Changes

Jump to: navigation, search

ML-TN-002 - Real-time Social Distancing estimation

301 bytes added, 15:54, 27 January 2021
Main application
As stated previously, the main application derives from the IIT Social-Distancing project. It was developed in several steps starting when only a few alpha samples of the i.MX8M Plus were available.
==== Step #1 ====
The first step was conducted using the official evaluation kit (EVK) by NXP. Its goal was to make the Social-Distancing project to work on the new platform maintaining the core functionalities. In essence, the code was modified in order to replace the [https://github.com/CMU-Perceptual-Computing-Lab/openpose OpenPose library] with [https://github.com/tensorflow/tfjs-models/tree/master/posenet PoseNet]. This was required to cope with the operations actually supported by the [https://www.nxp.com/design/software/development-software/eiq-ml-development-environment:EIQ NXP eIQ] software stack and the NPU. For those who are familiar with embedded software development, this should be unsurprising. When porting applications from PC-like platforms to embedded platforms, handling such hardware/software constraints is a common practice.
The resulting processing pipeline is shown in the following figure.
 
[[File:Ss-main-pipeline-20210127.png|center|thumb|600x600px|Processing pipeline]]
The following screenshots show the application running on the EVK.
[[File:Social-distancing-screenshot1.png|center|thumb|600x600px|captionThe step 1 application running on the EVK (1/2)]] [[File:Social-distancing-screenshot2.png|center|thumb|600x600px|The step 1 application running on the EVK (2/2)]]
[[File:Social-distancing-screenshot2==== Step #2 ====Step #2 concerned implementing some optimizations in order to increase the overall frame rate.png|center|thumb|600x600px|c]]
== Testing and results ==
4,650
edits

Navigation menu