
Citation: | Yongxu Li, Xudong Lai, Mingwei Wang. Semisupervised heterogeneous ensemble for ship target discrimination in synthetic aperture radar images[J]. Acta Oceanologica Sinica, 2022, 41(7): 180-192. doi: 10.1007/s13131-021-1980-2 |
Class Ostracoda Latreille, 1802, emend. Martin and Davis, 2001 are a big group of small bivalved crustaceans. They inhabit almost all aquatic environments with high taxonomic diversity (Karanovic, 2010). Ostracods are one of the momentous groups of marine organisms, and are functionally important in the process of bio-geo-chemical cycles in marine ecosystem, especially in the tropics and subtropical regions (Angel et al., 2007; George and Nair, 1980). They also play a significant participant of marine deposition, because their calcified valves are preserved as fossils (Di Celma et al., 2016). The studies of ostracods have been well improved in last two decades, and many new taxa have been erected (Harrison-Nelson and Kornicker, 2000; Chavtur, 2003; Lum et al., 2008; Karanovic, 2010; Chavtur and Angel, 2011; Pinto and Jocqué, 2013; Xiang et al., 2017a, b, 2018; Du et al., 2018). These faunae might no-monophyletic, phylogeny remains indistinct, and classification is based on typical characteristics (Fortey and Thomas, 1998; Yamaguchi and Endo, 2003).
Halocyprid ostracods constitute appreciable part of marine zooplankton. They are floating through virtually everywhere in marine environment including surface, hydrothermal vent, cold seep and abyss (van Harten, 1992; Oakley et al., 2013; Tanaka and Yasuhara, 2016; Yamaguchi et al., 2016). In 1853, the largest family Halocyprididae Dana, 1853 (Chavtur, 2003; Martin and Davis, 2001; Brandão et al., 2019) within order Halocyprida Dana, 1853 was erected. And then, the subfamily Conchoeciinae Müller, 1912 was erected under this family. In 2011, Chavtur and Angel (2011) designated the tribe Conchoeciini Chavtur and Angel, 2011 on the basis of the locational shifts of glands. Not long ago, Du et al. (2018) erected genus Polyconchoecia Xiang, Chen and Du, 2018 with the type species P. commixtus Xiang, Chen and Du, 2018 based on the definite characteristics of locations of major glands on carapace. Soon after that, genus Conchoecia Dana, 1849 was subdivided into five genera: Conchoecia; Macrochoecilla Chavtur, 2018; Lophuroecia Chavtur, 2018; Parvidentoecia Chavtur, 2018; and Hyalocoecia Chavtur, 2018; and genus Parthenoecia Chavtur, 2018 was erected, mainly based on characteristics of lateral gland, armature of seta-e on the first antenna in the male, and copulatory appendage (Chavtur and Bashmanov, 2018). Thus far, the tribe Conchoeciini has contained 27 genera (Brandão et al., 2019).
In this study, a new species of genus Polyconchoecia from the South China Sea was described.
Collections were obtained from two cruises of the South China Sea in 2014–2015. All zooplankton specimens were collected using a Multinet sampling system (Type Midi, Mesh-size aperture 200 µm, HydroBios Inc., Kiel, Germany) by vertical and stratified hauls from bottom to surface. Collections were preserved by immersion in 5% buffered formaldehyde.
Specimens were dissected under a Carl Zeiss Discovery V20 zoom-stereomicroscope. Dissected appendages were mounted in permanent slides with CMC-9AF medium (Masters Company Inc., Illinois, USA). Observations were done by a Carl Zeiss Axio Imager Z2 differential interference contrast microscope system with AxioVision Image-Pro software (Carl Zeiss Inc., Oberkochen, Germany). All drawings were made from micro-images of dissected appendages, followed the methodology in Chavtur and Angel (2011), and further processed with Adobe Photoshop CS6 (Adobe Inc., San Jose, CA, USA).
The type specimens/appendages were deposited in the Marine Biological Sample Museum of the Chinese Offshore Investigation and Assessment, Third Institute of Oceanography, MNR (Xiamen, China), under the collection numbers TIO-OHH-PP-201 to TIO-OHH-PP-204.
