Synthetic-Range-Profile-Based Training Library Construction for Ship Target Recognition Purposes of Scanning Radar Systems

Karabayr, Osman; Saynak, Ugur; Kartal, M.; Coşkun, Ahmet F.; Gulum, Taylan O.; Bati, Baki

doi:10.1109/taes.2020.2972249

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ship target recognition usually adopts SAR image, AIS data, or video streaming. Karabayır et al [5] pointed out the importance of a training library and proposed a ship target recognition scheme based on knearest-neighbour (KNN) classifier. Chaturvedi et al [3] integrated SAR image and AIS data to identify ships at an area, which required ships to install radar and AIS equipment.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, ship recognition is more challenging than vehicle recognition. To achieve ship recognition, a series of literature [3][4][5][6] have been investigated and explored.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, SAR is effective to capture images of large ships but is unable to capture images of small vessels. Thus, recent ship recognition systems [4,5,7,8] employ cameras to capture images of ships and further adopts the computer vision technique [9,10] to implement ship recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Although ship recognition systems based on the computer vision technique have an advantage in deployment cost and small target recognition, they still provide coarse-grained services. In other words, prior ship recognition systems [4][5][6][7][8] only support ship target detection and classification, which fails to satisfy the increasing requirements of IWTS, such as tracking a given ship. Ship tracking provides crucial on-site microscopic kinematic traffic information which benefits traffic flow analysis, ship safety enhancement, traffic control, etc.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FGSR: A Fine-Grained Ship Retrieval Dataset and Method in Smart Cities

Xian

Jin

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Ship reidentification is an important part of water transportation systems in smart cities. Existing ship reidentification methods lack a large-scale fine-grained ship retrieval dataset in the wild and existing ship recognition solutions mainly focus on the ship target identification rather than the fine-grained ship reidentification. Furthermore, previous ship target identification systems are usually based on synthetic aperture radar (SAR) image, automatic identification system (AIS) data, or video streaming, which is confronted with expensive deployment costs, such as the installation cost of SAR and AIS, and the communication and storage overhead. Indeed, ship reidentification benefits for traffic monitoring, navigation safety, vessel tracking, etc. To address these problems, we propose a new large-scale fine-grained ship retrieval dataset (named FGSR) that consists of 30,000 images of 1000 ships captured in the wild. Besides, to tackle the difficulty of spatial-temporal inconsistency in ship identification in the wild, we design a multioriented ship reidentification network named FGSR-Net that consists of three modules to address different crucial problems. The pyramid fusion module was aimed at addressing the problem of variant size and shape of ship targets, the occlusion modules attempt to detect the unchangeable area of ship images, while the multibranch identity module generates discriminative feature representation for ship targets from different orientations. Experimental evaluations on FGSR dataset show the effectiveness and efficiency of our proposed FGSR-Net. The mean average precision of ship reidentification is around 92.4%, and our FGSR-Net proposed method only takes 3 seconds to give the retrieval results from 30,000 images.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Thus, ship recognition is more challenging than vehicle recognition. To achieve ship recognition, a series of literature [3][4][5][6] have been investigated and explored.…”

Section: Introductionmentioning

confidence: 99%