FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308806884> ?p ?o ?g. }

• W4308806884 endingPage "119242" @default.
• W4308806884 startingPage "119242" @default.
• W4308806884 abstract "Fallen person detection (FPD) is a new problem that aims to detect a person who lies or falls down on driving roads. The biggest difficulty in FPD is capturing a sufficient number of training images of people lying on driving roads because of the dangers involved. In this paper, we propose a novel fallen person detection image synthesis framework to address this difficulty. Our framework first embeds a fallen person instance into an image of a driving road, thereby generating a hard-to-acquire image (image of a person who has fallen on a road) from two easy-to-acquire images (driving road image and fallen person image). We then reduce the domain gap between the two images using domain adaptation. Finally, we remove some pixel artifacts from the border between the fallen person and background area in the synthesized image. Our proposed framework addresses the lack of training data, which is a serious problem inherent to FPD. Furthermore, we develop a new dataset named FPD (Fallen Person detection with Driving scenes)-set to train a detection network. FPD-set consists of four subsets: (1) RealFP218, (2) RealD1.8K, (3) RealFPDK1.4K and (4) RealFPDY1.1K. RealFP218 consists of 218 images of real fallen persons and their pixel-level mask annotations; and RealD1.8K consists of 1820 real driving road images. The two sets will be used to synthesize the driving road images including fallen persons. RealFPDK1.4K and RealFPDY1.1K are test sets which are captured at two different places (K-City and Yonsei University). The two test sets consist of 1400 and 1161 images of real fallen persons on the road with bounding box annotations, respectively. Our dataset covers a variety of conditions, including occlusion, lack of lighting, and shadows, thereby facilitating qualitative and quantitative evaluations in the real world. We will release this dataset for the benefit of the autonomous driving society. We verify the effectiveness of our training image synthesis method by applying the detector to the RealFPDK1.4K and RealFPDY1.1K datasets. Our approach achieves AP scores of 0.815 and 0.753, and the scores are higher than those of the baseline by + 0 . 287 and + 0 . 210 on RealFPDK1.4K and RealFPDY1.1K, respectively. Experimental results demonstrate that our framework contributes significantly to training an FPD network. • We quantify the collected dataset and the experimental results (Abstract). • We clarify our main advance and the need for FPD (Sections 1 and 6). • We explain the detailed architecture of our model (Section 4). • We statistically analyzed our datasets (Sections 4 and 5). • We added more figures, ablation studies, and experimental results (Section 5)." @default.
• W4308806884 created "2022-11-15" @default.
• W4308806884 creator A5008045203 @default.
• W4308806884 creator A5009819072 @default.
• W4308806884 creator A5028558267 @default.
• W4308806884 creator A5033655570 @default.
• W4308806884 creator A5065415014 @default.
• W4308806884 date "2023-03-01" @default.
• W4308806884 modified "2023-10-17" @default.
• W4308806884 title "Fallen person detection for autonomous driving" @default.
• W4308806884 cites W2011807137 @default.
• W4308806884 cites W2017745767 @default.
• W4308806884 cites W2026849320 @default.
• W4308806884 cites W2031489346 @default.
• W4308806884 cites W2117539524 @default.
• W4308806884 cites W2125276050 @default.
• W4308806884 cites W2170932168 @default.
• W4308806884 cites W2465597433 @default.
• W4308806884 cites W2618530766 @default.
• W4308806884 cites W2743197123 @default.
• W4308806884 cites W2767459365 @default.
• W4308806884 cites W2789621390 @default.
• W4308806884 cites W2792824754 @default.
• W4308806884 cites W2799107345 @default.
• W4308806884 cites W2933564790 @default.
• W4308806884 cites W2949651581 @default.
• W4308806884 cites W2963271314 @default.
• W4308806884 cites W2969896647 @default.
• W4308806884 cites W2982014123 @default.
• W4308806884 cites W3003504361 @default.
• W4308806884 cites W3013274043 @default.
• W4308806884 cites W3083654920 @default.
• W4308806884 cites W3112836416 @default.
• W4308806884 cites W3114107561 @default.
• W4308806884 cites W3131579999 @default.
• W4308806884 cites W3177372855 @default.
• W4308806884 cites W3185731136 @default.
• W4308806884 cites W3189844823 @default.
• W4308806884 doi "https://doi.org/10.1016/j.eswa.2022.119242" @default.
• W4308806884 hasPublicationYear "2023" @default.
• W4308806884 type Work @default.
• W4308806884 citedByCount "2" @default.
• W4308806884 countsByYear W43088068842023 @default.
• W4308806884 crossrefType "journal-article" @default.
• W4308806884 hasAuthorship W4308806884A5008045203 @default.
• W4308806884 hasAuthorship W4308806884A5009819072 @default.
• W4308806884 hasAuthorship W4308806884A5028558267 @default.
• W4308806884 hasAuthorship W4308806884A5033655570 @default.
• W4308806884 hasAuthorship W4308806884A5065415014 @default.
• W4308806884 hasConcept C154945302 @default.
• W4308806884 hasConcept C31972630 @default.
• W4308806884 hasConcept C41008148 @default.
• W4308806884 hasConceptScore W4308806884C154945302 @default.
• W4308806884 hasConceptScore W4308806884C31972630 @default.
• W4308806884 hasConceptScore W4308806884C41008148 @default.
• W4308806884 hasLocation W43088068841 @default.
• W4308806884 hasOpenAccess W4308806884 @default.
• W4308806884 hasPrimaryLocation W43088068841 @default.
• W4308806884 hasRelatedWork W1891287906 @default.
• W4308806884 hasRelatedWork W1969923398 @default.
• W4308806884 hasRelatedWork W2036807459 @default.
• W4308806884 hasRelatedWork W2058170566 @default.
• W4308806884 hasRelatedWork W2170022336 @default.
• W4308806884 hasRelatedWork W2229312674 @default.
• W4308806884 hasRelatedWork W258625772 @default.
• W4308806884 hasRelatedWork W2755342338 @default.
• W4308806884 hasRelatedWork W2772917594 @default.
• W4308806884 hasRelatedWork W3116076068 @default.
• W4308806884 hasVolume "213" @default.
• W4308806884 isParatext "false" @default.
• W4308806884 isRetracted "false" @default.
• W4308806884 workType "article" @default.