The electronic edition of this article conforms to the requirements of the amended International Code of Zoological Nomenclature, and hence the new names contained herein are available under that code from the electronic edition of this article. This published work and the nomenclatural acts it contains have been registered in ZooBank, the online registration system for the ICZN. The ZooBank LSIDs (Life Science Identifiers) can be resolved and the associated information viewed through any standard web browser by appending the LSID to the prefix “http://zoobank.org/”. The LSID for this publication is: urn:lsid:zoobank.org:pub:C8D3334A-AA1C-4355-AB53-140B299051B0. The electronic edition of this work was published in a journal with an ISSN, and has been archived and is available from the following digital repositories: SpringerLink, PubMed Central, LOCKSS.
Oder Halocyprida Dana, 1853
Family Halocyprididae Dana, 1853
Subfamily Conchoeciinae Müller, 1912
Tribe Conchoeciini Chavtur and Angel, 2011
Genus Polyconchoecia Xiang, Chen and Du, 2018
Species Polyconchoecia chenii Xiang, Wang and Chen sp. nov.
LSID: urn:lsid:zoobank.org:act:9B60314F-EE85-46C7-8213-737601ED74D8
Etymology. Latinized name of Ruixiang Chen, our teacher, a scientist of the planktonic research group, Third Institute of Oceanography, MNR, in recognition of his important contributions of marine ostracods of China.
Holotype. No. TIO-OHH-PP-201, adult female, length 2.57 mm, height 1.47 mm from Sta. CS-068 (14°31′N, 114°54′E) in the top of the South China Sea, 200–500 m water layer, 12 January 2015. Specimen was dissected on slide and deposited in the Marine Biological Sample Museum, in the Third Institute of Oceanography, MNR, China (Xiamen, China).
Paratypes. No. TIO-OHH-PP-202, adult female, length 2.33 mm, height 1.35 mm, No. TIO-OHH-PP-203, adult female, length 2.45 mm, height 1.41 mm, from the same locality of the holotype, and dissected on slide. TIO-OHH-PP-204, adult female, length 2.35 mm, height 1.33 mm, collected from Sta. CS-012 (7°06.46′N, 113°53.6′E) in the South China Sea, 200–500 m water layer on 2 January 2014, deposited in 5% buffered formaldehyde. Paratypes were deposited with the holotype.
Distribution. The mesopelagic water in the South China Sea.
Diagnosis. Carapace without ornamentation or setae, height about 56.5%–57.9% of length, sub-rectangle in lateral view with rounded corners; rostrums wide, developed, equilong, anteriorly and curved to downward; shoulder vaults unconspicuous, higher in anterior part, ventral margin with slightly concave, left asymmetric gland opening on postero-dorsal corner, a lateral gland opening on right postero-ventral corner, dense edge glands placed along all ventral margin; left postero-ventral margin without gland. Frontal organ segmented. In first antenna, a- and c-setae analogic with long end joint, b- and d- setae analogic without end joint. E-seta of second antenna present. Maxilla with five disto-anterior setae, one disto-medial seta, two medial setae, and three disto-posterior setae on endopod 2. Proximal-ventral group of setae of fifth limb with seven setae, endopod 1 with two ventral setae. Vesting of exopod of sixth limb strong and spinose, basale with seven ventral plumose setae, endopod 1 bare, endopod 2 without ventral seta. Furca with unpaired seta.
Carapace (Figs 1a-c and 7a, b). Carapace smooth without setae and ornamentation (pits or grooves), sub-rectangle in lateral view; shoulder vaults unconspicuous; rostrum subequal anteriorly with acutangular tip, curved downward, wide and developed; antero-ventral margin, postero-dorsal and postero-ventral corner rounded; anterior part slightly higher than posterior part; dorsal margin approximately flat; ventral margin with slightly concavity. Carapace with three groups of glands: one asymmetric gland opening on postero-dorsal corner of left valve, one lateral gland opening on right postero-ventral corner; dense edge glands placed along anterior to posterior ventral margin; postero-ventral corner of left valve without gland. Length 2.33–2.57 mm, height 1.33–1.47 mm, height about 56.5%–57.9% of length.
Frontal organ (Figs 2a, c and 7c, d). Stem and capitulum separated, straight and clavate with blunt tip, small disto-dorsal and ventral spines. Capitate base separated from first antenna.
First antenna (Figs 2a, b, d and 7c). First antenna uniramous. Basale and endopod 1 bare. Endopod 2 with one small dorsal spinose seta. Endopod 3–5 very short and small. Endopod 4 with two ventral sensory setae (a- and b-setae). Endopod 5 blunt conical with three disto-ventral sensory setae (c-, d-, e-setae). A- and c-setae analogic long columnar, thin walled and bare with long end joint; b- and d- setae equilong and bare without end joint, slightly longer than a- and c-setae; e-seta extremely long (approximately one and half length of a-seta) and spinose ventral spines with numerous small ventral spines on distal half.
Second antenna (Figs 2e, f, 3a, b and 7e, f). Limb biramous with large protopodite with powerful muscles. Endopod without c- and d-setae. Endopod 1 large, folded forward, with bend a- and b-setae, a-seta bare and short, b-seta long and spinose, about twice length of a-seta; processus mamillaris normal. Endopod 2 and 3 integrated into a small peg shaped bulge on disto-dorsal margin of endopod 1, with bare 5 setae; g-seta longest and ringed; f-seta second longest; h-, i-, j- setae equilong. Exopod 1 more than seventeen times length of 2, with one bend acerose spine on disto-dorsal margin instead of plumose seta; exopod 2–7 very short with analogous long plumose swimming seta on disto-ventral margin respectively; exopod 8 and 9 fused with one long plumose seta, one shorter plumose seta and one very small seta on tip.
Mandible (Figs 3c-e, 4a-c and 7g-j). Basale large. Exopod tiny peg shaped, with one dorsal plumose seta with bare distal part. Endopod 1 more than two times length of 2, with one disto-ventral seta. Endopod 2 short, with two setae on disto-ventral margin: outer one bare and short, inner one long with small spines on distal half length; three setae on disto-dorsal edge: mid one short and bare, others long with small ventral spines. Endopod 3 very short, with six setae on tip: seta 1 claw-shaped with distal ventral spines; seta 2 small with ventral spines; seta 3 claw-shaped and biggest with disto-ventral spines; setae 4 and 6 subequal in length; seta 5 about twice length of seta 4. Toothed edge of basale big and triangular with two bare long setae on medio-ventral side and two bare short setae on medio-distal side. Toothed edge of basale with eight distal teeth in one list. Coxal endite constituting by three parts: distal teeth list with one big and bend distal triangular papillae, one big papilla constituted four small teeth, five strip papillae, and one flat papilla; proximal teeth list with small teeth; medial part with some long and big papillae and numerous long cilia.
Maxilla (Figs 4d-f and 8a, b). Exopod with two spinose setae on tip. Endopod 1 big rectangular, with two long and three short bare setae on antero-distal edge, one spinose seta on disto-posterior edge, two long spinose setae on medial side, one long and two short spinose setae on posterior side. Terminal segment with five claws: two bilateral stout spinose claws, two inner puny bare claws and one mid spinose claw; spinose claws with disto-ventral spines. Maxilla with three hirsute endites: endite I with five plumose setae; endite II with one bare and three plumose setae; endite III with ten bare setae.
Fifth limb (Figs 5a-c, 6c and 8c). Limb biramous. Basale large and wide with eleven setae: dorsal seta (vestige of exopod) long and bare; proximal-ventral group of setae with five plumose setae and a pair of symmetric ventral spinose setae; disto-ventral group of setae with one central seta and a pair of symmetric ventral spinose setae. Endopod 1 long with two ventral setae and one dorsal seta; endopod 2 short with three long bare curved claws on tip, mid claw longest, mid and ventral claws with numerous small ventral spines. Coxale with three endites: endite I big rectangular with one short bare and one long plumose proximal setae, one small bare one small plumose and one long plumose distal setae; endite II very short with one long plumose seta; ventral group of setae of endite III with two strong bare and blunt setae, and four sharp plumose setae. Epipod with one small bare inner seta and about sixteen lathy lithe plumose setae.
Sixth limb (Figs 5d, 6d and 8d). Basale broad with one long plumose seta (vesting of exopod), two long proximo-ventral, two short ventral and three short disto-ventral plumose setae; basale without dorso-lateral seta. Exopod 1 short with one ventral seta. Exopod 2 long and thin, with one dorsal and one ventral seta. Terminal segment blunt and very short with three very long acerose claws on tip; mid claw longest with curved distal part; mid and ventral claws with numerous small disto-ventral spines. Epipod with one small bare inner seta and about seventeen lathy lithe plumose setae.
