Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211888049> ?p ?o ?g. }
- W3211888049 abstract "Visuals captured by high-flying aerial drones are increasingly used to assess biodiversity and animal population dynamics around the globe. Yet, challenging acquisition scenarios and tiny animal depictions in airborne imagery, despite ultra-high resolution cameras, have so far been limiting factors for applying computer vision detectors successfully with high confidence. In this paper, we address the problem for the first time by combining deep object detectors with super-resolution techniques and altitude data. In particular, we show that the integration of a holistic attention network based super-resolution approach and a custom-built altitude data exploitation network into standard recognition pipelines can considerably increase the detection efficacy in real-world settings. We evaluate the system on two public, large aerial-capture animal datasets, SAVMAP and AED. We find that the proposed approach can consistently improve over ablated baselines and the state-of-the-art performance for both datasets. In addition, we provide a systematic analysis of the relationship between animal resolution and detection performance. We conclude that super-resolution and altitude knowledge exploitation techniques can significantly increase benchmarks across settings and, thus, should be used routinely when detecting minutely resolved animals in aerial imagery." @default.
- W3211888049 created "2021-11-22" @default.
- W3211888049 creator A5007937949 @default.
- W3211888049 creator A5045464613 @default.
- W3211888049 creator A5051376499 @default.
- W3211888049 creator A5052504255 @default.
- W3211888049 date "2022-01-01" @default.
- W3211888049 modified "2023-09-27" @default.
- W3211888049 title "Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance" @default.
- W3211888049 cites W114517082 @default.
- W3211888049 cites W1536680647 @default.
- W3211888049 cites W2017335377 @default.
- W3211888049 cites W2032593695 @default.
- W3211888049 cites W2037299664 @default.
- W3211888049 cites W2065114757 @default.
- W3211888049 cites W2102605133 @default.
- W3211888049 cites W2109255472 @default.
- W3211888049 cites W2143897835 @default.
- W3211888049 cites W2175423925 @default.
- W3211888049 cites W2214802144 @default.
- W3211888049 cites W2283306344 @default.
- W3211888049 cites W2295675274 @default.
- W3211888049 cites W2297338375 @default.
- W3211888049 cites W2526773958 @default.
- W3211888049 cites W2538965960 @default.
- W3211888049 cites W2565639579 @default.
- W3211888049 cites W2576556885 @default.
- W3211888049 cites W2604602375 @default.
- W3211888049 cites W2607041014 @default.
- W3211888049 cites W2612445135 @default.
- W3211888049 cites W2737340643 @default.
- W3211888049 cites W2738678155 @default.
- W3211888049 cites W2752508182 @default.
- W3211888049 cites W2768765894 @default.
- W3211888049 cites W2805498525 @default.
- W3211888049 cites W2810030371 @default.
- W3211888049 cites W2866634454 @default.
- W3211888049 cites W2884561390 @default.
- W3211888049 cites W2884585870 @default.
- W3211888049 cites W2895082331 @default.
- W3211888049 cites W2896155169 @default.
- W3211888049 cites W2921243212 @default.
- W3211888049 cites W2922182161 @default.
- W3211888049 cites W2948995641 @default.
- W3211888049 cites W2950855258 @default.
- W3211888049 cites W2956586819 @default.
- W3211888049 cites W2958927440 @default.
- W3211888049 cites W2963037581 @default.
- W3211888049 cites W2963037989 @default.
- W3211888049 cites W2963470893 @default.
- W3211888049 cites W2963516811 @default.
- W3211888049 cites W2963556638 @default.
- W3211888049 cites W2963606888 @default.
- W3211888049 cites W2963986095 @default.
- W3211888049 cites W2964121744 @default.
- W3211888049 cites W2964325192 @default.
- W3211888049 cites W2969704791 @default.
- W3211888049 cites W2977497713 @default.
- W3211888049 cites W2983869563 @default.
- W3211888049 cites W2992930668 @default.
- W3211888049 cites W3016951142 @default.
- W3211888049 cites W3034669389 @default.
- W3211888049 cites W3034971973 @default.
- W3211888049 cites W3087729170 @default.
- W3211888049 cites W3090598983 @default.
- W3211888049 cites W3092151103 @default.
- W3211888049 cites W3096739052 @default.
- W3211888049 cites W3106250896 @default.
- W3211888049 cites W3116991906 @default.
- W3211888049 cites W3122799380 @default.
- W3211888049 cites W3125372245 @default.
- W3211888049 cites W3157042932 @default.
- W3211888049 cites W3172507542 @default.
- W3211888049 cites W54257720 @default.
- W3211888049 cites W639708223 @default.
- W3211888049 doi "https://doi.org/10.1109/wacvw54805.2022.00057" @default.
- W3211888049 hasPublicationYear "2022" @default.
- W3211888049 type Work @default.
- W3211888049 sameAs 3211888049 @default.
- W3211888049 citedByCount "1" @default.
- W3211888049 countsByYear W32118880492023 @default.
- W3211888049 crossrefType "proceedings-article" @default.
- W3211888049 hasAuthorship W3211888049A5007937949 @default.
- W3211888049 hasAuthorship W3211888049A5045464613 @default.
- W3211888049 hasAuthorship W3211888049A5051376499 @default.
- W3211888049 hasAuthorship W3211888049A5052504255 @default.
- W3211888049 hasBestOaLocation W32118880492 @default.
- W3211888049 hasConcept C108583219 @default.
- W3211888049 hasConcept C115961682 @default.
- W3211888049 hasConcept C127413603 @default.
- W3211888049 hasConcept C144024400 @default.
- W3211888049 hasConcept C149923435 @default.
- W3211888049 hasConcept C153180895 @default.
- W3211888049 hasConcept C154945302 @default.
- W3211888049 hasConcept C176262533 @default.
- W3211888049 hasConcept C188198153 @default.
- W3211888049 hasConcept C205372480 @default.
- W3211888049 hasConcept C205649164 @default.
- W3211888049 hasConcept C2776151529 @default.
- W3211888049 hasConcept C2776429412 @default.