仿鹰眼-中脑机制的无人机空中加油显著性检测
收稿日期: 2023-01-09
修回日期: 2023-02-06
录用日期: 2023-02-15
网络出版日期: 2023-03-03
基金资助
科技创新2030-“新一代人工智能”重大项目(2018AAA0102403);国家自然科学基金(U20B2071)
Biologically eagle-eye and midbrain mechanism-based saliency detection of UAV aerial refueling targets
Received date: 2023-01-09
Revised date: 2023-02-06
Accepted date: 2023-02-15
Online published: 2023-03-03
Supported by
Science and Technology Innovation 2030-Key Project of "New Generation Artificial Intelligence"(2018AAA0102403);National Natural Science Foundation of China(U20B2071)
空中加油是提高无人机（UAV）空中持续作战能力的重要技术，其中对加油锥套的检测和识别是实现空中加油的首要任务。针对空中加油快速、准确的目标检测难题，结合鹰眼敏锐的视觉机制，设计了一种仿鹰眼-中脑机制的显著性检测算法，采用仿鹰眼颜色拮抗和明暗适应机制模型从加油锥套视频序列中提取多通道图像特征，为适应锥套在图像中的面积，模拟仿鹰中脑网络门控机制对多通道特征显著图进行空间门控处理，模拟仿鹰中脑网络增益机制对显著图进行增强处理。通过公开数据集和空中加油试飞数据集分别进行了测试，仿真对比实验结果验证了所提出的显著性检测算法可在设定显著目标面积占比的条件下有效抑制背景影响，并能检测到空中加油的锥套目标。
武桐言 , 霍梦真 , 段海滨 , 邓亦敏 . 仿鹰眼-中脑机制的无人机空中加油显著性检测[J]. 航空学报, 2023 , 44(20) : 628492 -628492 . DOI: 10.7527/S1000-6893.2023.28492
Aerial refueling is an important technology to improve the air endurance of Unmanned Aerial Vehicles (UAVs), and detection and identification of the refueling cone sleeve are the primary tasks to achieve aerial refueling. In order to meet the needs of fast and accurate target detection for aerial refueling, based on the keen vision mechanism of the eagle eye, a saliency detection algorithm imitating the eagle eye vision is designed. According to the characteristics of aerial refueling targets and scenes, the eagle-eye color antagonism and light-dark adaptation mechanism model is used to extract multi-channel image features from the primary image. The channel feature saliency map is subjected to spatial gating processing. On this basis, in furtherance of the salient target, the saliency map is enhanced by using the eagle-eye vision midbrain network gain model to obtain the final saliency map. According to the characteristics of aerial refueling targets and scenes, the eagle-eye color antagonism and light-dark adaptation mechanism model extract multi-channel image features from the primary image. The channel feature saliency map is subjected to spatial gating processing. To further enhance the salient target, the saliency map is enhanced by using the eagle-eye vision mid-brain network gain model to obtain the final saliency map. The algorithm is tested through the public data set and the aerial refueling simulation data set, and is then compared with other algorithms. The experimental results show that the saliency detection algorithm proposed in this paper can suppress the background influence by setting the proportion of the salient target area, highlight the salient target, and extract the aerial refueling drogue or the salient target whose size is similar.
