{"id":30806,"date":"2024-08-07T16:52:07","date_gmt":"2024-08-07T16:52:07","guid":{"rendered":"https:\/\/www.writemyessays.app\/blog\/questions\/detection-and-classification-of-gracillaria-and-linnaeus-underwater-plant-species-using-a-hybrid-object-detection-and-cnn-model\/"},"modified":"2024-08-07T16:52:07","modified_gmt":"2024-08-07T16:52:07","slug":"detection-and-classification-of-gracillaria-and-linnaeus-underwater-plant-species-using-a-hybrid-object-detection-and-cnn-model","status":"publish","type":"questions","link":"https:\/\/www.writemyessays.app\/blog\/questions\/detection-and-classification-of-gracillaria-and-linnaeus-underwater-plant-species-using-a-hybrid-object-detection-and-cnn-model\/","title":{"rendered":"Detection and Classification of Gracillaria and Linnaeus Underwater Plant Species Using a Hybrid Object Detection and CNN Model"},"content":{"rendered":"

In marine ecosystems, the presence
\nof specific underwater plant species such as Gracillaria and Linnaeus is vital
\nfor supporting marine biodiversity and sustaining fishing hotspots. Accurate
\ndetection and classification of these species are crucial for ecological
\nstudies and fisheries management. This research introduces a hybrid object
\ndetection model designed to identify and classify Gracillaria and Linnaeus
\nspecies in challenging underwater environments. Given the constraints of
\nlimited and low-quality data, the study utilized two blurry underwater videos,
\nfrom which 200 frames were extracted and processed.<\/span><\/p>\n

The preprocessing stage involved
\ntechniques such as Auto-Orient, Resize (stretching images to 640×640), and
\nmultiple augmentation methods including horizontal and vertical flipping, 90\u00b0
\nrotations, and brightness adjustments. These steps expanded the dataset to
\n1,043 images, which were then used to train a YOLOv8-based object detection
\nmodel. The model achieved a mean average precision (mAP) of 74% and a recall of
\n66%, indicating its potential in identifying these underwater species despite
\nthe data limitations.<\/span><\/p>\n

Following object detection, the
\nidentified segments were cropped and further classified using a Convolutional
\nNeural Network (CNN) model. The CNN was trained on a subset of 412 high-quality
\nimages, which were also subjected to augmentation, resulting in 1,043 images.
\nThe CNN model demonstrated a high accuracy of 98% in classifying the plant
\nspecies. When integrated into a pipeline, the combined YOLOv8 and CNN model
\nsystem achieved an overall classification accuracy of 87%. Despite these
\npromising results, the system did exhibit some misclassifications, with five
\ninstances of Linnaeus being detected as Gracillaria, underscoring the need for
\nfurther refinement.<\/span><\/p>\n

The research concludes by
\nacknowledging the limitations of the current model and dataset, highlighting
\nthe necessity for higher-quality, high-resolution underwater videos to enhance
\ndetection accuracy. Future work will focus on refining the CNN model, possibly
\nincorporating advanced architectures like DenseNet, and improving the overall
\npipeline efficiency to enhance classification performance. This study
\ncontributes to the growing field of marine ecology by providing a foundational
\napproach for the automated detection and classification of critical underwater
\nplant species, with potential applications in ecological monitoring and
\nfisheries management.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

In marine ecosystems, the presence of specific underwater plant species such as Gracillaria and Linnaeus is vital for supporting marine biodiversity and sustaining fishing hotspots. Accurate detection and classification of these species are crucial for ecological studies and fisheries management. This research introduces a hybrid object detection model designed to identify and classify Gracillaria and […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","meta":[],"disciplines":[63],"paper_types":[],"tagged":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions\/30806"}],"collection":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions"}],"about":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/types\/questions"}],"author":[{"embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/comments?post=30806"}],"version-history":[{"count":0,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/questions\/30806\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/media?parent=30806"}],"wp:term":[{"taxonomy":"disciplines","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/disciplines?post=30806"},{"taxonomy":"paper_types","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/paper_types?post=30806"},{"taxonomy":"tagged","embeddable":true,"href":"https:\/\/www.writemyessays.app\/blog\/wp-json\/wp\/v2\/tagged?post=30806"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}