A Pose Measurement Method of Non-cooperative Target Based on Monocular Vision

Long, Chenrong; Bai, Zhining; Zhi, Shuai; Qiu, Chengbo; Wang, Yamin; Hu, Qinglei

doi:10.1109/ccdc52312.2021.9601391

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing pose measurement methods focus on cooperative targets, which are equipped with specialized visual measurement equipment, which can effectively reduce the difficulty of pose measurement. However, most objects to be tested in space are non-cooperative targets, 5 such as Space debris, faulty satellites, space facilities of other countries and institutions, etc. These non-cooperative targets do not have specific target targets, making it difficult to find effective feature points for target recognition and measurement.…”

Section: Introductionmentioning

confidence: 99%

Pose measurement method of space target based on Zynq platform

Zhang,

Yang,

Wang

et al. 2023

AOPC 2023: Optic Fiber Gyro

View full text Add to dashboard Cite

With the continuous deepening of human exploration of space, space control technology is receiving increasing attention. In space in orbit missions, both autonomous approach and close range operations require measuring the relative pose between targets. At present, there have been a large number of research results and applications of visual pose measurement methods in engineering both domestically and internationally. However, research on visual pose measurement for non-cooperative targets is relatively weak. Not only is there a lack of systematic and complete target pose measurement methods, but the response speed and accuracy in engineering applications also need to be further improved.This article proposes a new spatial object pose measurement method based on the Zynq platform, which utilizes the control algorithm and operating system advantages of the processor, as well as the parallel computing and dynamic configuration advantages of FPGA. Through software and hardware collaborative design, highquality data and image acquisition and precise pose calculation are carried out for non-cooperative targets. The algorithm in this paper is optimized and improved in data format, time sequence control, distortion correction, corner detection, feature extraction, stereo matching, Iterative reconstruction, pose calculation, etc. Finally, the target pose measurement method with clear data flow, hardware and software combination, and industrial application is realized. The experimental results show that the proposed method has fast response and accurate calculation results in visual pose measurement of non-cooperative targets.

show abstract

Section: Introductionmentioning

confidence: 99%

Pose measurement method of space target based on Zynq platform

Zhang,

Yang,

Wang

et al. 2023

AOPC 2023: Optic Fiber Gyro

View full text Add to dashboard Cite

show abstract

“…(2) Define multiple target attitudes in advance as annotation information, and transform the attitude estimation problem into a classification problem. This method is often used for attitude detection of non-cooperative targets [16,17]. For example, Sharma et al [18], at Stanford University, proposed a non-cooperative target attitude estimation method, based on convolutional neural network.…”

Section: Introductionmentioning

confidence: 99%

Design and Implementation of 3-D Measurement Method for Container Handling Target

Huang

Zhang

et al. 2022

JMSE

View full text Add to dashboard Cite

In the process of automatic container terminal loading and unloading, the three-dimensional attitude of the container affects the security of loading and unloading operations, so the three-dimensional attitude positioning of the container is very important. In this paper, a visual non-contact measurement method is used to realize the real-time orientation of the three-dimensional attitude of the container. First, the container corner is coarsely positioned by a small-scale deep learning network. Secondly, the precise position of the container keyhole is obtained by the secondary positioning of the container corner through the traditional image processing algorithm, and the container posture is measured in three dimensions by combining the physical motion model of the container during loading and unloading. After testing, unlike previous measurement methods, the measurement accuracy of this method met the requirements of automatic loading and unloading of container terminals, and the measurement time met the requirements of real-time measurement.

show abstract