Phytoliths constitute microscopic SiO₂-rich biominerals formed in the cellular system of many living plants and are often preserved in soils, sediments and artefacts. Their analysis contributes significantly to the identification and study of botanical remains in (paleo)ecological and archaeological contexts. Traditional identification and classification of phytoliths rely on human experience, and as such, an emerging challenge is to automatically classify them to enhance data homogeneity among researchers worldwide and facilitate reliable comparisons. In the present study, a deep artificial neural network (NN) is implemented under the objective to detect and classify phytoliths, extracted from modern wheat (Triticum spp.). The proposed methodology is able to recognise four phytolith morphotypes: (a) Stoma, (b) Rondel, (c) Papillate, and (d) Elongate dendritic. For the learning process, a dataset of phytolith photomicrographs was created and allocated to training, validation and testing data groups. Due to the limited size and low diversity of the dataset, an end-to-end encoder-decoder NN architecture is proposed, based on a pre-trained MobileNetV2, utilised for the encoder part and U-net, used for the segmentation stage. After the parameterisation, training and fine-tuning of the proposed architecture, it is capable to classify and localise the four classes of phytoliths in unknown images with high unbiased accuracy, exceeding 90%. The proposed methodology and corresponding dataset are quite promising for building up the capacity of phytolith classification within unfamiliar (geo)archaeological datasets, demonstrating remarkable potential towards automatic phytolith analysis.

Semantic segmentation plays a significant role in unstructured and planetary scene understanding, offering to a robotic system or a planetary rover valuable knowledge about its surroundings. Several studies investigate rover-based scene recognition planetary-like environments but there is a lack of a semantic segmentation architecture, focused on computing systems with low resources and tested on the lunar surface. In this study, a lightweight encoder-decoder neural network (NN) architecture is proposed for rover-based ground segmentation on the lunar surface. The proposed architecture is composed by a modified MobilenetV2 as encoder and a lightweight U-net decoder while the training and evaluation process were conducted using a publicly available synthetic dataset with lunar landscape images. The proposed model provides robust segmentation results, allowing the lunar scene understanding focused on rocks and boulders. It achieves similar accuracy, compared with original U-net and U-net-based architectures which are 110–140 times larger than the proposed architecture. This study, aims to contribute in lunar landscape segmentation utilizing deep learning techniques, while it proves a great potential in autonomous lunar navigation ensuring a safer and smoother navigation on the moon. To the best of our knowledge, this is the first study which propose a lightweight semantic segmentation architecture for the lunar surface, aiming to reinforce the autonomous rover navigation.

Feature extraction plays a crucial role in computer vision and autonomous navigation, offering valuable information for real-time localization and scene understanding. However, although multiple studies investigate keypoint detection and description algorithms in urban and indoor environments, far fewer studies concentrate in unstructured environments. In this study, a multi-task deep learning architecture is developed for keypoint detection and description, focused on poor-featured unstructured and planetary scenes with low or changing illumination. The proposed architecture was trained and evaluated using a training and benchmark dataset with earthy and planetary scenes. Moreover, the trained model was integrated in a visual SLAM (Simultaneous Localization and Maping) system as a feature extraction module, and tested in two feature-poor unstructured areas. Regarding the results, the proposed architecture provides a mAP (mean Average Precision) in a level of 0.95 in terms of keypoint description, outperforming well-known handcrafted algorithms while the proposed SLAM achieved two times lower RMSE error in a poor-featured area with low illumination, compared with ORB-SLAM2. To the best of the authors’ knowledge, this is the first study that investigates the potential of keypoint detection and description through deep learning in unstructured and planetary environments.

Dimitris Tatsis, Nikolaos Kechagias, Antonios Tsekos, Georgios Petrakis, Konstantinos Vahtsevanos. JKAOMS 2022;48:59-62. https://doi.org/10.5125/jkaoms.2022.48.1.59

Feature extraction plays a crucial role in visual localization, SLAM (Simultaneous Localization and Mapping) and autonomous navigation, by enabling the extraction and tracking of distinctive visual features for both mapping and localization tasks. However, most of the studies, investigate the efficiency and performance of the algorithms in urban, vegetated or indoor environments and not in unstructured environments which suffers by poor information in visual cues where a feature extraction algorithm or architecture could base on. In this study, an investigation of SuperPoint architecture’s efficiency in keypoint detection and description applied to unstructured and planetary scenes was conducted, producing three different models: (a) an original SuperPoint model trained from scratch, (b) an original fine-tuned SuperPoint model, (c) an optimized SuperPoint model, trained from scratch with the same parametarization as the corresponding original model. For the training process, a dataset of 48 000 images was utilized representing unstructured scenes from Earth, Moon and Mars while a benchmark dataset was used aiming to evaluate the model in illumination and viewpoint changes. The experimentation proved that the optimized SuperPoint model provides superior performance using repeatability and homography estimation metrics, compared with the original SuperPoint models, and handcrafted keypoint detectors and descriptors.