Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386688678> ?p ?o ?g. }
- W4386688678 endingPage "7806" @default.
- W4386688678 startingPage "7806" @default.
- W4386688678 abstract "Long-range target detection in thermal infrared imagery is a challenging research problem due to the low resolution and limited detail captured by thermal sensors. The limited size and variability in thermal image datasets for small target detection is also a major constraint for the development of accurate and robust detection algorithms. To address both the sensor and data constraints, we propose a novel convolutional neural network (CNN) feature extraction architecture designed for small object detection in data-limited settings. More specifically, we focus on long-range ground-based thermal vehicle detection, but also show the effectiveness of the proposed algorithm on drone and satellite aerial imagery. The design of the proposed architecture is inspired by an analysis of popular object detectors as well as custom-designed networks. We find that restricted receptive fields (rather than more globalized features, as is the trend), along with less downsampling of feature maps and attenuated processing of fine-grained features, lead to greatly improved detection rates while mitigating the model's capacity to overfit on small or poorly varied datasets. Our approach achieves state-of-the-art results on the Defense Systems Information Analysis Center (DSIAC) automated target recognition (ATR) and the Tiny Object Detection in Aerial Images (AI-TOD) datasets." @default.
- W4386688678 created "2023-09-13" @default.
- W4386688678 creator A5002842383 @default.
- W4386688678 creator A5011391575 @default.
- W4386688678 creator A5021852735 @default.
- W4386688678 date "2023-09-11" @default.
- W4386688678 modified "2023-10-17" @default.
- W4386688678 title "Long-Range Thermal Target Detection in Data-Limited Settings Using Restricted Receptive Fields" @default.
- W4386688678 cites W1861492603 @default.
- W4386688678 cites W1995837975 @default.
- W4386688678 cites W1999525858 @default.
- W4386688678 cites W2029309147 @default.
- W4386688678 cites W2065337811 @default.
- W4386688678 cites W2076161723 @default.
- W4386688678 cites W2093650732 @default.
- W4386688678 cites W2097117768 @default.
- W4386688678 cites W2108598243 @default.
- W4386688678 cites W2109255472 @default.
- W4386688678 cites W2183341477 @default.
- W4386688678 cites W2194775991 @default.
- W4386688678 cites W2549139847 @default.
- W4386688678 cites W2565639579 @default.
- W4386688678 cites W2570343428 @default.
- W4386688678 cites W2579152745 @default.
- W4386688678 cites W2625219738 @default.
- W4386688678 cites W2777033955 @default.
- W4386688678 cites W2896155169 @default.
- W4386688678 cites W2910798558 @default.
- W4386688678 cites W2943085063 @default.
- W4386688678 cites W2945087682 @default.
- W4386688678 cites W2963037989 @default.
- W4386688678 cites W2963351448 @default.
- W4386688678 cites W2963446712 @default.
- W4386688678 cites W2964350391 @default.
- W4386688678 cites W2982770724 @default.
- W4386688678 cites W2985384565 @default.
- W4386688678 cites W2986661129 @default.
- W4386688678 cites W2988452521 @default.
- W4386688678 cites W2989604896 @default.
- W4386688678 cites W3009442072 @default.
- W4386688678 cites W3012573144 @default.
- W4386688678 cites W3022557096 @default.
- W4386688678 cites W3035396860 @default.
- W4386688678 cites W3042011474 @default.
- W4386688678 cites W3096609285 @default.
- W4386688678 cites W3106250896 @default.
- W4386688678 cites W3108849448 @default.
- W4386688678 cites W3119011217 @default.
- W4386688678 cites W3125372245 @default.
- W4386688678 cites W3138516171 @default.
- W4386688678 cites W3157386596 @default.
- W4386688678 cites W3160733999 @default.
- W4386688678 cites W3172818782 @default.
- W4386688678 cites W3202921246 @default.
- W4386688678 cites W3210997132 @default.
- W4386688678 cites W4283717190 @default.
- W4386688678 cites W4312090255 @default.
- W4386688678 cites W4380446752 @default.
- W4386688678 cites W4385271156 @default.
- W4386688678 cites W639708223 @default.
- W4386688678 doi "https://doi.org/10.3390/s23187806" @default.
- W4386688678 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37765864" @default.
- W4386688678 hasPublicationYear "2023" @default.
- W4386688678 type Work @default.
- W4386688678 citedByCount "0" @default.
- W4386688678 crossrefType "journal-article" @default.
- W4386688678 hasAuthorship W4386688678A5002842383 @default.
- W4386688678 hasAuthorship W4386688678A5011391575 @default.
- W4386688678 hasAuthorship W4386688678A5021852735 @default.
- W4386688678 hasBestOaLocation W43866886781 @default.
- W4386688678 hasConcept C108583219 @default.
- W4386688678 hasConcept C110384440 @default.
- W4386688678 hasConcept C115961682 @default.
- W4386688678 hasConcept C138885662 @default.
- W4386688678 hasConcept C153180895 @default.
- W4386688678 hasConcept C154945302 @default.
- W4386688678 hasConcept C205649164 @default.
- W4386688678 hasConcept C22019652 @default.
- W4386688678 hasConcept C2776151529 @default.
- W4386688678 hasConcept C2776401178 @default.
- W4386688678 hasConcept C2776429412 @default.
- W4386688678 hasConcept C31972630 @default.
- W4386688678 hasConcept C41008148 @default.
- W4386688678 hasConcept C41895202 @default.
- W4386688678 hasConcept C50644808 @default.
- W4386688678 hasConcept C52622490 @default.
- W4386688678 hasConcept C62649853 @default.
- W4386688678 hasConcept C76155785 @default.
- W4386688678 hasConcept C81363708 @default.
- W4386688678 hasConcept C94915269 @default.
- W4386688678 hasConceptScore W4386688678C108583219 @default.
- W4386688678 hasConceptScore W4386688678C110384440 @default.
- W4386688678 hasConceptScore W4386688678C115961682 @default.
- W4386688678 hasConceptScore W4386688678C138885662 @default.
- W4386688678 hasConceptScore W4386688678C153180895 @default.
- W4386688678 hasConceptScore W4386688678C154945302 @default.
- W4386688678 hasConceptScore W4386688678C205649164 @default.
- W4386688678 hasConceptScore W4386688678C22019652 @default.