Italy

ICPR 2020

Hardware-software Implementation of quantised Siamese Neural Networks for Energy Efficient Real-Time Object Tracking – a demo

energy efficiency

tracking

siamese neural network

real-time

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


demo

J.K. Aggarwal Award: Abhinav Gupta

Breathing rate together with heart rate, blood pressure,
and body temperature, are considered as essential and vital
signs of human body. In this demo, we present a novel system to
estimate the respiratory rate using a low-cost, non-intrusive, and
passive infrared thermopile sensor array. The thermopile sensor
array can detect the thermal infrared energy and generate a
low-resolution video from subjects within its viewing range. We
collected low resolution 8 8-pixel thermal video clips from 40
subjects at resting position from a distance of one-meter between
the thermopile sensor array and the subjects. We processed
the image frames using Haar-like filters and generated a one-dimensional
feature signal from each video. The signal exhibits
an almost periodic behavior following the respiratory movements.
A peak detection algorithm is used to detect each breath. The
proposed method is computationally efficient because it is based
on multiplierless Haar-type feature extraction and peak detection.
We achieved a high positive correlation rate of 97.77% between
the actual respiratory rate that was measured by monitoring
the chest movements during inhalation and exhalation and the
estimated rate in our dataset. We will demonstrate this IR array
based respiration rate detection system during the demo session.

Respiratory rate estimation using a low-resolution infrared sensor array

Direct Motion Segmentation from Emulated Asynchronous Camera Events

A Fully Automated Process for Semiconductor Technology Analysis through SEM Cross-Sections

BOE Digital Human: Visualize Your Life Data

Multimodal trajectory prediction in the CARLA simulator

Semantic Segmentation for Pedestrian Detection from Motion in Temporal Domain

Suspicious Activity Detection

Inter-Homines: Distance-Based Risk Estimation

Autonomous Platform based on Small-Scale Car for Versatile Data Collection and Algorithm Verification

technical paper

https://d3smihljt9218e.cloudfront.net/transcript/9544/subtitle/6bfaab3c7a1917b744d6c20238f5197c.vtt

English (automatic)

Premium content

Hardware-software Implementation of quantised Siamese Neural Networks for Energy Efficient Real-Time Object Tracking – a demo

Downloads

Next from ICPR 2020

J.K. Aggarwal Award: Abhinav Gupta

Similar lecture

Real-time Pedestrian Lane Detection for Assistive Navigation using Neural Architecture Search