Seventh limb (Figs 6a, e and 8e). Segment 1 slender and bare. Segment 2 very short conical with one bare long seta and one bare lathy lithe seta (four times length of another) on tip. Epipod with one small bare inner seta and about fourteen lathy lithe plumose setae.
Furca (Figs 6b and 8f). Each furcal lamella with one large dorsal seta and seven claws, from long to short in turn arrangement. Seta and claws with numerous small disto-ventral spines. Furca with ventral unpaired seta.
These specimens are considered to be one species of the subfamily Conchoeciinae Müller, 1912 of family Halocyprididae Dana, 1853, according to the Chen and Chavtur’s diagnosis (Chen and Lin, 1995; Chavtur and Angel, 2011), and then we can put them into the tribe Conchoeciini, Chavtur and Angel, 2011 easily. They are very close to Polyconchoecia commixtus, the type species of genus Polyconchoecia, which genus has been reported recently and with only one species yet. They have shared characteristics as followed: (1) similar size of full adult; (2) the shapes of carapace are very close; (3) left valve has a left asymmetric gland near postero-dorsal corner; (4) right valve has a lateral gland on right postero-ventral corner; (5) dense edge glands are placed along anterior to posterior ventral margin of carapace in line; (6) exopod 1 of second antenna has one bend acerose spine on disto-dorsal margin instead of plumose seta; (7) the structures of main limbs are similar.
Although these specimens are very close to P. commixtus, P. chenii sp. nov. is discriminated by the morphological comparisons shown in Table 1. They have obvious and individual distinctions to separate from P. commixtus: (1) left asymmetric gland of carapace of the new species is moved posteriorly, the carapace have no right asymmetric gland or compound gland (Figs 1b, c and 7a, b); (2) the frontal organ of this species is separated to stem and capitulum, and has more ventral spines (Figs 2a and 7c, d); (3) in P. chenii sp. nov., the seta of endopod 2 of the first antenna is very small; (4) in P. commixtus, a- to d-setae of the sensory setae of the first antenna are analogic with long end joint, e-seta has short end joint; in these specimens, a- and c-setae are analogic with long end joint, b- and d-setae are analogic without end joint, e-seta has no end joint; (5) in P. commixtus, the endopod of the second antenna has not c-, d- and e-setae, and one small oval hump with central concave on mid-ventral margin, instead of processus mamillaris; in these specimens, e-seta is present and the processus mamillaris is normal (Figs 2f and 7e); (6) in P. commixtus, the exopod 2-4 of the second antenna have no swimming setae (Figs 2e, 3a and 7f); (7) they have unsimilar tooth edge of the coxal endite (Figs 3b, c, 7j and Table 1); (8) they have different setal counts of the mandible, maxilla, fifth limb, and sixth limb (detailed numbers are given in Table 1); (9) P. chenii sp. nov. has unpaired seta on the furcal lamella (Figs 6b and 8f).
Characteristics | P. commixtus | P. chenii sp. nov. | |
Carapace | left asymmetric gland | near postero-dorsal margin, moved anteriorly | on postero-dorsal corner |
right asymmetric gland | on right postero-ventral corner | none | |
right lateral gland | constituting a compound gland with right asymmetric gland | only on right postero-ventral corner | |
Frontal organ | stem and capitulum | fused | separated |
spines | small disto-ventral and mid-ventral spines | small disto-dorsal and ventral spines | |
First antenna | endopod 2 | with one long dorsal plumose seta | with one small dorsal plumose seta |
sensory setae | a- to d-setae analogic, long columnar, thin walled and bare, with long end joint; e-seta bare, with short end joint | a- and c-setae analogic, long columnar, thin walled and bare with long end joint; b- and d- setae analogic, equilong and bare without end joint, slightly longer than a- and c-setae; e- seta spinose, without short end joint | |
