Paper Reading AI Learner

On the Role of Field of View for Occlusion Removal with Airborne Optical Sectioning

2022-04-28 09:26:10
Francis Seits, Indrajit Kurmi, Rakesh John Amala Arokia Nathan, Rudolf Ortner, Oliver Bimber

Abstract

Occlusion caused by vegetation is an essential problem for remote sensing applications in areas, such as search and rescue, wildfire detection, wildlife observation, surveillance, border control, and others. Airborne Optical Sectioning (AOS) is an optical, wavelength-independent synthetic aperture imaging technique that supports computational occlusion removal in real-time. It can be applied with manned or unmanned aircrafts, such as drones. In this article, we demonstrate a relationship between forest density and field of view (FOV) of applied imaging systems. This finding was made with the help of a simulated procedural forest model which offers the consideration of more realistic occlusion properties than our previous statistical model. While AOS has been explored with automatic and autonomous research prototypes in the past, we present a free AOS integration for DJI systems. It enables bluelight organizations and others to use and explore AOS with compatible, manually operated, off-the-shelf drones. The (digitally cropped) default FOV for this implementation was chosen based on our new finding.

Abstract (translated)

URL

https://arxiv.org/abs/2204.13371

PDF

https://arxiv.org/pdf/2204.13371.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot