Semantic segmentation of plant organs using SegNet network and RGB-D images

This project is about semantic segmentation of 4 classes of plant organs (stem, petiole, leaf and fruit) from RGB-D images using Pyhton 3, Tensorflow 2.0 and Keras. I worked with synthetic data, randomly generated and annotated with Blender and used a SegNet architecture trained from Scratch with 10000 images.

Dataset

The dataset is now available in Kaggle : https://www.kaggle.com/harlequeen/synthetic-rgbd-images-of-plants

1.Training & Evaluation

The model was trained on 10000 images ( 8000 images for training, 1000 images for validation and 1000 for test ) of size 224x224 on 4x12Go GPU, the curves of accuracy and loss were as follows :

Training accuracy = 99%

Validation accuracy = 98%

The curves of accuracy and loss are shown below :

2.Inference

The model was tested on 1000 RGBD images and with a test accuracy = 97,8% , here is some results:

3.Architecture

Here is a screenshot of one bloc of SegNet visualised in Tensorboard :

Conclusion

This project is about semantic segmentation of plant organs into 4 classes + Background using synthetic RGB-D images.

References

• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation by Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla, Senior Member, IEEE

Contact

Farouk EL BAHA

Junior ML & DL Engineer

e-mail: alfarouk.elbaha@gmail.com

linkedin: www.linkedin.com/in/farouk-el-baha-74803b188