Key words： aerial refueling; eagle-eye vision; color opponency; midbrain network; saliency detection; UAV
| 1 | REN J R， QUAN Q， LIU C J， et al. Docking control for probe-drogue refueling： An additive-state-decomposition-based output feedback iterative learning control method［J］. Chinese Journal of Aeronautics， 2020， 33（3）： 1016-1025. |
| 2 | 张国斌， 张青斌， 丰志伟， 等. 软式空中加油对接约束力不确定性分析［J］. 航空学报， 2021， 42（9）： 224517. |
| ZHANG G B， ZHANG Q B， FENG Z W， et al. Uncertainty analysis on binding force of hose-drogue aerial refueling［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（9）： 224517 （in Chinese）. | |
| 3 | 吴慈航， 闫建国， 钱先云， 等. 受油机指定时间姿态稳定控制［J］. 航空学报， 2022， 43（2）： 324996. |
| WU C H， YAN J G， QIAN X Y， et al. Predefined-time attitude stabilization control of receiver aircraft［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（2）： 324996 （in Chinese）. | |
| 4 | 邹泉， 华艺欣， 邵翥， 等.自主空中加油能力需求及关键评价指标分析［J/OL］.系统仿真学报：1-11 ［2023-01-02］. DOI： 10.16182/j.issn1004731x.joss.22-0655 . |
| ZOU Q， HUA Y X， SHAO Z， et al. Analysis of capability requirements and key evaluation indicators for autonomous air refueling［J/OL］. Journal of System Simulation： 1-11［2023-01-02］. DOI：10.16182/j.issn1004731x.joss.22-0655 （in Chinese）. | |
| 5 | 唐崇武， 汪刚志， 张飞飞. 面向自主空中加油的锥套识别与测量算法研究［J］. 电子测量技术， 2022， 45（1）： 111-116. |
| TANG C W， WANG G Z， ZHANG F F. Drogue detection and position measurement algorithm research for autonomous aerial refueling［J］. Electronic Measurement Technology， 2022， 45（1）： 111-116 （in Chinese）. | |
| 6 | GARCIA J A B， YOUNES A B. Real-time navigation for drogue-type autonomous aerial refueling using vision-based deep learning detection［J］. IEEE Transactions on Aerospace and Electronic Systems， 2021， 57（4）： 2225-2246. |
| 7 | LEE A， DALLMANN W， NYKL S， et al. Long-range pose estimation for aerial refueling approaches using deep neural networks［J］. Journal of Aerospace Information Systems， 2020， 17（11）： 634-646. |
| 8 | CHOI A J， YANG H H， HAN J H. Study on robust aerial docking mechanism with deep learning based drogue detection and docking［J］. Mechanical Systems and Signal Processing， 2021， 154： 107579. |
| 9 | 王宏伦， 阮文阳， 王延祥， 等. 基于可变视场角的空中加油锥套位姿精确测量方法［J］. 战术导弹技术， 2020（4）： 135-143. |
| WANG H L， RUAN W Y， WANG Y X， et al. Accurate measurement of refueling drogue pose based on variable field angle［J］. Tactical Missile Technology， 2020（4）： 135-143 （in Chinese）. | |
| 10 | XU X B， DUAN H B， GUO Y J， et al. A cascade adaboost and CNN algorithm for drogue detection in UAV autonomous aerial refueling［J］. Neurocomputing， 2020， 408： 121-134. |
| 11 | BORJI A， CHENG M M， HOU Q B， et al. Salient object detection： A survey［J］. Computational Visual Media， 2019， 5（2）： 117-150. |
| 12 | 段海滨， 张奇夫， 范彦铭， 等. 基于计算机视觉的UAV自主空中加油半物理仿真［J］. 北京航空航天大学学报， 2013， 39（11）： 1491-1496. |
| DUAN H B， ZHANG Q F， FAN Y M， et al. Hardware-in-loop simulation platform for UAV autonomous aerial refueling based on computer vision［J］. Journal of Beijing University of Aeronautics and Astronautics， 2013， 39（11）： 1491-1496 （in Chinese）. | |
| 13 | 段海滨， 张奇夫， 邓亦敏， 等. 基于仿鹰眼视觉的无人机自主空中加油［J］. 仪器仪表学报， 2014， 35（7）： 1450-1458. |
| DUAN H B， ZHANG Q F， DENG Y M， et al. Biologically eagle-eye-based autonomous aerial refueling for unmanned aerial vehicles［J］. Chinese Journal of Scientific Instrument， 2014， 35（7）： 1450-1458 （in Chinese）. | |
| 14 | ZHU W J， LIANG S， WEI Y C， et al. Saliency optimization from robust background detection［C］∥ 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2014： 2814-2821. |
| 15 | 孙永斌. 基于仿生智能的无人机软式自主空中加油技术研究［D］. 北京： 北京航空航天大学， 2021： 5-21. |
| SUN Y B. UAV probe-and-drogue autonomous aerial refueling techniques based on bionic intelligence ［D］. Beijing： Beihang University， 2021： 5-21 （in Chinese）. | |
| 16 | 段海滨， 邓亦敏， 王晓华. 仿鹰眼视觉及应用［M］ . 北京： 科学出版社， 2021： 1-17. |
| DUAN H B， DENG Y M， WANG X H. Biological eagle-eye vision and its applications ［M］. Beijing： Science Press， 2021： 1-17 （in Chinese）. | |
