Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Journal Home About Issues in Progress Current Issue All Issues Early Posting Feature Issues

Optical counting platform of shrimp larvae using masked k-means and a side window filter

Kun Qian and Hong-chao Duan

Open Access Open Access

Abstract

Accurate and efficient counting of shrimp larvae is crucial for monitoring reproduction patterns, assessing growth rates, and evaluating the performance of aquaculture. Traditional methods via density estimation are ineffective in the case of high density. In addition, the image contains bright spots utilizing the point light source or the line light source. Therefore, in this paper an automated shrimp counting platform based on optics and image processing is designed to complete the task of counting shrimp larvae. First, an area light source ensures a uniformly illuminated environment, which helps to obtain shrimp images with high resolution. Then, a counting algorithm based on improved ${ k}$-means and a side window filter (SWF) is designed to achieve an accurate number of shrimp in the lamp house. Specifically, the SWF technique is introduced to preserve the body contour of shrimp larvae, and eliminate noise, such as water impurities and eyes of shrimp larvae. Finally, shrimp larvae are divided into two groups, independent and interdependent, and counted separately. Experimental results show that the designed optical counting system is excellent in terms of visual effect and objective evaluation.

© 2023 Optica Publishing Group

Full Article  |  PDF Article
More Like This
ShrimpSeg: a local–global structure for the mantis shrimp point cloud segmentation network with contextual reasoning

Tengping Jiang, Shan Liu, Qinyu Zhang, Lin Zhao, Jian Sun, and Yongjun Wang
Appl. Opt. 62(10) D97-D103 (2023)

Dual-mode LiDAR SoC with an on-chip interframe filter and common optical platform design for keystone correction and auto-focus

Jier Wang, Hengwei Yu, and Patrick Yin Chiang
Appl. Opt. 62(29) 7658-7668 (2023)

ASA-BiSeNet: improved real-time approach for road lane semantic segmentation of low-light autonomous driving road scenes

Yang Liu, Fulong Yi, Yuhua Ma, and Yongfu Wang
Appl. Opt. 62(19) 5224-5235 (2023)

View More...

Data availability

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Cited By

Optica participates in Crossref's Cited-By Linking service. Citing articles from Optica Publishing Group journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (17)
Fig. 1.
Fig. 1. Structural diagram of area light source.

Download Full Size | PDF

Fig. 2.
Fig. 2. Designed container with a specific camera.

Download Full Size | PDF

Fig. 3.
Fig. 3. Optical acquisition platform.

Download Full Size | PDF

Fig. 4.
Fig. 4. Comparison results of different light sources. (a) Line light source. (b) Area light source.

Download Full Size | PDF

Fig. 5.
Fig. 5. Structure of shrimp larvae.

Download Full Size | PDF

Fig. 6.
Fig. 6. Group of shrimp larvae.

Download Full Size | PDF

Fig. 7.
Fig. 7. Image binaryzation. (a) Original image. (b) Binary image.

Download Full Size | PDF

Fig. 8.
Fig. 8. Contrast enhancement. (a) Original image. (b) Enhanced image.

Download Full Size | PDF

Fig. 9.
Fig. 9. Effect of the mask operation.

Download Full Size | PDF

Fig. 10.
Fig. 10. Clustering result ($k = 6$). (a)–(e) Five clusters of background information. (f) Cluster of shrimp larvae.

Download Full Size | PDF

Fig. 11.
Fig. 11. Classification of shrimp larvae. (a) Segmented image of shrimp larvae. (b) Sticky shrimp larvae. (c) Independent shrimp larvae.

Download Full Size | PDF

Fig. 12.
Fig. 12. Flow chart of the proposed algorithm.

Download Full Size | PDF

Fig. 13.
Fig. 13. Comparison results in the case of sparse density (151). (a) MA (144). (b) Canny (141). (c) ${K}$-means (311). (d) Blob (145). (e) Masked ${k}$-means (153).

Download Full Size | PDF

Fig. 14.
Fig. 14. Comparison results in the case of medium density (1005). (a) MA (851). (b) Canny (873). (c) ${K}$-means (2317). (d) Blob (978). (e) Masked ${k}$-means (997).

Download Full Size | PDF

Fig. 15.
Fig. 15. Comparison results in the case of dense density (2135). (a) MA (1244). (b) Canny (1718). (c) ${K}$-means (3140). (d) Blob (2008). (e) Masked ${k}$-means (2089).

Download Full Size | PDF

Fig. 16.
Fig. 16. Ablation results in the case of dense shrimp. (a) Original image. (b) Result without filtering. (c) Result with the opening operation. (d) Processing result with SWF.

Download Full Size | PDF

Fig. 17.
Fig. 17. Ablation results in the case of sparse shrimp. (a) Original image. (b) Result without filtering. (c) Result with the opening operation. (d) Processing result with SWF.

Download Full Size | PDF

Tables (1)

Tables Icon

Table 1. Comparison of the ER

View Table

Equations (8)

Equations on this page are rendered with MathJax. Learn more.

n 1 sin ⁡ θ 1 = n 2 sin ⁡ θ 2 ,
V o u t = A ⋅ ( V i n ) γ ,
d ij = ‖ x i − μ j ‖ 2 ,
C λ i = C λ i ⋃ { x i } ,
μ j = 1 | C j | ∑ x ∈ C j x .
I i r , ρ , θ = F ( q i , r , ρ , θ ) ,
I SWF = a r g min ∀ I i r , ρ , θ ⁡ ‖ q i − I i r , ρ , θ ‖ 2 2 .
E = | I d − A c | / A c .
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use