Second antenna | endopod | c-, d-, e-setae absent; b-seta bare; one small oval hump with central concave on mid-ventral margin, instead of processus mamillaris | e-setae present; b-seta spinose; processus mamillaris normal. |
exopod | exopod 1 and 2 fused, exopod 2-4 bare, exopod 8 and 9 separated; terminal plumose seta with single tip | exopod 1 and 2 separated, exopod 2-4 with plumose setae, exopod 8 and 9 fused | |
Mandible | coxale teeth side | with eight distal teeth | with six distal teeth |
tooth endites | with four tooth plates | with three tooth plates | |
endopod | endopod 1 with one ventral seta, and one dorsal seta; endopod 2 with one disto-ventral seta; terminal segment with seven spinose setae | endopod 1 with one ventral seta, without dorsal seta; endopod 2 with two disto-ventral setae; terminal segment with six setae, ventral three bare | |
Maxilla | endopod | endopod 1 with six disto-anterior setae, one disto-medial seta, none medial seta, and two disto-posterior setae; mid seta of terminal segment bare | endopod 1 with five disto-anterior setae, one disto-medial seta, two medial setae, and three disto-posterior setae; mid seta of terminal segment spinose |
endites | endite I with eleven plumose setae, endite II with ten plumose setae, endite III with eight plumose setae | endite I with five plumose setae; endite II with one bare and three plumose setae; endite III with ten bare setae | |
Fifth limb | basale | proximal-ventral group of setae with four setae | proximal-ventral group of setae with seven setae |
endopod | endopod 1 with one ventral seta | endopod 1 with two ventral setae | |
endites | endite I with one seta; endite II with two setae; endite III with one proximal seta, three sharp and two blunt distal setae | endite I with five setae; endite II with one seta; endite III with none proximal seta, four sharp and two blunt distal setae | |
Sixth limb | basale | disto-dorsal seta (vesting of exopod) small and bare; three small ventral setae. | disto-dorsal seta (vesting of exopod) strong and spinose; seven ventral plumose setae |
endopod | endopod 1 with one ventral seta; endopod 2 with one ventral seta | endopod 1 bare; endopod 2 without ventral seta | |
Furca | unpaired seta | no | yes |
The ostracod faunae of the South China Sea have been known mainly from plankton surveys in surface water or euphotic zone (0–200 m). The local ostracod diversity of deep environments may equal or exceed that of their epi-pelagic relatives (Gianni, 2004; Danovaro et al., 2008). In these years, there are more and more deep-water species have been discovered and reported (Yin et al., 2014; Tanaka and Yasuhara, 2016; Du et al., 2018; Xiang et al., 2018). This work is the second discovery of the genus Polyconchoecia from the world.
We thank Patrick Page-McCaw (Vanderbilt University, USA), Mingyu Li (Xiamen University, China), Guangcheng Chen for critical reading of the manuscript. We are thankful for our zooplankton research group of Third Institute of Oceanography, MNR, for their valuable suggestions for the manuscript preparation.
[1] |
Ai Jiaqiu, Pei Zhilin, Yao Baidong, et al. 2021. AIS data aided Rayleigh CFAR ship detection algorithm of multiple-target environment in SAR images. IEEE Transactions on Aerospace and Electronic Systems,
|
[2] |
Aiello M, Vezzoli R, Gianinetto M. 2019. Object-based image analysis approach for vessel detection on optical and radar images. Journal of Applied Remote Sensing, 13(1): 014502
|
[3] |
Albukhanajer W A, Jin Yaochu, Briffa J A. 2017. Classifier ensembles for image identification using multi-objective Pareto features. Neurocomputing, 238: 316–327. doi: 10.1016/j.neucom.2017.01.067
|
[4] |
Amozegar M, Khorasani K. 2016. An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines. Neural Networks, 76: 106–121. doi: 10.1016/j.neunet.2016.01.003
|
[5] |
Ao Wei, Xu Feng, Li Yongchen, et al. 2018. Detection and discrimination of ship targets in complex background from spaceborne ALOS-2 SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(2): 536–550. doi: 10.1109/JSTARS.2017.2787573
|
[6] |
