US 11,756,206 B2
Recognition method and device for analyzing a starvation extent of a whiteleg shrimp based on underwater imaging
Pengcheng Nie, Hangzhou (CN); Yong He, Hangzhou (CN); Guoquan Zeng, Hangzhou (CN); Chengyong Cai, Hangzhou (CN); Junqi Yu, Hangzhou (CN); Hui Zhang, Hangzhou (CN); Jianzhong Ma, Hangzhou (CN); Chen Chen, Hangzhou (CN); and Maocang Yan, Hangzhou (CN)
Assigned to Zhejiang University, Hangzhou (CN); and Zhejiang Mariculture Research Institute, Wenzhou (CN)
Filed by ZHEJIANG UNIVERSITY, Hangzhou (CN); and ZHEJIANG MARICULTURE RESEARCH INSTITUTE, Wenzhou (CN)
Filed on Apr. 12, 2021, as Appl. No. 17/228,104.
Claims priority of application No. 202010286454.5 (CN), filed on Apr. 13, 2020.
Prior Publication US 2021/0319562 A1, Oct. 14, 2021
Int. Cl. G06T 7/13 (2017.01); G06T 7/12 (2017.01); G06T 7/292 (2017.01); G06T 7/246 (2017.01); G06T 7/90 (2017.01); G06T 5/00 (2006.01); G06T 5/20 (2006.01); G06V 40/10 (2022.01); H04N 23/74 (2023.01)
CPC G06T 7/13 (2017.01) [G06T 5/002 (2013.01); G06T 5/20 (2013.01); G06T 7/12 (2017.01); G06T 7/246 (2017.01); G06T 7/292 (2017.01); G06T 7/90 (2017.01); G06V 40/10 (2022.01); H04N 23/74 (2023.01); G06T 2207/20132 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A recognition device for analyzing a starvation extent of a whiteleg shrimp based on underwater imaging, comprising a bracket, a camera mounted on a top of the bracket, a plurality of light sources for illumination, a memory storing program codes, and a processor connected with the camera, the processor executing the stored codes for:
receiving an image of shrimp collected by the camera, extracting an edge image of the shrimp after preprocessing the collected image, and calculating a movement speed of shrimp and a quantity of baits after recognizing a head and a tail of the shrimp, to recognize the starvation extent of the shrimp; and
calculating the movement speed of the shrimp is comparing a movement distance of a same body in two adjacent frame images based on ethological features of the shrimp; and calculating the quantity of baits is comparing the quantities of baits in two adjacent frame images to determine whether the quantity of baits increases.