FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383503722> ?p ?o ?g. }

• W4383503722 endingPage "71386" @default.
• W4383503722 startingPage "71371" @default.
• W4383503722 abstract "Pedestrian detection is the use of computer vision technology to identify and accurately locate pedestrians in image or video data, which has a strong use value. This technology can be used as the research basis for visual tasks such as person re-identification, human pose estimation and behavior analysis, and can also be applied to industrial fields such as intelligent security, automatic driving and human-computer interaction. However, the problems of low image resolution, blurred appearance, large scale difference of pedestrians, occluded pedestrians and complex background still bring great challenges to the detection performance. To solve these problems, this paper proposes a high-performance pedestrian detection network dedicated to difficult conditions: DCPDN. Firstly, we design an optimized super-resolution reconstruction network to preprocess the image to alleviate the performance damage caused by low-resolution and blurred images. Then, to solve the multi-scale problem in pedestrian detection, we propose a weighted cross-scale feature fusion module, which adopts a hierarchical detection strategy to deal with pedestrian objects of different scales while fully fusing feature maps of different levels. Finally, to solve the occlusion problem that has plagued pedestrian detection for a long time, we design an occlusion processing module based on graph convolutional network, which can effectively use the correlation information between different parts of the human body and promote the feature expression of occluded objects. On the CityPersons dataset, the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MR</i> <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>-2</sup> of the detector is reduced by 6.9%, 19.2%, 8.9%, 1.9%, 3.6% and 14.2%, respectively, corresponding to different partition subsets of R, HO, A, L, M and S. On the Caltech dataset, corresponding to different divisions of R, HO, A, L and S, the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MR</i> <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>-2</sup> of the detector is reduced by 9.9%, 15.8%, 16.3%, 6.8% and 25.8%, respectively. The experimental results show that the performance improvement of the detector is significant on both severe occlusion (HO) and small scale (S) subsets. After testing, the algorithm has strong robustness to occluded pedestrians, and can be easily embedded in other detection frameworks. Our DCPDN is able to compete with the state of the art methods and is especially effective when dealing with the pedestrian detection problem under difficult conditions." @default.
• W4383503722 created "2023-07-08" @default.
• W4383503722 creator A5011392298 @default.
• W4383503722 creator A5023185583 @default.
• W4383503722 date "2023-01-01" @default.
• W4383503722 modified "2023-10-14" @default.
• W4383503722 title "DCPDN: High-Performance Pedestrian Detection Networks for Difficult Conditions" @default.
• W4383503722 cites W1885185971 @default.
• W4383503722 cites W1999853363 @default.
• W4383503722 cites W2031454541 @default.
• W4383503722 cites W2039051707 @default.
• W4383503722 cites W2064675550 @default.
• W4383503722 cites W2081021369 @default.
• W4383503722 cites W2098699644 @default.
• W4383503722 cites W2108598243 @default.
• W4383503722 cites W2133755669 @default.
• W4383503722 cites W2157190232 @default.
• W4383503722 cites W2159386181 @default.
• W4383503722 cites W2161969291 @default.
• W4383503722 cites W2168356304 @default.
• W4383503722 cites W2200528286 @default.
• W4383503722 cites W2239879258 @default.
• W4383503722 cites W2302502886 @default.
• W4383503722 cites W2382036597 @default.
• W4383503722 cites W2490270993 @default.
• W4383503722 cites W2497039038 @default.
• W4383503722 cites W2503339013 @default.
• W4383503722 cites W2531915888 @default.
• W4383503722 cites W2560533888 @default.
• W4383503722 cites W2565639579 @default.
• W4383503722 cites W2594507094 @default.
• W4383503722 cites W2607041014 @default.
• W4383503722 cites W2743905801 @default.
• W4383503722 cites W2747898905 @default.
• W4383503722 cites W2775890136 @default.
• W4383503722 cites W2792824754 @default.
• W4383503722 cites W2883363148 @default.
• W4383503722 cites W2894820835 @default.
• W4383503722 cites W2896540732 @default.
• W4383503722 cites W2944524737 @default.
• W4383503722 cites W2962850098 @default.
• W4383503722 cites W2963315052 @default.
• W4383503722 cites W2963318220 @default.
• W4383503722 cites W2963372104 @default.
• W4383503722 cites W2963402313 @default.
• W4383503722 cites W2963404857 @default.
• W4383503722 cites W2963470893 @default.
• W4383503722 cites W2963681621 @default.
• W4383503722 cites W2963998989 @default.
• W4383503722 cites W2964101377 @default.
• W4383503722 cites W2966759264 @default.
• W4383503722 cites W2988452521 @default.
• W4383503722 cites W2990075400 @default.
• W4383503722 cites W2990501368 @default.
• W4383503722 cites W2998471151 @default.
• W4383503722 cites W2999759184 @default.
• W4383503722 cites W3001652308 @default.
• W4383503722 cites W3011219267 @default.
• W4383503722 cites W3026181888 @default.
• W4383503722 cites W3033971630 @default.
• W4383503722 cites W3041107669 @default.
• W4383503722 cites W3049690032 @default.
• W4383503722 cites W3110568504 @default.
• W4383503722 cites W3130267610 @default.
• W4383503722 cites W3151111735 @default.
• W4383503722 cites W3153681304 @default.
• W4383503722 cites W3162952120 @default.
• W4383503722 cites W3163331908 @default.
• W4383503722 cites W3173669596 @default.
• W4383503722 cites W3205929373 @default.
• W4383503722 cites W4220757105 @default.
• W4383503722 cites W4312554764 @default.
• W4383503722 cites W4312932696 @default.
• W4383503722 cites W4312951616 @default.
• W4383503722 cites W4313013512 @default.
• W4383503722 cites W639708223 @default.
• W4383503722 doi "https://doi.org/10.1109/access.2023.3293120" @default.
• W4383503722 hasPublicationYear "2023" @default.
• W4383503722 type Work @default.
• W4383503722 citedByCount "0" @default.
• W4383503722 crossrefType "journal-article" @default.
• W4383503722 hasAuthorship W4383503722A5011392298 @default.
• W4383503722 hasAuthorship W4383503722A5023185583 @default.
• W4383503722 hasBestOaLocation W43835037221 @default.
• W4383503722 hasConcept C121332964 @default.
• W4383503722 hasConcept C127413603 @default.
• W4383503722 hasConcept C132525143 @default.
• W4383503722 hasConcept C138885662 @default.
• W4383503722 hasConcept C153180895 @default.
• W4383503722 hasConcept C154945302 @default.
• W4383503722 hasConcept C22212356 @default.
• W4383503722 hasConcept C2776401178 @default.
• W4383503722 hasConcept C2777113093 @default.
• W4383503722 hasConcept C2778755073 @default.
• W4383503722 hasConcept C2780156472 @default.
• W4383503722 hasConcept C31258907 @default.
• W4383503722 hasConcept C31972630 @default.
• W4383503722 hasConcept C41008148 @default.

• next