Baudat G, Anouar F. 2000. Generalized discriminant analysis using a kernel approach. Neural Computation, 12(10): 2385–2404. doi: 10.1162/089976600300014980
|
[7] |
Belkin M, Niyogi P. 2004. Semi-supervised learning on Riemannian manifolds. Machine Learning, 56(1): 209–239
|
[8] |
Bhanu B, Lin Yingqiang. 2003. Genetic algorithm based feature selection for target detection in SAR images. Image and Vision Computing, 21(7): 591–608. doi: 10.1016/S0262-8856(03)00057-X
|
[9] |
Blum A, Mitchell T. 1998. Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory. Madison, WI: ACM, 92–100
|
[10] |
Cai Zhaowei, Vasconcelos N. 2021. Cascade R-CNN: High quality object detection and instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(5): 1483–1498. doi: 10.1109/TPAMI.2019.2956516
|
[11] |
Camps-Valls G, Marsheva T V B, Zhou Dengyong. 2007. Semi-supervised graph-based hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 45(10): 3044–3054. doi: 10.1109/TGRS.2007.895416
|
[12] |
Chang Yanglang, Anagaw A, Chang Lena, et al. 2019. Ship detection based on YOLOv2 for SAR imagery. Remote Sensing, 11(7): 786. doi: 10.3390/rs11070786
|
[13] |
Chen Shiyuan, Li Xiaojiang, Chi Shaoquan, et al. 2020. Ship target discrimination in SAR images based on BOW model with multiple features and spatial pyramid matching. IEEE Access, 8: 166071–166082. doi: 10.1109/ACCESS.2020.3022642
|
[14] |
Cui Cheng, Guo Ruoyu, Du Yuning, et al. 2021. Beyond self-supervision: A simple yet effective network distillation alternative to improve backbones. arXiv preprint, arXiv: 2103.05959
|
[15] |
Dasgupta S, Littman M L, McAllester D. 2001. PAC generalization bounds for co-training. In: Proceedings of the 14th International Conference on Neural Information Processing Systems. Vancouver, British Columbia: MIT Press, 375–382
|
[16] |
Deng Jia, Dong Wei, Socher R, et al. 2009. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 248–255
|
[17] |
Di Martino G, Iodice A, Riccio D, et al. 2014. Filtering of azimuth ambiguity in stripmap synthetic aperture radar images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(9): 3967–3978. doi: 10.1109/JSTARS.2014.2320155
|
[18] |
Du Lan, Dai Hui, Wang Yan, et al. 2020. Target discrimination based on weakly supervised learning for high-resolution SAR images in complex scenes. IEEE Transactions on Geoscience and Remote Sensing, 58(1): 461–472. doi: 10.1109/TGRS.2019.2937175
|
[19] |
Falqueto L E, Sá J A S, Paes R L, et al. 2019. Oil rig recognition using convolutional neural network on Sentinel-1 SAR images. IEEE Geoscience and Remote Sensing Letters, 16(8): 1329–1333. doi: 10.1109/LGRS.2019.2894845
|
[20] |
Gao Gui. 2011. An improved scheme for target discrimination in high-resolution SAR images. IEEE Transactions on Geoscience and Remote Sensing, 49(1): 277–294. doi: 10.1109/TGRS.2010.2052623
|
[21] |
Gao Fei, Shi Wei, Wang Jun, et al. 2019. Enhanced feature extraction for ship detection from multi-resolution and multi-scene synthetic aperture radar (SAR) images. Remote Sensing, 11(22): 2694. doi: 10.3390/rs11222694
|
[22] |
Haider N S, Singh B K, Periyasamy R, et al. 2019. Respiratory sound based classification of chronic obstructive pulmonary disease: A risk stratification approach in machine learning paradigm. Journal of Medical Systems, 43(8): 255. doi: 10.1007/s10916-019-1388-0
|
[23] |
He Jinglu, Wang Yinghua, Liu Hongwei, et al. 2018. A novel automatic PolSAR ship detection method based on superpixel-level local information measurement. IEEE Geoscience and Remote Sensing Letters, 15(3): 384–388. doi: 10.1109/LGRS.2017.2789204
|
[24] |
He Tong, Zhang Zhi, Zhang Hang, et al. 2019. Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE, 558–567
|
[25] |
Hua Wenqiang, Wang Shuang, Liu Hongying, et al. 2017. Semisupervised PolSAR image classification based on improved cotraining. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11): 4971–4986. doi: 10.1109/JSTARS.2017.2728067
|
[26] |
Huang Xin, Wang Xinxin, Lv Wenyu, et al. 2021. PP-YOLOv2: A practical object detector. arXiv preprint, arXiv: 2104.10419
|
[27] |
