Beyond texture: unveiling spiny crown-of-thorns starfish with multiresolution analysis

Abstract

Coral reefs are essential ecosystems in the vast expanses of oceans, nurturing various forms of marine life within their vibrant and expansive structures. However, these underwater paradises suffer considerable threat from the population explosions of crown-of-thorns starfish (COTS), which detrimentally affect scleractinian corals across the Indo-Pacific region. This study addresses the early drawback of solely relying on texture analysis for COTS detection, recognizing the associated insufficiency due to variability in reef substrates. By integrating multiresolution analysis employing wavelet transform, edge information, and texture analysis using gray-level co-occurrence probability, this approach employs crucial Haralick features refined for pattern recognition. This enables a more detailed understanding of COTS traits, including the detection of the numerous sharp spines that cover their upper bodies. This approach considerably enhances classification reliability, making notable progress with an impressive accuracy of 95.00% using the eXtreme Gradient Boosting (XGBoost) Classifier. Moreover, this model streamlines processing requirements by increasing computational and memory efficiencies, making it more resource-efficient than the current models. This advancement enhances detection and opens avenues for early intervention and future research. Furthermore, integrating the model with underwater imagery could enable citizen science initiatives and autonomous underwater vehicle (AUV) surveys. Empowering trained volunteers and equipping AUVs with this technology could considerably expand coral reef monitoring efforts. Early COTS outbreak detection allows for shorter response times, potentially mitigating the damage and facilitating targeted conservation strategies.

Keywords

Coral reef conservation / Crown-of-thorns starfish / Discrete wavelet transforms / Gray-level co-occurrence probability

References

[1] Abbasi A, MahmoudZadeh S, Yazdani A. A cooperative dynamic task assignment framework for cotsbot auvs. IEEE Trans Autom Sci Eng, 2022, 19(2): 1163-1179,

[2] Arima M, Yoshida K, Tonai H (2014) Development of a coral monitoring system for the use of underwater vehicle. In: OCEANS 2014-Taipei, Taipei, pp 1–6. https://doi.org/10.1109/OCEANS-TAIPEI.2014.6964462

[3] Banerji S, Sinha A, Liu C. New image descriptors based on color, texture, shape, and wavelets for object and scene image classification. Neurocomputing, 2013, 117: 173-185,

[4] Beijbom O, Edmunds PJ, Kline DI, Mitchell BG, Kriegman D (2012) Automated annotation of coral reef survey images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, pp 1170–1177. https://doi.org/10.1109/CVPR.2012.6247798

[5] Bonin-Font F, Burguera A, Lisani JL. Visual discrimination and large area mapping of posidonia oceanica using a lightweight auv. IEEE Access, 2017, 5: 24479-24494,

[6] Cesar H, Burke L, Pet-Soede L (2003) The economics of worldwide coral reef degradation. CEEC, Arnhem

[7] Chandler JF, Burn D, Caballes CF, Doll P, Kwong S, Lang B et al (2023) Increasing densities of Pacific crown-of-thorns starfish (Acanthaster cf. solaris) at Lizard Island, northern Great Barrier Reef, resolved using a novel survey method. Sci Rep 13(1):19306

[8] Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, pp 785–794. https://doi.org/10.1145/2939672.2939785

[9] Clement R, Dunbabin M, Wyeth G (2005) Towards robust image detection of crown-of-thorns starfish for autonomous population monitoring. In: Proceedings of the 2005 Australasian Conference on Robotics & Automation (ACRA 2005), Sydney, pp 1–8. https://doi.org/10.1109/ACRA.2005.1616460

[10] Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE Trans Inf Theory, 1990, 36(5): 961-1005,

[11] Dayoub F, Dunbabin M, Corke P (2015) Robotic detection and tracking of crown-of-thorns starfish. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, pp 1921–1928. https://doi.org/10.1109/IROS.2015.7353629

[12] Deaker DJ, Byrne M. Crown of thorns starfish life-history traits contribute to outbreaks, a continuing concern for coral reefs. Emerg Top Life Sci, 2022, 6(1): 67-79,

[13] Dirnwoeber M, Machan R, Herler J. Coral reef surveillance: infrared-sensitive video surveillance technology as a new tool for diurnal and nocturnal long-term field observations. Remote Sens, 2012, 4(11): 3346-3362,

[14] Dumas P, Fiat S, Durbano A, et al.. Citizen science, a promising tool for detecting and monitoring outbreaks of the crown-of-thorns starfish acanthaster spp. Sci Rep, 2020, 10: 291,

