended Guided Filter: Simultaneous Noise Suppression and Details Enhancement Open
Guided image filter implicitly balances noise and details based on local variance, achieving noise suppression while preserving prominent edges. However, we have observed limitations in using variance to distinguish between noise and image…
View article: Evolution of the thermostability of actin-depolymerizing factors enhances the adaptation of pollen germination to high temperature
Evolution of the thermostability of actin-depolymerizing factors enhances the adaptation of pollen germination to high temperature Open
Double fertilization in many flowering plants (angiosperms) often occurs during the hot summer season, but the mechanisms that enable angiosperms to adapt specifically to high temperatures are largely unknown. The actin cytoskeleton is ess…
View article: Mechanical regulation of cortical microtubules in plant cells
Mechanical regulation of cortical microtubules in plant cells Open
Summary All living organisms are subjected to mechanical forces at all times. It has been reported that mechanics regulate many key cellular processes, including cell polarity establishment, cell division and gene expression, as a physical…
View article: SplatFlow: Learning Multi-frame Optical Flow via Splatting
SplatFlow: Learning Multi-frame Optical Flow via Splatting Open
The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in par…
View article: Towards a Fully Automated 3D Reconstruction System Based on LiDAR and GNSS in Challenging Scenarios
Towards a Fully Automated 3D Reconstruction System Based on LiDAR and GNSS in Challenging Scenarios Open
High-precision 3D maps play an important role in autonomous driving. The current mapping system performs well in most circumstances. However, it still encounters difficulties in the case of the Global Navigation Satellite System (GNSS) sig…
View article: Synchronous Maneuver Searching and Trajectory Planning for Autonomous Vehicles in Dynamic Traffic Environments
Synchronous Maneuver Searching and Trajectory Planning for Autonomous Vehicles in Dynamic Traffic Environments Open
In the real-time decision-making and local planning process of autonomous vehicles in dynamic environments, the autonomous driving system may fail to find a reasonable policy or even gets trapped in some situation due to the complexity of …
View article: Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion Open
It is challenging to achieve robust lane detection based on a single frame, particularly when complicated driving scenarios are present. A novel approach based on multiple frames is proposed in this paper by taking advantage of the fusion …
View article: Multi-Stage Hough Space Calculation for Lane Mark Detection via IMU and Vision Data Fusion
Multi-Stage Hough Space Calculation for Lane Mark Detection via IMU and Vision Data Fusion Open
It's challenging to achieve robust lane detection depending on single frame when considering complicated scenarios. In order to detect more credible lane markings by using sequential frames, a novel approach to fusing vision and Inertial M…
View article: Distance Estimation of Monocular Based on Vehicle Pose Information
Distance Estimation of Monocular Based on Vehicle Pose Information Open
In order to measure the distance between our vehicle and the target vehicle by monocular vision and eliminate the estimation error bring by changing of vehicle pose, we propose the distance estimation method based on the vehicle pose infor…
View article: Multi-robot Simultaneous Localization and Mapping based on Pose Graphs Fusion
Multi-robot Simultaneous Localization and Mapping based on Pose Graphs Fusion Open
This paper describes an efficient method for multi-robot simultaneous localization and mapping (SLAM), which establishes a joint model of multi-robot pose graphs based on several special inner and outer loop points called conjunction point…
View article: An adaptive longitudinal control method for autonomous follow driving based on neural dynamic programming and internal model structure
An adaptive longitudinal control method for autonomous follow driving based on neural dynamic programming and internal model structure Open
Autonomous vehicles are considered to have great potentials in improving transportation safety and efficiency. Autonomous follow driving is one of the highly probable application forms of autonomous vehicles in the near future. In this art…
View article: Parameterized Batch Reinforcement Learning for Longitudinal Control of Autonomous Land Vehicles
Parameterized Batch Reinforcement Learning for Longitudinal Control of Autonomous Land Vehicles Open
This paper presents a parameterized batch reinforcement learning algorithm for near-optimal longitudinal control of autonomous land vehicles (ALVs). The proposed approach uses an actor-critic architecture, where parameterized feature vecto…