An improved YOLOv3 algorithm to detect molting in swimming crabs against a complex background

Tang, Chao; Zhang, Gang; Hu, Haigang; Wei, Pengbo; Duan, Zheng; Qian, Yunxia

doi:10.1016/j.aquaeng.2020.102115

Cited by 28 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, as the main framework, combined with the adaptive dark-channel defogging algorithm, the YOLOv3 model can be effectively implemented to detect whether soft-shell crabs are moulting. 88 With its high detection rate, the YOLOv4 model can be used for real-time detection to meet the requirement of crayfish quality detection. 89 Furthermore, Liu et al 90 proposed an improved YOLOv3 network for aquatic animal recognition, which improved the recognition accuracy.…”

Section: Dos Santos Andmentioning

confidence: 99%

“…For example, breeding soft‐shell crabs still relies on artificial recognition, and artificial intervention may interfere with crab moulting to some extent with strong subjectivity. Therefore, as the main framework, combined with the adaptive dark‐channel defogging algorithm, the YOLOv3 model can be effectively implemented to detect whether soft‐shell crabs are moulting 88 . With its high detection rate, the YOLOv4 model can be used for real‐time detection to meet the requirement of crayfish quality detection 89 …”

Section: Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for visual recognition and detection of aquatic animals: A review

Deng

et al. 2022

Reviews in Aquaculture

View full text Add to dashboard Cite

The ocean is an important ecosystem, and aquatic animals play an important role in the biological world, especially in aquaculture. How to accurately and intelligently recognise and detect aquatic animals is one of the urgent problems in the field of underwater biological detection. The wide applications of artificial intelligence (AI), especially deep learning (DL), provide new opportunities and challenges for the efficient and intelligent exploration of aquatic animals. DL has been widely used in the visual recognition and detection of terrestrial animals, but it is in the early stages of use for aquatic animals due to the complexity of underwater environment and the difficulty of data acquisition. Here, this article reviews the current application status of DL for aquatic animals, potential challenges and future directions. The key advances of DL algorithms applied to the visual recognition and detection of aquatic animals are generalised, including datasets, algorithms and performance. The applications of DL are summarised in aquatic animals, including image detection, video detection, species classification, biomass estimation, behaviour analysis and food safety. Furthermore, the challenges are summed up and classified in the object recognition and detection domain for aquatic animals. Finally, further research direction is discussed and the conclusions are drawn. The key advances of DL in the recognition and detection of aquatic animals will help to further excavate and extend the application of DL in the field of marine biological exploration.

show abstract

Section: Dos Santos Andmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

Deep learning for visual recognition and detection of aquatic animals: A review

Deng

et al. 2022

Reviews in Aquaculture

View full text Add to dashboard Cite

show abstract

“…Anotasi merupakan proses sebelum melakukan latih data [26] yang bertujuan merepresentasikan Ground Truth [27] dan label kelas dari objek pada citra yang akan digunakan [28] seperti yang terlihat pada gambar 2 anotasi menggunakan LabelImg serta tabel 3 menjelaskan tentang kelas pada objek. YOLO format menjadi anotasi yang digunakan pada penelitian akan simpan ke dalam file berekstensi TXT yang berisikan informasi Id Kelas, x, y, width (w), height (h) [29].…”

Section: Annotasiunclassified

Deteksi dan Klasifikasi Penyakit Pada Daun Kopi Menggunakan Yolov7

Ardiansyah¹

2023

SISFOKOM

View full text Add to dashboard Cite

In improving the economy of developing countries, the highest export commodity is the coffee plant. Indonesia produces 639 thousand tons of coffee every year. Therefore, establishing Indonesia as 4th in the world. However, decreased productivity due to diseases of the coffee plant leaves can reduce the productivity of coffee production. Leaf diseases include Miner, Rust, Phoma, and Cercospora. Based on extant issues in agriculture, utilization such as artificial intelligence, Computer Vision, and Bigdata can decrease the costs incurred to trade with plant diseases. With significant advances in artificial intelligence in Machine Learning comes the Deep Learning method. YOLO is Deep Learning seeded as an object detection compared to other approaches. YOLOv7 is the latest version of the YOLO architecture that can detect speed, high Precision, easy-to-train data, and implementation. The main contribution of this research was to develop using model-based YOLOv7, use coffee leaf costume datasets, data augmentation, and preprocessing datasets. This research utilizes Google Colab and GPU Tesla T4 to get a result F1-score of 0.93, Precision of 0.926, Recall of 0.932, mAP@IoU .5 of 0.956, mAP@IoU .5:.95 of 0.927 for the entire trained data class. However, the best result is the binary class to get a result F1-score of 0.99, Precision of 0.991, Recall of 1, mAP@IoU .5 of 0.998, mAP@IoU .5:.95 of 0.994.

show abstract

“…In contrast, deep learning algorithms, despite having higher hardware requirements, automatically learn features from raw data, providing accurate detection in complex environments [ 10 , 11 ]. For instance, Tang et al [ 12 ] optimized YOLOv3 for the real-time detection of crab molting in pike farming systems, achieving a 91% prediction accuracy even in muddy water. Sun et al [ 13 ] improved the Faster RCNN algorithm for identifying flowers and fruits of unripe small tomatoes, reaching a model accuracy of 99.5%.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Sun-Dried Kelp Detection: Introducing K-YOLO, a Lightweight Model with Improved Precision and Recall

Xiao,

Zhu,

Hong

et al. 2024

Sensors

View full text Add to dashboard Cite

Kelp, often referred to as a “sea vegetable”, holds substantial economic significance. Currently, the drying process for kelp in China primarily relies on outdoor sun-drying methods. Detecting kelp in the field presents challenges arising from issues such as overlapping and obstruction. To address these challenges, this study introduces a lightweight model, K-YOLOv5, specifically designed for the precise detection of sun-dried kelp. YOLOv5-n serves as the base model, with several enhancements implemented in this study: the addition of a detection head incorporating an upsampling layer and a convolution module to improve the recognition of small objects; the integration of an enhanced I-CBAM attention mechanism, focusing on key features to enhance the detection accuracy; the replacement of the CBS module in the neck network with GSConv to reduce the computational burden and accelerate the inference speed; and the optimization of the IoU algorithm to improve the identification of overlapping kelp. Utilizing drone-captured images of sun-dried kelp, a dataset comprising 2190 images is curated. Validation on this self-constructed dataset indicates that the improved K-YOLOv5 model significantly enhances the detection accuracy, achieving 88% precision and 78.4% recall. These values represent 6.8% and 8.6% improvements over the original model, respectively, meeting the requirements for the real-time recognition of sun-dried kelp.

show abstract

An improved YOLOv3 algorithm to detect molting in swimming crabs against a complex background

Cited by 28 publications

References 4 publications

Deep learning for visual recognition and detection of aquatic animals: A review

Deep learning for visual recognition and detection of aquatic animals: A review

Deteksi dan Klasifikasi Penyakit Pada Daun Kopi Menggunakan Yolov7

Enhancing Sun-Dried Kelp Detection: Introducing K-YOLO, a Lightweight Model with Improved Precision and Recall

Contact Info

Product

Resources

About