A5100381940- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Ecology and Vegetation Dynamics Studies
- Robot Manipulation and Learning
- Image Processing Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Recommender Systems and Techniques
- Wildlife Ecology and Conservation
- Urban, Neighborhood, and Segregation Studies
- Soil Carbon and Nitrogen Dynamics
- Forest Management and Policy
- Evaluation Methods in Various Fields
- Plant Water Relations and Carbon Dynamics
- Medical Image Segmentation Techniques
- Impact of Light on Environment and Health
- Place Attachment and Urban Studies
- Community Health and Development
- Advanced Vision and Imaging
- Advanced Decision-Making Techniques
- Advanced Neural Network Applications
- Hand Gesture Recognition Systems
- Toxic Organic Pollutants Impact
- Mercury impact and mitigation studies
Institute of Psychology, Chinese Academy of Sciences
2021
University of Chinese Academy of Sciences
2011-2021
Chinese Academy of Sciences
2011-2020
Suzhou Institute of Biomedical Engineering and Technology
2020
Institute of Botany
2018
Shenyang Institute of Automation
2016-2017
Xidian University
2015-2016
South China Botanical Garden
2011
Accurate robot grasp detection for model free objects plays an important role in robotics. With the development of RGB-D sensors, object perception technology has made great progress. Reach feature expression by colour and depth data is a critical problem that needs to be addressed order accomplish grasping task. To solve fusion, this paper proposes convolutional neural networks (CNN) based approach combined with regression classification. In CNN model, modal are deeply fused together...
This paper introduces a dual-layer density estimation-based architecture for multiple object instance detection in robot inventory management applications. The approach consists of raw scale-invariant feature transform (SIFT) matching and key point projection. dominant scale ratio reference clustering threshold are estimated using the first layer estimation. A cascade filters is applied after template reconstruction refined to eliminate false matches. Before second estimation, adaptive...
The recommendation system could mine the user's behavior operation data and provide different personalized services for users. problems of inaccurate incomplete description patients' needs in internet medical service have brought great challenges to service. This paper takes field as research object improve collaborative filtering algorithm system. Firstly, static evaluation model based on doctor entity hospital is established by using Analytic Hierarchy Process (AHP) realize initial...
This paper proposes a new frame which combines kernel density estimation with convex quadrilateral verification to achieve identification and localization of object instance in zooming image. Reference centers are first calculated based on scales, orientations, reference vectors for all matched key points. Then the valid center peak value is held. A region interest evaluated radius confirmed scale point row column number corresponding training Homography matrix computed using points within...
Administrators, public workers, and researchers are continuously seeking ways to improve cooperative behaviors from citizens. Place identity, or people's identification of belonging a certain place, is quite important for these behaviors. However, existing research studies have made inconsistent claims about whether there was an effect place identity on local In this study, we try reconcile the ambivalent conclusions by taking organizational (i.e., subsociety closely linked daily life) into...
The social security prevention and control is a process of dynamic management, which possesses three characteristics strategy, integration systematicness. It difficult to achieve the optimal input-output ratio in absence optimization working structure. In this paper, we proposed structure strategy public based on analytic hierarchy (AHP). Firstly, four basic elements (i.e., people, case, time space) impacting were extracted. And then driving modes under different structures concluded....