Page 216 - 《水产学报》2023年第1期

王禹莎，等 水产学报, 2023, 47(1): 019516

on Computer Vision. Venice, Italy: IEEE, 2017: 2980- towards real-time object detection with region proposal
2988. networks[J]. IEEE Transactions on Pattern Analysis and
[22] Brosnan T, Sun D W. Improving quality inspection of Machine Intelligence, 2017, 39(6): 1137-1149.
food products by computer vision –a review[J]. Journal [33] Hsieh C L, Chang H Y, Chen F H, et al. A simple and
of Food Engineering, 2004, 61(1): 3-16. effective digital imaging approach for tuna fish length
[23] Blonk R J W, Komen J, Tenghe A, et al. Heritability of measurement compatible with fishing operations[J].
shape in common sole, Solea solea, estimated from Computers and Electronics in Agriculture, 2011, 75(1):
image analysis data[J]. Aquaculture, 2010, 307(1-2): 6- 44-51.
11. [34] Monkman G G, Hyder K, Kaiser M J, et al. Using
[24] Gjedrem T. Flesh quality improvement in fish through machine vision to estimate fish length from images using
breeding[J]. Aquaculture International, 1997, 5(3): 197- regional convolutional neural networks[J]. Methods in
206. Ecology and Evolution, 2019, 10(12): 2045-2056.
[25] Navarro A, Zamorano M J, Hildebrandt S, et al. Estim- [35] Muñoz-Benavent P, Andreu-García G, Valiente-
ates of heritabilities and genetic correlations for body González J M, et al. Enhanced fish bending model for
composition traits and G × E interactions, in gilthead automatic tuna sizing using computer vision[J]. Com-
seabream (Sparus auratus L. )[J]. Aquaculture, 2009, puters and Electronics in Agriculture, 2018, 150: 52-61.
295(3-4): 183-187. [36] 房舒. 基于深度学习的鱼类表型数据测量方法研究
[26] Tang Q, Qiu W, Zhou Y C. Classification of complex [D]. 杭州: 浙江大学, 2021.
power quality disturbances using optimized S-transform Fang S. Research on fish phenotypic data measurement
and kernel SVM[J]. IEEE Transactions on Industrial method based on deep learning[D]. Hangzhou: Zhejiang
Electronics, 2020, 67(11): 9715-9723. University, 2021 (in Chinese).
[27] Zhou C, Zhang B H, Lin K, et al. Near-infrared imaging [37] 黄康为. 基于机器视觉的水下动态鱼体尺寸测量方法
to quantify the feeding behavior of fish in aquaculture[J]. 研究与实现 [D]. 杭州: 浙江大学, 2021.
Computers and Electronics in Agriculture, 2017, 135: Huang K W. Research and implement of machine vision
233-241. based underwater dynamic fish size measurement
[28] Jia B B, Zhang M L. Multi-dimensional classification via method[D]. Hangzhou: Zhejiang University, 2021 (in
kNN feature augmentation[J]. Pattern Recognition, 2020, Chinese).
106: 107423. [38] Haffray P, Bugeon J, Rivard Q, et al. Genetic paramet-
[29] Tharwat A, Hemedan A A, Hassanien A E, et al. A bio- ers of in-vivo prediction of carcass, head and fillet yields
metric-based model for fish species classification[J]. by internal ultrasound and 2D external imagery in large
Fisheries Research, 2018, 204: 324-336. rainbow trout (Oncorhynchus mykiss)[J]. Aquaculture,
[30] Cai K W, Miao X Y, Wang W, et al. A modified 2013, 410-411: 236-244.
YOLOv3 model for fish detection based on MobileNetv1 [39] Kause A, Paananen T, Ritola O, et al. Direct and indir-
as backbone[J]. Aquacultural Engineering, 2020, 91: ect selection of visceral lipid weight, fillet weight, and
102117. fillet percentage in a rainbow trout breeding program[J].
[31] Prasetyo E, Suciati N, Fatichah C. A comparison of Journal of Animal Science, 2007, 85(12): 3218-3227.
YOLO and mask R-CNN for segmenting head and tail of [40] Navarro A, Zamorano M J, Hildebrandt S, et al. Estim-
fish[C]//Proceedings of the 2020 4th International Con- ates of heritabilities and genetic correlations for growth
ference on Informatics and Computational Sciences (ICI- and carcass traits in gilthead seabream (Sparus auratus
CoS). Semarang, Indonesia: IEEE, 2020: 1-6. L. ), under industrial conditions[J]. Aquaculture, 2009,
[32] Ren S, He K, Girshick R B, et al. Faster R-CNN: 289(3-4): 225-230.

中国水产学会主办 sponsored by China Society of Fisheries https://www.china-fishery.cn
9