Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL

TL;DR

This paper introduces an open-source dataset and benchmarking pipeline for real-time object detection in RoboCup Small Size League, demonstrating the effectiveness of optimized CNN models on embedded systems.

Contribution

It provides the first dedicated dataset and benchmarking framework for SSL object detection, along with a pipeline for training, deploying, and evaluating CNN models on low-power embedded devices.

Findings

MobileNet SSD v1 achieves 44.88% AP at 94 FPS on SSL robots.

The dataset enables benchmarking of real-time detection models in SSL.

The pipeline facilitates deployment of CNNs on embedded systems.

Abstract

When producing a model to object detection in a specific context, the first obstacle is to have a dataset labeling the desired classes. In RoboCup, some leagues already have more than one dataset to train and evaluate a model. However, in the Small Size League (SSL), there is not such dataset available yet. This paper presents an open-source dataset to be used as a benchmark for real-time object detection in SSL. This work also presented a pipeline to train, deploy, and evaluate Convolutional Neural Networks (CNNs) models in a low-power embedded system. This pipeline was used to evaluate the proposed dataset with state-of-art optimized models. In this dataset, the MobileNet SSD v1 achieves 44.88% AP (68.81% AP50) at 94 Frames Per Second (FPS) while running on an SSL robot.