An edge detection framework conjoining with IMU data for assisting indoor navigation of visually impaired persons

作者：

Highlights：

• A framework with IMU is proposed to aid object detections for moving camera.

• It overcomes existing approaches that cannot detect contaminated image edges.

• It overcomes deblurring algorithms that are not suitable for real‐time implementation.

• Its topological structure is adapted continuously for changing indoor environment.

• Results show it is a strong candidate for reliable real‐time navigation.

摘要

•A framework with IMU is proposed to aid object detections for moving camera.•It overcomes existing approaches that cannot detect contaminated image edges.•It overcomes deblurring algorithms that are not suitable for real‐time implementation.•Its topological structure is adapted continuously for changing indoor environment.•Results show it is a strong candidate for reliable real‐time navigation.

论文关键词：Edge detection,Sigmoid function,Particle swarm optimization,Smartphone navigation,Vision impaired persons,Inertial measurement unit (IMU)

论文评审过程：Received 20 June 2016, Revised 18 August 2016, Accepted 5 September 2016, Available online 15 September 2016, Version of Record 5 October 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.09.007