Abstract
CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening
Highlights
The ability to detect the presence of people or other objects in three dimensional data is an important factor in enabling autonomy and automation in environments where machinery and humans are both present
Several approaches for people detection exist, where the problem of detecting people and other objects in 2D images is well documented in the academic literature, especially methods composing different types of machine learning such as Histograms of Oriented Gradients (HOG) Dalal and Triggs (2005) and convolutional neural networks (CNNs)
Much research has been done on methods for detection in data from 2D and 3D lidars typically found on autonomous vehicles and mobile robots
Summary
The ability to detect the presence of people or other objects in three dimensional data is an important factor in enabling autonomy and automation in environments where machinery and humans are both present. A natural example is in the automotive industry, where autonomous vehicles must be able to accurately perceive their surroundings. Another example is in any industrial environment where robotic machinery must coexist with personnel, whether it is on a large offshore platform or in a small indoor robotic cell. Much research has been done on methods for detection in data from 2D and 3D lidars typically found on autonomous vehicles and mobile robots. A 3D lidar was used in Spinello et al (2011), where a bottom-up, topdown detector was used to select hypothetical candidates and perform validation on a tessellated volume, respectively
Sign-in/Register to view highlights & summary 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 callMore From: Modeling, Identification and Control: A Norwegian Research Bulletin
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
