SwePub
Sök i LIBRIS databas

  Utökad sökning

L773:2379 8858
 

Sökning: L773:2379 8858 > Deep Instance Segme...

LIBRIS Formathandbok  (Information om MARC21)
FältnamnIndikatorerMetadata
00004156naa a2200553 4500
001oai:research.chalmers.se:1bb3cbba-b831-4f33-b62a-b1b472f79a9a
003SwePub
008220501s2023 | |||||||||||000 ||eng|
0247 a https://doi.org/10.1109/TIV.2022.31688992 DOI
0247 a https://research.chalmers.se/publication/5301602 URI
040 a (SwePub)cth
041 a engb eng
042 9 SwePub
072 7a art2 swepub-publicationtype
072 7a ref2 swepub-contenttype
1001 a Liu, Jianan4 aut
2451 0a Deep Instance Segmentation with Automotive Radar Detection Points
264 1c 2023
520 a Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points. With the development of automotive radar technologies in recent years, instance segmentation becomes possible by using automotive radar. Its data contain contexts such as radar cross section and micro-Doppler effects, and sometimes can provide detection when the field of view is obscured. The outcome from instance segmentation could be potentially used as the input of trackers for tracking targets. The existing methods often utilize a clustering-based classification framework, which fits the need of real-time processing but has limited performance due to minimum information provided by sparse radar detection points. In this paper, we propose an efficient method based on clustering of estimated semantic information to achieve instance segmentation for the sparse radar detection points. In addition, we show that the performance of the proposed approach can be further enhanced by incorporating the visual multi-layer perceptron. The effectiveness of the proposed method is verified by experimental results on the popular RadarScenes dataset, achieving 89.53% mean coverage and 86.97% mean average precision with the IoU threshold of 0.5, which is superior to other approaches in the literature. More significantly, the consumed memory is around 1MB, and the inference time is less than 40ms, indicating that our proposed algorithm is storage and time efficient. These two criteria ensure the practicality of the proposed method in real-world systems.
650 7a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe
650 7a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng
650 7a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Datorsystem0 (SwePub)202062 hsv//swe
650 7a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Computer Systems0 (SwePub)202062 hsv//eng
650 7a NATURVETENSKAPx Data- och informationsvetenskapx Datorseende och robotik0 (SwePub)102072 hsv//swe
650 7a NATURAL SCIENCESx Computer and Information Sciencesx Computer Vision and Robotics0 (SwePub)102072 hsv//eng
653 a Automobiles
653 a clustering
653 a Radar cross-sections
653 a environmental perception
653 a Automotive engineering
653 a Radar
653 a semantic segmentation
653 a Radar detection
653 a deep learning
653 a Semantics
653 a automotive radar
653 a Autonomous driving
653 a instance segmentation
653 a Point cloud compression
7001 a Xiong, Weiyiu Beihang University4 aut
7001 a Bai, Lipingu Beihang University4 aut
7001 a Xia, Yuxuan,d 1993u Chalmers tekniska högskola,Chalmers University of Technology4 aut0 (Swepub:cth)yuxuanx
7001 a Huang, Taou James Cook University4 aut
7001 a Ouyang, Wanliu The University of Sydney4 aut
7001 a Zhu, Bingu Beihang University4 aut
7102 a Beihang Universityb Chalmers tekniska högskola4 org
7730 t IEEE Transactions on Intelligent Vehiclesg 8:1, s. 84-94q 8:1<84-94x 2379-8858
8564 8u https://doi.org/10.1109/TIV.2022.3168899
8564 8u https://research.chalmers.se/publication/530160

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy