Abstract
Neuromorphic Vision Datasets for Pedestrian Detection, Action Recognition, and Fall Detection.
Highlights
Large-scale public datasets are vital for algorithm development in the computer vision field
We introduce three new neuromorphic vision datasets recorded by a novel neuromorphic vision sensor named Dynamic Vision Sensors (DVS) (Lichtsteiner et al, 2008)
For the Frequence encoding method, the edges of the object will be strengthened to a great extent, which is beneficial for object detection as we have a clearer profile of the object
Summary
Large-scale public datasets are vital for algorithm development in the computer vision field. UCF 101 (Soomro et al, 2012) is another large-scale dataset used for human action recognition. Both of the above datasets provide only the appearance information of objects in the scene. Not surprisingly, increasing RGB-D datasets, recorded by the Kinect sensor and dedicated to a wide range of applications, have become available (Cai et al, 2017). It is clear that the advent of new sensors always brings opportunities for new dataset development In this data report, we introduce three new neuromorphic vision datasets recorded by a novel neuromorphic vision sensor named Dynamic Vision Sensors (DVS) (Lichtsteiner et al, 2008)
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call