https://scholars.lib.ntu.edu.tw/handle/123456789/580961
標題: | Backbone alignment and cascade tiny object detecting techniques for dolphin detection and classification | 作者: | LEE Y.-C HSU H.-W DING J.-J HOU W LIEN-SIANG CHOU CHANG R.Y. JIAN-JIUN DING |
關鍵字: | Classification (of information); Deep learning; Dolphins (structures); Learning systems; Network architecture; Visualization; Automatic monitoring; Automatic tracking; High-resolution photos; Lower resolution; Occlusion problems; Regions of interest; Small object detection; State-of-the-art methods; Object detection | 公開日期: | 2021 | 出版社: | Institute of Electronics, Information and Communication, Engineers, IEICE | 卷: | E104.A | 期: | 4 | 起(迄)頁: | 734-743 | 來源出版物: | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences | 摘要: | Automatic tracking and classification are essential for studying the behaviors of wild animals. Owing to dynamic far-shooting photos, the occlusion problem, protective coloration, the background noise is irregular interference for designing a computerized algorithm for reducing human labeling resources. Moreover, wild dolphin images are hardacquired by on-the-spot investigations, which takes a lot of waiting time and hardly sets the fixed camera to automatic monitoring dolphins on the ocean in several days. It is challenging tasks to detect well and classify a dolphin from polluted photos by a single famous deep learning method in a small dataset. Therefore, in this study, we propose a generic Cascade Small Object Detection (CSOD) algorithm for dolphin detection to handle small object problems and develop visualization to backbone based classification (V2BC) for removing noise, highlighting features of dolphin and classifying the name of dolphin. The architecture of CSOD consists of the P-net and the F-net. The P-net uses the crude Yolov3 detector to be a core network to predict all the regions of interest (ROIs) at lower resolution images. Then, the F-net, which is more robust, is applied to capture the ROIs from high-resolution photos to solve single detector problems. Moreover, a visualization to backbone based classification (V2BC) method focuses on extracting significant regions of occluded dolphin and design significant post-processing by referencing the backbone of dolphins to facilitate for classification. Compared to the state of the art methods, including fasterrcnn, yolov3 detection and Alexnet, the Vgg, and the Resnet classification. All experiments show that the proposed algorithm based on CSOD and V2BC has an excellent performance in dolphin detection and classification. Consequently, compared to the related works of classification, the accuracy of the proposed designation is over 14% higher. Moreover, our proposed CSOD detection system has 42% higher performance than that of the original Yolov3 architecture. ? 2021 The Institute of Electronics. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104932110&doi=10.1587%2fTRANSFUN.2020EAP1054&partnerID=40&md5=8cbd58f85ce8979f8b7b4883cac0ab82 https://scholars.lib.ntu.edu.tw/handle/123456789/580961 |
ISSN: | 09168508 | DOI: | 10.1587/TRANSFUN.2020EAP1054 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。