空间控制技术与应用2023，Vol.49Issue(6)：17-27,11.DOI:10.3969/j.issn.1674-1579.2023.06.002
一种融合注意力机制的无人机目标分割算法
A Drone Object Segmentation Algorithm Integrating Attention Mechanism
摘要
Abstract
Low-altitude airspace drones are characterized by small size and flexible flight,which brings difficulties to visual detection of trespassing drones.The low-altitude drone object segmentation algorithm incorporating an at-tention mechanism named Rep-YOLACT(re-parameterization-you only look at coefficients network)is proposed,which is first used with RepVGG(re-parameterization visual geometry group)networks to improve ResNet(residual network)backbone in YOLACT and enhance the feature extraction capability of the network.Meanwhile,CBAM(convolutional block attention module)is added after the three feature layers output from the backbone feature ex-traction network,so as to further utilize the information of the feature layers efficiently.Experiments are conducted on FL-drones(flying drones dataset)and MUD(multiscale unmanned aerial vehicle dataset),respectively.The results show that the proposed Rep-YOLACT algorithm improves mask AP(average precision)and mask AR(aver-age recall)by 0.3％and 11.7％,respectively,compared with YOLACT algorithm on FL-drones.The proposed Rep-YOLACT algorithm improves 2.3％and 5％on mask AP and prediction frame AR compared to YOLACT algo-rithm,which can perform the drone segmentation task well and its segmentation accuracy is higher than other main-stream segmentation algorithms.关键词
无人机/目标分割/注意力机制/RepVGG网络/深度学习Key words
drone/object segmentation/attention mechanism/RepVGG network/deep learning分类
信息技术与安全科学引用本文复制引用
王传云,姜福宏,王田,高骞,王静静..一种融合注意力机制的无人机目标分割算法[J].空间控制技术与应用,2023,49(6):17-27,11.基金项目
国家自然科学基金资助项目(61703287和61972016)、辽宁省教育厅科学研究项目(LJKZ0218和LJKMZ20220556)、沈阳市中青年科技创新人才项目(RC210401)和沈阳航空航天大学引进人才科研启动基金项目(22YB03)Supported by National Natural Science Foundation of China(61703287 and 61972016),Scientific Research Program of Liaoning Provincial Education Department of China(LJKZ0218 and LJKMZ20220556),Young and Middle-Aged Science and Technolo-gy Innovation Talents Project of Shenyang of China(RC210401)and Doctoral Scientific Research Foundation of Shenyang Aerospace Uni-versity(22YB03) （61703287和61972016）
