Semantic Scene Understanding with Large Language Models on Unmanned Aerial Vehicles

Curtò, J. de; Zarzà, I. de; Calafate, Carlos T.

doi:10.3390/drones7020114

Cited by 26 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding camouflaged objects, we not only utilize binary ground truth data but also introduce additional training information, such as ranking information and relevant masks [45]. Large Language Models (LLMs) and Visual Language Models (VLMs) [46,47] can provide rich semantic information to models, including object names, context, and more. By integrating this information, we can gain a deeper understanding of the model's decision-making process and interpret the model's understanding and reasoning about scenes, thereby endowing our model with stronger semantic scene understanding capabilities.…”

Section: Discussionmentioning

confidence: 99%

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Wang,

Li,

Wei

et al. 2024

Electronics

View full text Add to dashboard Cite

The existence of camouflage targets is widespread in the natural world, as they blend seamlessly or closely resemble their surrounding environment, making it difficult for the human eye to identify them accurately. In camouflage target segmentation, challenges often arise from the high similarity between the foreground and background, resulting in segmentation errors, imprecise edge detection, and overlooking of small targets. To address these issues, this paper presents a robust localization-guided dual-branch network for the recognition of camouflaged targets. Two crucial branches, i.e., a localization branch and an overall refinement branch are designed and incorporated. The localization branch achieves accurate preliminary localization of camouflaged targets by incorporating the robust localization module, which integrates different high-level feature maps in a partially decoded manner. The overall refinement branch optimizes segmentation accuracy based on the output predictions of the localization branch. Within this branch, the edge refinement module is devised to effectively reduce false negative and false positive interference. By conducting context exploration on each feature layer from top to bottom, this module further enhances the precision of target edge segmentation. Additionally, our network employs five jointly trained output prediction maps and introduces attention-guided heads for diverse prediction maps in the overall refinement branch. This design adjusts the spatial positions and channel weights of different prediction maps, generating output prediction maps based on the emphasis of each output, thereby further strengthening the perception and feature representation capabilities of the model. To improve its ability to generate highly confident and accurate prediction candidate regions, tailored loss functions are designed to cater to the objectives of different prediction maps. We conducted experiments on three publicly available datasets for camouflaged object detection to assess our methodology and compared it with state-of-the-art network models. On the largest dataset COD10K, our method achieved a Structure-measure of 0.827 and demonstrated superior performance in other evaluation metrics, outperforming recent network models.

show abstract

Section: Discussionmentioning

confidence: 99%

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Wang,

Li,

Wei

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…VLMs excel at generating textual descriptions for images, offering detailed insights into objects, people, and events within images. They can also perform imagerelated tasks such as classification, object detection, and generating grammatically correct image captions [40].…”

Section: Discussionmentioning

confidence: 99%

Pursuit Problem of Unmanned Aerial Vehicles

Oleg,

Zhang

2023

Mathematics

View full text Add to dashboard Cite

The study examines scenarios involving a single pursuer tracking a single evader, as well as situations where multiple pursuers are involved in chasing multiple evaders. We formulate this problem as a search and pursuit problem for unmanned aerial vehicles (UAVs). Game theory offers a mathematical framework to model and examine strategic interactions involving multiple decision-makers. By employing game theory principles to address the search and pursuit problem, our objective is to optimize the efficiency of strategies for detecting and capturing unmanned aerial vehicles (UAVs).

show abstract

“…Generative Pre-trained Transformer (GPT) models, built upon a foundational architecture, play a pivotal role in advancing NLP capabilities [33]. These models have significantly transformed the NLP landscape, demonstrating an exceptional ability to capture and comprehend intricate linguistic structures, context, and semantic nuances [34].…”

Section: The Evolution Of Generative Pre-trained Transformer (Gpt) Mo...mentioning

confidence: 99%

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

Roumeliotis,

Tselikas,

Nasiopoulos

2024

Software

View full text Add to dashboard Cite

This paper presents a pioneering methodology for refining product recommender systems, introducing a synergistic integration of unsupervised models—K-means clustering, content-based filtering (CBF), and hierarchical clustering—with the cutting-edge GPT-4 large language model (LLM). Its innovation lies in utilizing GPT-4 for model evaluation, harnessing its advanced natural language understanding capabilities to enhance the precision and relevance of product recommendations. A flask-based API simplifies its implementation for e-commerce owners, allowing for the seamless training and evaluation of the models using CSV-formatted product data. The unique aspect of this approach lies in its ability to empower e-commerce with sophisticated unsupervised recommender system algorithms, while the GPT model significantly contributes to refining the semantic context of product features, resulting in a more personalized and effective product recommendation system. The experimental results underscore the superiority of this integrated framework, marking a significant advancement in the field of recommender systems and providing businesses with an efficient and scalable solution to optimize their product recommendations.

show abstract

Semantic Scene Understanding with Large Language Models on Unmanned Aerial Vehicles

Cited by 26 publications

References 14 publications

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Pursuit Problem of Unmanned Aerial Vehicles

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

Contact Info

Product

Resources

About