Hwang J I, Jung H S. 2018. Automatic ship detection using the artificial neural network and support vector machine from X-band SAR satellite images. Remote Sensing, 10(11): 1799. doi: 10.3390/rs10111799
|
[28] |
Interferometric wide swath. 2020. https://sentinel.esa.int/web/sentinel/user-guides/sentinel-1-sar/acquisition-modes/interferometric-wide-swath[2020-9-29]
|
[29] |
Kang Miao, Ji Kefeng, Leng Xiangguang, et al. 2017. Contextual region-based convolutional neural network with multilayer fusion for SAR ship detection. Remote Sensing, 9(8): 860. doi: 10.3390/rs9080860
|
[30] |
Kreithen D E, Halversen S D, Owirka G J. 1993. Discriminating targets from clutter. The Lincoln Laboratory Journal, 6(1): 25–52
|
[31] |
Lang Haitao, Tao Yunhong, Niu Lihui, et al. 2020. A new scattering similarity based metric for ship detection in polarimetric synthetic aperture radar image. Acta Oceanologica Sinica, 39(5): 145–150. doi: 10.1007/s13131-020-1563-7
|
[32] |
Lang Haitao, Zhang Jie, Zhang Xi, et al. 2016. Ship classification in SAR image by joint feature and classifier selection. IEEE Geoscience and Remote Sensing Letters, 13(2): 212–216. doi: 10.1109/LGRS.2015.2506570
|
[33] |
Li Yongxu, Lai Xudong, Zhang Xi, et al. 2019. Comparative study of sea clutter distribution and ship detectors’ performance for Sentinel-1 synthetic aperture radar image. Journal of Applied Remote Sensing, 13(4): 044506
|
[34] |
Lin T Y, Dollár P, Girshick R, et al. 2017. Feature pyramid networks for object detection. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI: IEEE, 936–944
|
[35] |
Liu Hongying, Zhu Dexiang, Yang Shuyuan, et al. 2016. Semisupervised feature extraction with neighborhood constraints for polarimetric SAR classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(7): 3001–3015. doi: 10.1109/JSTARS.2016.2532922
|
[36] |
Ma Liyong, Tang Lidan, Xie Wei, et al. 2018. Ship detection in SAR using extreme learning machine. In: International Conference on Machine Learning and Intelligent Communications. Heidelberg: Springer, 558–568
|
[37] |
Nigam K, McCallum A K, Thrun S, et al. 2000. Text classification from labeled and unlabeled documents using EM. Machine Learning, 39(2): 103–134
|
[38] |
PaddlePaddle Authors. 2021. PaddlePaddle/Paddledetection: object detection and instance segmentation toolkit based on PaddlePaddle. https://github.com/PaddlePaddle/PaddleDetection[2021-10-20]
|
[39] |
Pelich R, Longépé N, Mercier G, et al. 2015. AIS-based evaluation of target detectors and SAR sensors characteristics for maritime surveillance. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(8): 3892–3901. doi: 10.1109/JSTARS.2014.2319195
|
[40] |
Ren Shaoqing, He Kaiming, Girshick R, et al. 2017. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137–1149. doi: 10.1109/TPAMI.2016.2577031
|
[41] |
Seijo-Pardo B, Porto-Díaz I, Bolón-Canedo V, et al. 2017. Ensemble feature selection: homogeneous and heterogeneous approaches. Knowledge-Based Systems, 118: 124–139. doi: 10.1016/j.knosys.2016.11.017
|
[42] |
Sentinel-1 Observation Scenario. 2020. https://sentinel.esa.int/web/sentinel/missions/sentinel-1/observation-scenario[2020-09-29]
|
[43] |
Tello M, López-Martínez C, Mallorquí J J, et al. 2009. Advances in unsupervised ship detection with multiscale techniques. In: 2009 IEEE International Geoscience and Remote Sensing Symposium. Cape Town: IEEE, IV-979–IV-982
|
[44] |
Verbout S M, Weaver A L, Novak L M. 1998. New image features for discriminating targets from clutter. In: Proceedings Volume 3395, Radar Sensor Technology III. Orlando, FL: SPIE, 120–137
|
[45] |
Vespe M, Greidanus H. 2012. SAR image quality assessment and indicators for vessel and oil spill detection. IEEE Transactions on Geoscience and Remote Sensing, 50(11): 4726–4734. doi: 10.1109/TGRS.2012.2190293
|
[46] |
Wang Shuang, Guo Yanhe, Hua Wenqiang, et al. 2020. Semi-supervised PolSAR image classification based on improved tri-training with a minimum spanning tree. IEEE Transactions on Geoscience and Remote Sensing, 58(12): 8583–8597. doi: 10.1109/TGRS.2020.2988982
|
[47] |