| 17 | GUZMAN-PANDO A， CHACON-MURGUIA M I. DeepFoveaNet： Deep fovea eagle-eye bioinspired model to detect moving objects［J］. IEEE Transactions on Image Processing， 2021， 30： 7090-7100. |
| 18 | LI X， DUAN H B， LI J C， et al. Biological eagle eye-based method for change detection in water scenes［J］. Pattern Recognition， 2022， 122： 108203. |
| 19 | GOLDSMITH T H. Optimization， constraint， and history in the evolution of eyes［J］. The Quarterly Review of Biology， 1990， 65（3）： 281-322. |
| 20 | KEMP D J， HERBERSTEIN M E， FLEISHMAN L J， et al. An integrative framework for the appraisal of coloration in nature［J］. The American Naturalist， 2015， 185（6）： 705-724. |
| 21 | OLSSON P. Colour vision in birds： Comparing behavioral thresholds and model predictions［D］. Lund： Lund University， 2016. |
| 22 | MITKUS M， POTIER S， MARTIN G R， et al. Raptor vision［M］∥The Oxford Research Encyclopedia of Neuroscience， 2018. |
| 23 | BADEN T， EULER T， BERENS P. Understanding the retinal basis of vision across species［J］. Nature Reviews Neuroscience， 2020， 21（1）： 5-20. |
| 24 | YUAN B H， HAN L X， YAN H. Explore double-opponency and skin color for saliency detection［J］. Neurocomputing， 2021， 425： 219-230. |
| 25 | BECKWITH-COHEN B， HOROWITZ I， BDOLAH-ABRAM T， et al. Differences in ocular parameters between diurnal and nocturnal raptors［J］. Veterinary Ophthalmology， 2015， 18： 98-105. |
| 26 | POTIER S， MITKUS M， KELBER A. Visual adaptations of diurnal and nocturnal raptors［J］. Seminars in Cell & Developmental Biology， 2020， 106： 116-126. |
| 27 | MYSORE S P， KNUDSEN E I. Descending control of neural bias and selectivity in a spatial attention network： Rules and mechanisms［J］. Neuron， 2014， 84（1）： 214-226. |
| 28 | KNUDSEN E I. Control from below： The role of a midbrain network in spatial attention［J］. European Journal of Neuroscience， 2011， 33（11）： 1961-1972. |
| 29 | GODDARD C A， SRIDHARAN D， HUGUENARD J R， et al. Gamma oscillations are generated locally in an attention-related midbrain network［J］. Neuron， 2012， 73（3）： 567-580. |
| 30 | GODDARD C A， HUGUENARD J， KNUDSEN E. Parallel midbrain microcircuits perform independent temporal transformations［J］. The Journal of Neuroscience： the Official Journal of the Society for Neuroscience， 2014， 34（24）： 8130-8138. |
| 31 | ASADOLLAHI A， KNUDSEN E I. Spatially precise visual gain control mediated by a cholinergic circuit in the midbrain attention network［J］. Nature Communications， 2016， 7： 13472. |
| 32 | KNUDSEN E I， SCHWARZ J S， KNUDSEN P F， et al. Space-specific deficits in visual orientation discrimination caused by lesions in the midbrain stimulus selection network［J］. Current Biology， 2017， 27（14）： 2053-2064.e5. |
| 33 | GOFERMAN S， ZELNIK-MANOR L， TAL A. Context-aware saliency detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2012， 34（10）： 1915-1926. |
| 34 | ZHANG J M， SCLAROFF S. Exploiting surroundedness for saliency detection： A Boolean map approach［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 38（5）： 889-902. |
| 35 | 王晓华. 基于仿鹰眼-脑机制的小目标识别技术研究［D］. 北京： 北京航空航天大学， 2018： 11-23. |
| WANG X H. Research on small target recognition based on eagle eye-brain mechanisms［D］. Beijing： Beihang University， 2018： 11-23 （in Chinese）. | |
| 36 | WANG L J， LU H C， WANG Y F， et al. Learning to detect salient objects with image-level supervision［C］∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 3796-3805. |
| 37 | RONNEBERGER O， FISCHER P， BROX T. U-net： convolutional networks for biomedical image segmentation［C］∥International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham： Springer， 2015： 234-241. |
| 38 | HOU X D， ZHANG L Q. Saliency detection： a spectral residual approach［C］∥2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2007： 1-8. |
| 39 | ZHANG L H， YANG C， LU H C， et al. Ranking saliency［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（9）： 1892-1904. |
/
| 〈 |
|
〉 |
CJA