[15] Fisher R, O’Leary RA, Low-Choy S, et al.. Species richness on coral reefs and the pursuit of convergent global estimates. Curr Biol, 2015, 25(4): 500-505,

[16] Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern SMC, 1973, SMC–3(6): 610-621,

[17] Khan MM, Makoonlall A, Nazurally N, et al.. Identification of crown of thorns starfish (cots) using convolutional neural network (cnn) and attention model. PLoS ONE, 2023, 18(4): e0283121,

[18] Huang K, Aviyente S. Wavelet feature selection for image classification. IEEE Trans Image Process, 2008, 17(9): 1709-1720,

[19] Jan RQ, Shao YT, Fan Y, et al.. An underwater camera system for real-time coral reef fish monitoring. Raffles Bull Zool, 2007, 14: 273-279

[20] Kayal M, Bosserelle P, Adjeroud M. Bias associated with the detectability of the coral-eating pest crown-of-thorns seastar and implications for reef management. R Soc Open Sci, 2017, 4: 170396,

[21] Keesing JK, Lucas JS. Field measurement of feeding and movement rates of the crown-of-thorns starfish acanthaster planci (l.). J Exp Mar Biol Ecol, 1992, 156(1): 89-104,

[22] Kiaee N, Hashemizadeh E, Zarrinpanjeh N. Using GLCM features in Haar wavelet transformed space for moving object classification. IET Intell Transp Syst, 2019, 13(7): 1148-1153,

[23] Krishna S, Kumar D, Dwivedi VK (2022) Biorthogonal wavelets for multiresolution image compression. In: 2022 2nd International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), Mathura, pp 1–7. https://doi.org/10.1109/PARC52418.2022.9726558

[24] Kumar G, Bhatia PK (2014) A detailed review of feature extraction in image processing systems. In: 2014 Fourth International Conference on Advanced Computing & Communication Technologies, Rohtak, pp 5–12. https://doi.org/10.1109/ACCT.2014.74

[25] Li Y, Liu J, Kusy B, Marchant R, Do B, Merz T et al (2022) A real-time edge-AI system for reef surveys. In: Proceedings of the 28th Annual International Conference on Mobile Computing and Networking, Sydney, pp 903–906. https://doi.org/10.1145/3495243.3558278

[26] Lina JM. Image processing with complex daubechies wavelets. J Math Imaging Vis, 1997, 7: 211-223,

[27] Ling S, Cowan ZL, Boada J, et al.. Homing behaviour by destructive crown-of-thorns starfish is triggered by local availability of coral prey. Proc R Soc B Biol Sci, 2020, 287: 20201341,

[28] Liu J, Kusy B, Marchant R, Do B, Merz T, Crosswell J et al (2021) The CSIRO crown-of-thorn starfish detection dataset. Preprint at arXiv:2111.14311

[29] Mokji MM, Bakar SARA (2007) Gray level co-occurrence matrix computation based on Haar wavelet. In: Computer Graphics, Imaging and Visualisation (CGIV 2007), Bangkok, pp 273–279. https://doi.org/10.1109/CGIV.2007.45

[30] Nguyen Q. Detrimental starfish detection on embedded system: A case study of yolov5 deep learning algorithm and tensorflow lite framework. J Comput Sci Inst, 2022, 23: 105-111,

[31] Park JH, Kim KO, Yang YK (2001) Image fusion using multiresolution analysis. In: IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 Interational Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), Sydney, pp 864–866. https://doi.org/10.1109/IGARSS.2001.976662

[32] Pooloo N, Aumeer W, Khoodeeram R (2021) Monitoring coral reefs death causes with artificial intelligence. In: 2021 IST-Africa Conference (IST-Africa), South Africa, pp 1–9

[33] Sharif I, Khare S. Comparative analysis of haar and daubechies wavelet for hyper spectral image classification. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci, 2014, XL–8: 937-941,

[34] Sheth S, Prajapati DJ (2022) Recognition of underwater starfishes using deep learning. In: 2022 Second International Conference on Next Generation Intelligent Systems (ICNGIS), Kottayam, pp 1–5. https://doi.org/10.1109/ICNGIS54955.2022.10079811

[35] Stanković RS, Falkowski BJ. The haar wavelet transform: its status and achievements. Comput Electr Eng, 2003, 29(1): 25-44,

[36] Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, pp 10778–10787. https://doi.org/10.1109/CVPR42600.2020.01079

[37] Van den Hoek LS, Bayoumi EK. Importance, destruction and recovery of coral reefs. IOSR J Pharm Biol Sci, 2017, 12(2): 59-63

[38] Zhao ZQ, Zheng P, Xu ST, Wu X. Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst, 2019, 30(11): 3212-3232,