Single Vision System Research Articles

Vision System for the Mars Sample Return Capture Containment and Return System (CCRS)

The successful 2020 launch and 2021 landing of the National Aeronautics and Space Administration’s (NASA) Perseverance Mars rover initiated the first phase of the NASA and European Space Agency (ESA) Mars Sample Return (MSR) campaign. The goal of the MSR campaign is to collect scientifically interesting samples from the Martian surface and return them to Earth for further study in terrestrial laboratories. The MSR campaign consists of three major spacecraft components to accomplish this objective: the Perseverance Mars rover, the Sample Retrieval Lander (SRL) and the Earth Return Orbiter (ERO). Onboard the ERO spacecraft is the Capture, Containment and Return System (CCRS). CCRS will capture, process and return to Earth the samples that have been collected after they are launched into Mars orbit by the Mars Ascent Vehicle (MAV), which is delivered to Mars onboard the SRL. To facilitate the processing of the orbiting sample (OS) via the CCRS, we have designed and developed a vision system to determine the OS capture orientation. The vision system is composed of two cameras sensitive to the visible portion of the electromagnetic spectrum and two illumination modules constructed from broadband light emitting diodes (LED). Vision system laboratory tests and physics-based optical simulations predict CCRS ground processing will be able to correctly identify the OS post-capture orientation using only a single vision system image that is transmitted to Earth from Mars orbit.

A single-vision dual imaging optical system in flip chip alignment

In the case of flip-chip, the key to high-quality packaging is the high-precision alignment of the chip to the PCB. High-precision alignment is usually achieved using vision. Since the lens and camera are expensive and the camera coordinates system conversion is cumbersome, the single-vision system is proposed. However, there are defects in that the loss of light source is large, and the coaxial optical lens cannot be used. In this paper, a new single-vision dual-imaging optical system is proposed based on Zemax, which effectively solves the defects of the old single-vision system. The results show that the system can reduce the use of the lens and camera, reduce the use cost of the equipment, and easily convert the camera coordinate system to ensure the imaging quality.

Single vision system for simultaneous observation of keyhole and weld pool in plasma arc welding

A common CCD camera was equipped with a specially designed filter to constitute a vision system, which was used to capture the weld pool and the keyhole images during plasma arc welding process. Through image processing and calibration, the shapes and sizes of both the keyhole and the weld pool were measured under different welding conditions. The dynamic variations of the keyhole/weld pool sizes with time and their relations with the main process parameters were experimentally determined. Six stages of the keyhole/weld pool evolution were observed during the whole welding process. The observation results lay solid foundation for optimizing the welding process parameters and implementing process control of plasma arc welding.

Performance analysis of an INS/SLAM integrated system with respect to the geometrical arrangement of multiple vision sensors

A single vision system is the simplest vision-based method of simultaneous localization and mapping (SLAM) but it cannot reduce navigation errors that occur in the direction of the optical axis of vision sensors. Moreover, the limited observation area of vision sensors sometimes leads to failure in tracking a feature point. A vision sensor-based inertial navigation system INS/SLAM integrated system performs better with multiple vision sensors than with a single vision sensor because the observation area is wider and the impact of the sensitivity of the vision sensors is considerably smaller. However, the geometrical arrangement of multiple vision sensors induces navigation errors. This paper analyzes how the performance of the vision sensor-based INS/SLAM integrated system varies in relation to the geometrical arrangement of multiple vision sensors and the observation area of the vision sensors. The analysis shows that vertical navigation errors decline when the vision sensors are aimed horizontally, and that horizontal navigation errors decline in a similar manner when the vision sensor is aimed vertically; moreover, this behavior is especially evident when the level of sensitivity peaks in the horizontal direction.

Wii remote–based low-cost motion capture for automated assembly simulation

This paper describes the development of a Wii remote (Wiimote)---based low-cost motion capture system and demonstrates its application for automated assembly simulation. Multiple Wiimotes are used to form a vision system to perform motion capture in 3D space. A hybrid algorithm for calibrating a multi-camera stereo vision system has been developed based on Zhang's and Svoboda's calibration algorithms. This hybrid algorithm has been evaluated and shown accuracy improvement over Svoboda's algorithm for motion capture with multiple cameras. The captured motion data are used to automatically generate an assembly simulation of objects represented by CAD models in real time. The Wiimote-based motion capture system is practically attractive because it is inexpensive, wireless, and easily portable. Application examples have been developed for a single vision system with two Wiimotes to track the assembly of a microsatellite prototype frame and for an integrated vision system with four Wiimotes to track the assembly of a bookshelf.

Machine Lip-Reading of Japanese Vowels Utilizing A Stereoscopic Vision System.

The lip-shape recognition of Japanese vowels utilizing a stereoscopic vision system has been performed to enhance the discrimination of five vowels by machine lip-reading. The opening angle P4 between the upper lip and the lower lip is selected as the typical three-dimensional feature parameter of lip shape, in addition to the usual feature parameters such as the width P1 and the height P2 of the lip shape and distance P3 between the tips of the upper lip and the chin. Compared with the 3 two-dimensional parameters P1, P2 and P3 used in a single-vision system, the 3 and 4 three-dimensional parameters led to the significant increase of discrimination rate, and in particular, the discrimination rate by the 4 three-dimensional parameters was more than 90% for every tested subject. Recognition for an unspecified subject was also examined, based on the selections of the variance-covariance matrix and the mean vector of feature variables, by which the Mahalanobis' generalized square distance and the maximum likelihood discrimination function were determined.