Share This Author
Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking
- Chenglong Li, Hui Cheng, Shiyi Hu, Xiaobai Liu, Jin Tang, Liang Lin
- Computer ScienceIEEE Transactions on Image Processing
- 1 December 2016
An adaptive fusion scheme is proposed based on collaborative sparse representation in Bayesian filtering framework and jointly optimize sparse codes and the reliable weights of different modalities in an online way to perform robust object tracking in challenging scenarios.
An autonomous vision-based target tracking system for rotorcraft unmanned aerial vehicles
- Hui Cheng, Lishan Lin, Zhuoqi Zheng, Yuwei Guan, Zhongchang Liu
- Engineering, Computer ScienceIEEE/RSJ International Conference on Intelligent…
- 1 September 2017
Experimental results show that the proposed computationally efficient visual tracking scenario can stably track a maneuvering target and is robust to target occlusions and loss.
Autonomous coordinated control of a platoon of vehicles with multiple disturbances
This study studies coordinated control of a platoon of vehicles consisting of a leader and multiple followers when multiple vehicles suffer from disturbances. Small disturbances acting on one vehicle…
Image-to-Video Person Re-Identification With Temporally Memorized Similarity Learning
- Dongyu Zhang, Wenxi Wu, Hui Cheng, Ruimao Zhang, Zhenjiang Dong, Zhaoquan Cai
- Computer ScienceIEEE Transactions on Circuits and Systems for…
- 1 October 2018
A novel temporally memorized similarity learning neural network is proposed for the image-to-video person re-id problem, in which the probe is an image and the gallery is consists of videos captured by nonoverlapping cameras.
Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning
- Keze Wang, Shengfu Zhai, Hui Cheng, Xiaodan Liang, Liang Lin
- Computer ScienceACM Multimedia
- 13 August 2016
This paper proposes a novel inference-embedded multi-task learning framework for predicting human pose from still depth images, which is implemented with a deep architecture of neural networks, and shows that the proposed deep model significantly improves the accuracy of human pose estimation over other several state-of-the-art methods or SDKs.
Decentralized navigation of multiple agents based on ORCA and model predictive control
- Hui Cheng, Qiyuan Zhu, Zhongchang Liu, Tianye Xu, Liang Lin
- EngineeringIEEE/RSJ International Conference on Intelligent…
- 1 September 2017
This paper presents a decentralized strategy for collision-free navigation of multiple agents that combines the Optimal Reciprocal Collision Avoidance (ORCA) algorithm and Model Predictive Control (MPC) and shows that this new algorithm can reduce velocity vibrations in the traditional ORCA algorithm.
On the Over-Smoothing Problem of CNN Based Disparity Estimation
- Chuangrong Chen, Xiaozhi Chen, Hui Cheng
- Computer ScienceIEEE/CVF International Conference on Computer…
- 1 October 2019
This work proposes a single-modal weighted average operation on the probability distribution during inference, which can alleviate the problem of over-smoothing at boundaries effectively and proposes a novel metric that measures the disparity error in the local structure of edge boundaries.
MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network
- Junhao Cai, Hui Cheng, Zhanpeng Zhang, Jingcheng Su
- Computer ScienceInternational Conference on Robotics and…
- 18 February 2019
A novel grasp training system including the whole pipeline from data collection to model inference, which can collect effective grasp sample with a corrective strategy assisted by antipodal grasp rule, and an affordance interpreter network to predict pixelwise grasp affordance map is presented.
Autonomous Vision-Based Aerial Grasping for Rotorcraft Unmanned Aerial Vehicles
The experimental results illustrate that the proposed vision-based aerial grasping system can autonomously and reliably grasp the target object while working entirely onboard.
PPR-Net:Point-wise Pose Regression Network for Instance Segmentation and 6D Pose Estimation in Bin-picking Scenarios
- Zhi-Kai Dong, Sicheng Liu, Houde Liu
- Computer ScienceIEEE/RSJ International Conference on Intelligent…
- 1 November 2019
A simple but novel Point-wise Pose Regression Network (PPR-Net), where for each point in the point cloud, the network regresses a 6D pose of the object instance that the point belongs to, which works well in real world robot bin-picking tasks.