Deep Learning for Semantic Segmentation on Minimal Hardware

RoboCup is one of the major global AI events, gathering hundreds of teams from the world’s best universities to compete in various tasks ranging from soccer to home assistance and rescue. The commonality of these three seemingly dissimilar tasks is that in order to perform well, the robot needs to excel at the all major AI tasks: perception, control, navigation, strategy and planning. In this work, we focus on the first of these by presenting what is—to our knowledge—the first fully neural vision system for the Nao robot soccer. This is a challenging task, mainly due to the limited computational capabilities of the Nao robot. In this paper, we propose two novel neural network architectures for semantic segmentation and object detection that ensure low-cost inference, while improving accuracy by exploiting the properties of the environment. These models use synthetic transfer learning to be able to learn from a low number of hand-labeled images. The experiments show that our models outperform state-of-the-art methods such as Tiny YOLO at a fraction of the cost.

show abstract

“…al. [16]. First, we created 5000 test images, using 500 scene parameter (carpet color, lighting, color temperature, etc.)…”

Section: Datasetmentioning

confidence: 99%

“…One of the most important advances of recent years is the work published by Hess et al [16] in which they present a high-quality virtual RoboCup environment created with Unreal Engine TM . This scene generation enables anyone to create large datasets of realistic images of a soccer field along with pixel-level semantic labeling.…”

Section: Introductionmentioning

confidence: 99%

Fully neural object detection solutions for robot soccer

Szemenyei

Estivill‐Castro

2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…It achieved near real-time performance on a modern CPU without processing other tasks of the robot. In [7] a more efficient encoder-decoder architecture is proposed that maps an input image into a full-resolution pixelwise classification. To decrease the computation load they have used depthwise separable convolutions and removed skip connections.…”

Section: Related Workmentioning

confidence: 99%

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

Teimouri

Delavaran

Rezaei

2019

RoboCup 2019: Robot World Cup XXIII

View full text Add to dashboard Cite

Ball detection is one of the most important tasks in the context of soccer-playing robots. The ball is a small moving object which can be blurred and occluded in many situations. Several neural network based methods with different architectures are proposed to deal with the ball detection. However, they are either neglecting to consider the computationally low resources of humanoid robots or highly depend on manually-tuned heuristic methods to extract the ball candidates. In this paper, we propose a new ball detection method for low-cost humanoid robots that can detect most soccer balls with a high accuracy rate of up to 97.17%. The proposed method is divided into two steps. First, some coarse regions that may contain a full ball are extracted using an iterative method employing an efficient integral image based feature. Then they are fed to a lightweight convolutional neural network to finalize the bounding box of a ball. We have evaluated the proposed approach using a comprehensive dataset and the experimental results show the efficiency of our method.

show abstract

“…In [12] authors use geometric properties of the scene to create graph-structured FCN. In [6] authors proposed a modification of U-Net [20] architecture by removing skip connections from encoder to decoder and using depthwise separable convolution. This allows to achieve improvement in inference time and making it the right choice for real-time systems.…”

Section: Related Workmentioning

confidence: 99%

Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking

Kukleva

Khan

Farazi

et al. 2019

RoboCup 2019: Robot World Cup XXIII

View full text Add to dashboard Cite

Soccer ball detection is identified as one of the critical challenges in the RoboCup competition. It requires an efficient vision system capable of handling the task of detection with high precision and recall and providing robust and low inference time. In this work, we present a novel convolutional neural network (CNN) approach to detect the soccer ball in an image sequence. In contrast to the existing methods where only the current frame or an image is used for the detection, we make use of the history of frames. Using history allows to efficiently track the ball in situations where the ball disappears or gets partially occluded in some of the frames. Our approach exploits spatio-temporal correlation and detects the ball based on the trajectory of its movements. We present our results with three convolutional methods, namely temporal convolutional networks (TCN), ConvLSTM, and ConvGRU. We first solve the detection task for an image using fully convolutional encoder-decoder architecture, and later, we use it as an input to our temporal models and jointly learn the detection task in sequences of images. We evaluate all our experiments on a novel dataset prepared as a part of this work. Furthermore, we present empirical results to support the effectiveness of using the history of the ball in challenging scenarios.

show abstract

Deep Learning for Semantic Segmentation on Minimal Hardware

Cited by 15 publications

References 16 publications

Fully neural object detection solutions for robot soccer

Fully neural object detection solutions for robot soccer

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking

Contact Info

Product

Resources

About