Algorithm of detection rock object in landing zone of small celestial body surface

被引：0

作者：

Feng Z. ^{[1
,2
]}

Wang B. ^{[1
,2
,3
]}

Huang P. ^{[1
,2
]}

Xiong X. ^{[1
,2
,3
]}

Jin H. ^{[1
,2
,3
]}

机构：

[1] Institute of Information Engineering and Automation, Kunming University of Science and Technology, Kunming

[2] Faculty of Artificial Intelligence Industry, Kunming University of Science and Technology, Kunming

[3] Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science &Technology, Kunming

来源：

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2024年 / 45卷 / 04期

关键词：

deep learning; multi-head self-attention; multi-scale feature fusion; rocks detection on small body surface; small object detection;

D O I：

10.19650/j.cnki.cjsi.J2412406

中图分类号：

学科分类号：

摘要：

In response to the challenging issue of indistinct surface rock contours and difficulties in detecting small-sized rocks in dim environments on small celestial bodies, a method and model for rock target detection in landing areas on small celestial body surfaces is proposed. This approach integrates a multi-head self-attention mechanism into the YOLOv8x framework to enhance the model′s capability to capture the global view of images, thereby improving its adaptability to different lighting conditions in deep space environments. Additionally, a small object detection layer is added to the model to increase its focus on small-sized rocks, enhancing its adaptability to rocks of varying sizes. Comparative experimental results demonstrate that compared to the original algorithm, the proposed method achieves improvements of 6. 4% in rock detection precision, 3% in recall rate, and 5% in mean average precision. Furthermore, compared with other mainstream object detection algorithms, the proposed method shows significant improvements in performance metrics. This method provides a theoretical and technical foundation for the autonomous identification of rocks in landing areas on small celestial body surfaces in dim environments. © 2024 Science Press. All rights reserved.

引用

页码：194 / 205

页数：11

共 36 条

[1] LI X Y, LIN W, XIAO ZH Y, Et al., Planetary geology: “Extraterrestrial” model of geology [ J ], Bulletin of Chinese Academy of Sciences, 34, 7, pp. 776-784, (2019)
[2] GLASS B P., Introduction to Planetary Geology, (1982)
[3] MICHIKAMI T, HONDA C, MIYAMOTO H, Et al., Boulder size and shape distributions on asteroid Ryugu, Icarus, 331, pp. 179-191, (2019)
[4] FU S, LI CH L, ZHANG H Y, Et al., Geological body recognition based on multi-modal feature fusion, Earth Science, 48, 10, pp. 3743-3752, (2023)
[5] LI F S, LI X J, CHEN W T, Et al., Automatic lithology classification based on deep features using dual polarization sar images, Earth Science, 47, 11, pp. 4267-4279, (2022)
[6] MA Z D, MA L, LI K, Et al., Multi-scale lithology recognition based on deep learning of rock images, Bulletin of Geological Science and Technology, 41, 6, pp. 316-322, (2022)
[7] CASTANO R, ESTLIN T, ANDERSON R C, Et al., Oasis: Onboard autonomous science investigation system for opportunistic rover science [ J ], Journal of Field Robotics, 24, 5, pp. 379-397, (2007)
[8] CASTANO A, ANDERSON R C, CASTANO R, Et al., Intensity-based rock detection for acquiring onboard rover science, Lunar and Planetary Science Conference, (2004)
[9] BAJRACHARY A M., Single image based hazard detection for a planetary lander, Proceedings of the 5th Biannual World Automation Congress, pp. 585-590, (2002)
[10] ZHANG Z X, CUI P Y., An algorithm of rock detection and avoidance for planetary soft landing based on CCD landing camera, ACTA Aeronauticaet Astronautica Sinica, 30, 6, pp. 1510-1516, (2008)

← 1 2 3 4 →