Hsu, H.-W.H.-W.HsuLee, Y.-C.Y.-C.LeeDing, J.-J.J.-J.DingChang, R.Y.R.Y.ChangJIAN-JIUN DING2020-06-042020-06-042019https://scholars.lib.ntu.edu.tw/handle/123456789/497043Marine mammal detection is helpful for ecological conservation. In this paper, we proposed a novel automatic method in real-time to detect and recognize the dolphin that is underwater and just reveals some characteristics of the body. The proposed method is based on the convolutional neural network with an extra masking layer to approximate various filter without knowing the normal neural network, which explore a discriminative criterion to enhance the image segmentation performance. We evaluate the proposed system on our on-site dolphin shooting datasets. The proposed approach can achieve higher detection and recognition rates than existing classification models and outperform faster R-CNN baselines in the object detection. © 2018 IEEE.Convolutional neural network; Faster region-CNN; Marine mammals; Occlusion; Pattern recognition[SDGs]SDG14Convolution; Dolphins (structures); Image enhancement; Image segmentation; Mammals; Neural networks; Pattern recognition; Signal detection; Classification models; Convolutional neural network; Detection algorithm; Ecological conservation; Faster region-CNN; Marine mammals; Occlusion; Segmentation performance; Object detectionconference paper10.1109/IS3C.2018.000252-s2.0-85063199734https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063199734&doi=10.1109%2fIS3C.2018.00025&partnerID=40&md5=3ce15bb10f281dc9755c5b0087b991f2