Active Object Detection Using Double DQN and Prioritized Experience Replay

Visual object detection is one of the fundamental tasks in computer vision and robotics. Small scale, partial capture and occlusion often occur in robotic applications, most existing object detection algorithms perform poorly in such situations. While a robot can look at one object from different vi...

Full description

Saved in:
Bibliographic Details
Published in2018 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 7
Main Authors Han, Xiaoning, Liu, Huaping, Sun, Fuchun, Yang, Dongfang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2018
Subjects
Collision avoidance
Feature extraction
Object detection
Robots
Task analysis
Training
Visualization
Online AccessGet full text

Cover

More Information
Summary:Visual object detection is one of the fundamental tasks in computer vision and robotics. Small scale, partial capture and occlusion often occur in robotic applications, most existing object detection algorithms perform poorly in such situations. While a robot can look at one object from different views and plan its trajectory in the next few steps, which can lead to better observations. We formulate it as a sequential action-decision process, and develop a deep reinforcement learning architecture to solve the active object detection problem. A double deep Q-learning network (DQN) is applied to predict an action at each step. Experimental validation on the Active Vision Dataset shows the efficiency of the proposed method.
ISSN:2161-4407
DOI:10.1109/IJCNN.2018.8489296