A Multiple-Feature and Multiple-Kernel Scene Segmentation Algorithm for Humanoid Robot

2014 ◽  
Vol 44 (11) ◽  
pp. 2232-2240 ◽  
Author(s):  
Zhi Liu ◽  
Shuqiong Xu ◽  
Yun Zhang ◽  
Chun Lung Philip Chen
Keyword(s):  
Humanoid Robot ◽  
Segmentation Algorithm ◽  
Scene Segmentation ◽  
Multiple Kernel ◽  
Multiple Feature

Multi-Modality Video Scene Segmentation Algorithm with Shot Force Competition

2014 ◽  
Vol 513-517 ◽  
pp. 514-517
Author(s):  
Yun Zhu Xiang
Keyword(s):  
Segmentation Algorithm ◽  
Scene Segmentation ◽  
Full Account ◽  
Low Level ◽  
Video Scene ◽  
Video Shot ◽  
Media Data

In order to quickly and effectively segment the video scene, a multi-modality video scene segmentation algorithm with shot force competition is proposed in this paper. This method is take full account of temporal associated co-occurrence of multimodal media data, to calculate the similarity between video shot by merging the video low-level features, then go to the video scene segmentation based on the judgment method of shot competition. The authors experiments show that the video scene can be efficiently separated by the method proposed in the paper.

Edge Enhanced Traffic Scene Segmentation Algorithm with Deep Neural Network

2017 ◽  
Author(s):  
Wei Liu ◽  
Huan Tian ◽  
Jun Hu ◽  
Shuai Cheng ◽  
Huai Yuan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Segmentation Algorithm ◽  
Scene Segmentation

A scene segmentation algorithm combining the body and the edge of the object

2022 ◽  
Vol 59 (2) ◽  
pp. 102840
Author(s):  
Xianfeng Ou ◽  
Hanpu Wang ◽  
Wujing Li ◽  
Guoyun Zhang ◽  
Siyuan Chen
Keyword(s):  
The Body ◽  
Segmentation Algorithm ◽  
Scene Segmentation

A New Automatic Visual Scene Segmentation Algorithm for Flash Movie

2019 ◽  
Vol 78 (22) ◽  
pp. 31617-31632
Author(s):  
Lin Shi ◽  
Zengxiao Chi ◽  
Xiangzeng Meng
Keyword(s):  
Segmentation Algorithm ◽  
Visual Scene ◽  
Scene Segmentation ◽  
Flash Movie

scholarly journals Learning to Move an Object by the Humanoid Robots by Using Deep Reinforcement Learning

2021 ◽  
Author(s):  
Simge Nur Aslan ◽  
Burak Taşçı ◽  
Ayşegül Uçar ◽  
Cüneyt Güzeli˙ş
Keyword(s):  
Reinforcement Learning ◽  
Humanoid Robot ◽  
Semantic Segmentation ◽  
Humanoid Robots ◽  
Target Object ◽  
Segmentation Algorithm ◽  
Experimental Setup ◽  
Policy Gradient ◽  
Continuous Actions ◽  
Head Positions

This paper proposes an algorithm for learning to move the desired object by humanoid robots. In this algorithm, the semantic segmentation algorithm and Deep Reinforcement Learning (DRL) algorithms are combined. The semantic segmentation algorithm is used to detect and recognize the object be moved. DRL algorithms are used at the walking and grasping steps. Deep Q Network (DQN) is used to walk towards the target object by means of the previously defined actions at the gate manager and the different head positions of the robot. Deep Deterministic Policy Gradient (DDPG) network is used for grasping by means of the continuous actions. The previously defined commands are finally assigned for the robot to stand up, turn left side and move forward together with the object. In the experimental setup, the Robotis-Op3 humanoid robot is used. The obtained results show that the proposed algorithm has successfully worked.

Sign in / Sign up

Export Citation Format

Share Document