Comparison of Encoder-Decoder Networks for Soccer Field Segmentation

• Otávio H. R. Guimarães Institut Polytechnique de Paris Route de Saclay
• Marcos R. O. A. Maximo ITA
• Jose Maria Parente de Oliveira ITA

Resumo

Convolutional neural networks consist of state-of the-art models used for the solution of computer vision problems. This paper contributes by evaluating the efficiency of several encoder-decoder neural networks, trained to perform the segmentation of the soccer field in Humanoid KidSize Robot Soccer competitions. To compare the efficiency of several encoders, a total of fourteen neural network models, based on the U-Net and SegNet architectures, were tested and compared in terms of accuracy, cost function value, IoU, and average inference time. Based on that, the networks based on U-Net that utilized the MobileNetv3Small or the ResNet18 for the encoding process were found to be the optimal solution among the considered alternatives to segment the soccer field.

Palavras-chave: neural networks, CNN, encoder-decoder, semantic segmentation, robot soccer