A5071996752- Video Surveillance and Tracking Methods
- Robotics and Automated Systems
- Advanced Image and Video Retrieval Techniques
- Infrared Target Detection Methodologies
- Advanced Image Fusion Techniques
- Robotic Path Planning Algorithms
- Visual Attention and Saliency Detection
- Robotics and Sensor-Based Localization
Beijing University of Technology
2014-2015
Beijing Academy of Artificial Intelligence
2015
A novel mobile robots 3D-perception obstacle regions method in indoor environment based on Improved Salient Region Extraction (ISRE) is proposed. This model acquires the original image by Kinect sensor and then gains Original Salience Map (OSM) Intensity Feature (IFM) from salience filtering algorithm. The IFM was used as input neutron of PCNN. In order to make ignition range more exact, PCNN pulse further improved follows: point multiplication algorithm taken between internal neuron...
This paper proposes a distributed intelligent assistant robotic system in order to improve the quality of elderly people's life population aging society. The is composed embedded sensor networks and multirobot platform. In proposed system, we use SP 2 ATM (simultaneous path planning topological mapping) with RBPF (Rao-Blackwellized particle filter) for localization mobile robots. perform service tasks, an accurate reliable 3D environment map reconstructed by using effective reconstruction...
Visual object tracking is a fundamental research topic in computer vision. In this paper, we proposed novel hybrid method based on Pulse Coupled Neural Network (PCNN) and Multiple Instance Learning (MIL). Most modern trackers may be inaccurate when the training samples are imprecise which causes drift. To resolve these problems, MIL introduced into task, can alleviate drift to some extent. However, tracker detect positive sample that less important. PCNN different from traditional artificial...