MARIO: Modular and Extensible Architecture for Computing Visual Statistics in RoboCup SPL (2022-09-20T00:00:00.000000Z)

Abstract

This technical report describes a modular and extensible architecture for computing visual statistics in RoboCup SPL (MARIO), presented during the SPL Open Research Challenge at RoboCup 2022, held in Bangkok (Thailand). MARIO is an open-source, ready-to-use software application whose final goal is to contribute to the growth of the RoboCup SPL community. MARIO comes with a GUI that integrates multiple machine learning and computer vision based functions, including automatic camera calibration, background subtraction, homography computation, player + ball tracking and localization, NAO robot pose estimation and fall detection. MARIO has been ranked no. 1 in the Open Research Challenge.

Authors

D. Bloisi

1 papers

A. Pennisi

1 papers

Cristian Zampino

1 papers

Abstract

Authors

References29 items

StrongSORT: Make DeepSORT Great Again

A Survey of Modern Deep Learning based Object Detection Models

Estimation

OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields

Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

Deep Cosine Metric Learning for Person Re-identification

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Parallel multi-modal background modeling

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Simple online and realtime tracking with a deep association metric

Simple online and realtime tracking

You Only Look Once: Unified, Real-Time Object Detection

RoboCup . Objective

Performance Study of Multi-target Tracking Using Kalman Filter and Hungarian Algorithm

Data Driven Research and Development in RoboCup Collection, Organization and Analysis of RoboCup Game Data

Independent multimodal background subtraction

The Kalman Filter

System Dependencies

A cost matrix is computed as the Intersection-over-Union (IoU) distance between each detection and all the predicted bounding boxes from the existing targets

No such file or directory: ’python’ – Solution : change the value python in python3 in Preparation

Addendum: Environment Setup and Codebase Prerequisities

Data Association and Statistics. Game data containing player and ball information is extracted and used to compute the statistics of the game

In order to setup the Docker repository, run the following commands: $ echo "deb [arch=$(dpkg --print-architecture) \ signed-by=/etc/apt/keyrings/docker

Spatial conﬁguration

IMBS-MT is designed for performing an accurate foreground extraction in real-time for full-HD images

Build and Setup Docker image. In order to build and setup the Docker image, run the following commands: References

quality and reduces time consumption

RoboCup Technical Committee

• the content of this folder in MARIO-docker/MARIO/video

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names