Ward K D, Tough R J A, Watts S. 2006. Sea Clutter: Scattering the K Distribution and Radar Performance. London: The Institution of Engineering and Technology
|
[48] |
Zhang Tianwen, Zhang Xiaoling, Ke Xiao, et al. 2020. LS-SSDD-v1.0: A deep learning dataset dedicated to small ship detection from large-scale Sentinel-1 SAR images. Remote Sensing, 2020,12(18): 2997
|
[49] |
Zhou Zhihua, Li Ming. 2005. Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on knowledge and Data Engineering, 17(11): 1529–1541. doi: 10.1109/TKDE.2005.186
|
[50] |
Zhu Xizhou, Hu Han, Lin S, et al. 2019. Deformable ConvNets V2: More deformable, better results. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA: IEEE, 9300–9308
|
[51] |
Zhu Xizhou, Su Weijie, Lu Lewei, et al. 2021. Deformable DETR: Deformable transformers for end-to-end object detection. arXiv: 2010.04159
|
Characteristics | P. commixtus | P. chenii sp. nov. | |
Carapace | left asymmetric gland | near postero-dorsal margin, moved anteriorly | on postero-dorsal corner |
right asymmetric gland | on right postero-ventral corner | none | |
right lateral gland | constituting a compound gland with right asymmetric gland | only on right postero-ventral corner | |
Frontal organ | stem and capitulum | fused | separated |
spines | small disto-ventral and mid-ventral spines | small disto-dorsal and ventral spines | |
First antenna | endopod 2 | with one long dorsal plumose seta | with one small dorsal plumose seta |
sensory setae | a- to d-setae analogic, long columnar, thin walled and bare, with long end joint; e-seta bare, with short end joint | a- and c-setae analogic, long columnar, thin walled and bare with long end joint; b- and d- setae analogic, equilong and bare without end joint, slightly longer than a- and c-setae; e- seta spinose, without short end joint | |
Second antenna | endopod | c-, d-, e-setae absent; b-seta bare; one small oval hump with central concave on mid-ventral margin, instead of processus mamillaris | e-setae present; b-seta spinose; processus mamillaris normal. |
exopod | exopod 1 and 2 fused, exopod 2-4 bare, exopod 8 and 9 separated; terminal plumose seta with single tip | exopod 1 and 2 separated, exopod 2-4 with plumose setae, exopod 8 and 9 fused | |
Mandible | coxale teeth side | with eight distal teeth | with six distal teeth |
tooth endites | with four tooth plates | with three tooth plates | |
endopod | endopod 1 with one ventral seta, and one dorsal seta; endopod 2 with one disto-ventral seta; terminal segment with seven spinose setae | endopod 1 with one ventral seta, without dorsal seta; endopod 2 with two disto-ventral setae; terminal segment with six setae, ventral three bare | |
Maxilla | endopod | endopod 1 with six disto-anterior setae, one disto-medial seta, none medial seta, and two disto-posterior setae; mid seta of terminal segment bare | endopod 1 with five disto-anterior setae, one disto-medial seta, two medial setae, and three disto-posterior setae; mid seta of terminal segment spinose |
endites | endite I with eleven plumose setae, endite II with ten plumose setae, endite III with eight plumose setae | endite I with five plumose setae; endite II with one bare and three plumose setae; endite III with ten bare setae | |
Fifth limb | basale | proximal-ventral group of setae with four setae | proximal-ventral group of setae with seven setae |
endopod | endopod 1 with one ventral seta | endopod 1 with two ventral setae | |
endites | endite I with one seta; endite II with two setae; endite III with one proximal seta, three sharp and two blunt distal setae | endite I with five setae; endite II with one seta; endite III with none proximal seta, four sharp and two blunt distal setae | |
Sixth limb | basale | disto-dorsal seta (vesting of exopod) small and bare; three small ventral setae. | disto-dorsal seta (vesting of exopod) strong and spinose; seven ventral plumose setae |
endopod | endopod 1 with one ventral seta; endopod 2 with one ventral seta | endopod 1 bare; endopod 2 without ventral seta | |
Furca | unpaired seta | no | yes |