文献类型：期刊文献

英文题名：Simple weakly supervised deep learning pipeline for detecting individual red-attacked trees in VHR remote sensing images

作者：Qiao, Rui[1] Ghodsi, Ali[1] Wu, Honggan[2] Chang, Yuanfei[3] Wang, Chengbo[3]

第一作者：Qiao, Rui

通信作者：Wang, CB[1]

机构：[1]Univ Waterloo, Dept Stat & Actuarial Sci, Waterloo, ON, Canada;[2]Chinese Acad Forestry, Res Inst Forest Resource Informat Tech, Beijing, Peoples R China;[3]Chinese Acad Sci, Aerosp Informat Res Inst, 20 Datun Rd, Beijing 100101, Peoples R China

年份：2020

卷号：11

期号：7

起止页码：650-658

外文期刊名：REMOTE SENSING LETTERS

收录：;EI(收录号：20202308794770);Scopus(收录号：2-s2.0-85085860557);WOS:【SCI-EXPANDED(收录号:WOS:000537015500001)】；

基金：This work was supported by the Program of Institute of Forest Resource Information Techniques [CAFYBB2017ZC001].

语种：英文

外文关键词：Antennas - Convolutional neural networks - Cost effectiveness - Forestry - Large dataset - Object detection - Object recognition - Pipelines - Remote sensing - Statistical tests

摘要：After an attack the by pine wood nematode, pine tree needles turn red. Using convolutional neural networks (CNNs) based object detection methods, machines can detect red-attacked trees. However, most deep learning object detection algorithms (such as Faster R-CNN and YOLO among others) often require a large number of labelled training datasets, where in each image every object must be given a bounding box label. To increase the cost-effectiveness of this process, we propose a simple yet efficient weakly supervised processing pipeline, based on class activation maps to locate the target. Unlike object detection methods that require bounding-box-labelled data for training, the proposed pipeline only needs image-level-labelled data. Using the proposed pipeline, we could achieve an average precision (AP) of 91.82% on test dataset. Comparing with sliding window-based method which achieves an average precision (AP) of 89.95%, our method not only gets a better AP but also runs faster than sliding window-based pipeline. This result not only indicates that the pipeline is a highly effective one but also demonstrates that image-level-labelled aerial images can be used for the detection of red-attacked tree. The proposed method should also find use in other object detection applications in the field of remote sensing.