Scientists from the St. Petersburg State University of Aerospace Instrumentation (SUAI) have created a unique machine learning model for landscape analysis. The system processes data from drones in real time, recognizing objects with high accuracy.\u00a0<\/p>\n\n\n
Previously, creating a map of the area took a whole day – specialists manually processed each area. Now, thanks to the development of GUAP, this process has been reduced to a few minutes – while the drone flies over the territory.\u00a0<\/p>\n\n\n
The drone is equipped with lidar, a device that scans surfaces with laser beams, creating a detailed 3D image. A computer model analyzes the data, recording the smallest details: rivers, bridges, forests. The development belongs to a team of five employees from the machine learning laboratory of the SUAI School of Engineering.\u00a0<\/p>\n\n\n
\u201cPreviously, mathematical algorithms were used to construct 3D maps, but they produced many errors,\u201d explained laboratory assistant Rodion Mashkovtsev. \u201cOur model provides high accuracy, which is critical for analysis.\u201d\u00a0<\/p>\n\n\n
One of the key advantages of the system is the ability to solve urgent problems immediately. For example, look for those lost in the mountains, even if the slopes are covered with dense forest. Lidar \u201csees\u201d through foliage, while conventional cameras are powerless.\u00a0<\/p>\n\n\n
\u201cGround-based lidars did not allow covering large areas,\u201d noted the head of the laboratory, Sergei Nenashev. \u201cAerial scanning makes it possible to process thousands of square kilometers.\u201d\u00a0<\/p>\n\n\n
Data from drones is instantly transmitted to the server, where neural network<\/a> analyzes them in real time. This opens up prospects for geodesy, oil production<\/a>, urban planning and other areas.\u00a0<\/p>\n\n\n \u201cThe system accurately recognizes objects, saving human resources,\u201d added laboratory assistant Roman Voronov. \u201cThis is useful for cadastral work, construction, monitoring of reservoirs and protection of objects.\u201d\u00a0<\/p>\n\n\n The new GUAP technology speeds up landscape analysis hundreds of times and can be used in a wide variety of industries – from agriculture to logistics.\u00a0<\/p>\n\n\n Source: sro-ciz.ru<\/sub><\/p>\n","protected":false},"excerpt":{"rendered":" Scientists from the St. Petersburg State University of Aerospace Instrumentation (SUAI) have created a unique machine learning model for landscape analysis. The system processes data from drones in real time, recognizing objects with high accuracy. Previously, creating a map of the area took a whole day – specialists m<\/p>\n","protected":false},"author":9,"featured_media":17090,"comment_status":"open","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_seopress_robots_primary_cat":"","_seopress_titles_title":"The SUAI machine learning model analyzes the landscape from drones in real time","_seopress_titles_desc":"SUAI scientists have developed a machine learning model for landscape analysis from drones. The system works in real time with high accuracy, saving time and resources.","_seopress_robots_index":"","_seopress_analysis_target_kw":"","footnotes":""},"categories":[9],"tags":[377],"class_list":["post-60027","news","type-news","status-publish","has-post-thumbnail","category-geofizika","tag-bespilotnye-tehnologii"],"acf":[],"pbg_featured_image_src":{"full":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta.webp",1200,790,false],"thumbnail":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-150x150.webp",150,150,true],"medium":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-300x198.webp",300,198,true],"medium_large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-768x506.webp",768,506,true],"large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-1024x674.webp",1024,674,true],"1536x1536":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta.webp",1200,790,false],"2048x2048":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta.webp",1200,790,false],"bricks_large_16x9":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-1200x675.webp",1200,675,true],"bricks_large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta.webp",1200,790,false],"bricks_large_square":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta.webp",1200,790,false],"bricks_medium":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-600x395.webp",600,395,true],"bricks_medium_square":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/05\/dron-s-lidarom-dlya-semki-landshafta-600x600.webp",600,600,true]},"pbg_author_info":{"display_name":"Lyubov Cherkasova","author_link":"https:\/\/geoconversation.org\/en\/author\/amourallis\/","author_img":false},"pbg_comment_info":" No Comments","pbg_excerpt":"Scientists from the St. Petersburg State University of Aerospace Instrumentation (SUAI) have created a unique machine learning model for landscape analysis. The system processes data from drones in real time, recognizing objects with high accuracy. Previously, creating a map of the area took a whole day - specialists m","_links":{"self":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news\/60027","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/types\/news"}],"author":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/comments?post=60027"}],"version-history":[{"count":0,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news\/60027\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/media\/17090"}],"wp:attachment":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/media?parent=60027"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/categories?post=60027"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/tags?post=60027"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}