Noncooperative Target Detection of Spacecraft Objects Based on Artificial Bee Colony Algorithm

Abstract

Accurate and fast recognition of Non-Cooperative Target (NCT) is an essential technology for Tethered Space Robots (TSR) when implementing on-orbit service. NCT is the spacecraft objects which could not be identified and located through the communication channels in the outer space. One of the approaches to resolve this problem is the use of intelligent computer vision system to track the object and hence to carry out operation and support tasks. By treating multi-object detection as the multi-peak optimization problem, this paper proposed a multi-circle detection method for recognition of circular modules on NCT and a multi-template matching method for other modules. Incorporating the concept of species into the Artificial Bee Colony (ABC) algorithm, a multi-peak optimization algorithm named as Species based Artificial Bee Colony (SABC) was proposed and applied to the above multi-object detection problem. In order to test and verify SABC, benchmark tests consisted of five multi-peak functions were conducted to verify the effectiveness for higher accuracy and shorter execution time in finding multiple optima. Firstly, we applied SABC into circle detection and design complete detection flow. Circular modules of NCT were adopted to the experiments and it was verified that the proposed multi-circle detection method based on SABC can locate circles with higher success rate and better accuracy than other methods. Furthermore, we employed SABC to multi-template matching and conducted experiments using simulated cases of China space missions as well as the Chang'e Camera Point System (CPS) developed by the Hong Kong Polytechnic University with China National Space Agency. Practical applications of multi-objects detection for NCT with kinds of noises, weakened brightness and shoot in continuous flights were evaluated in the experiments, and the results demonstrated that our methods were robust under different kinds of circumstances and thus confirmed its feasibility and effectiveness.

An Overview of Evolutionary Algorithms toward Spacecraft Attitude Control

“…Similar to the ant colony optimization algorithm, the artificial bee colony algorithm is primarily designed for a combinatorics based problem where the potential solution can be discretized into an array of building blocks that can be rearranged and mutated to find an optimum solution. Additionally, the ABC algorithm has bee used for trajectory optimization [71], parameter optimization [72,73], and remote sensing applications [74,75].…”

SFSNet: An Inherent Feature Segmentation Method for Ground Testing of Spacecraft

“…Zhang et al [14] merged similar line segments that were detected by Hough transform, and obtained the true triangle bracket edge using distance and area constraints. Liu et al [15] obtained the multi-elliptical features of the nozzle of a spacecraft using an improved bee colony algorithm. Another feasible method utilizes the relatively invariant local feature clusters in an image as the target feature.…”