A Comparative Study of Visual Identification Methods for Highly Similar Engine Tubes in Aircraft Maintenance, Repair and Overhaul.

Unique identification of machine parts is critical to production and maintenance, repair and overhaul (MRO) processes in the aerospace industry. Despite recent advances in automating these identification processes, many are still performed manually. This is time-consuming, labour-intensive and prone to error, particularly when dealing with visually similar objects that lack distinctive features or markings or when dealing with parts that lack readable identifiers due to factors such as dirt, wear and discolouration. Automation of these processes has the potential to alleviate these problems. However, due to the high visual similarity of components in the aerospace industry, commonly used object identifiers are not directly transferable to this domain. This work focuses on the challenging component spectrum engine tubes and aims to understand which identification method using only object-inherent properties can be applied to such problems. Therefore, this work investigates and proposes a comprehensive set of methods using 2D image or 3D point cloud data, incorporating digital image processing and deep learning approaches. Each of these methods is implemented to address the identification problem. A comprehensive benchmark problem is presented, consisting of a set of visually similar demonstrator tubes, which lack distinctive visual features or markers and pose a challenge to the different methods. We evaluate the performance of each algorithm to determine its potential applicability to the target domain and problem statement. Our results indicate a clear superiority of 3D approaches over 2D image analysis approaches, with PointNet and point cloud alignment achieving the best results in the benchmark.

Alleviate Similar Object in Visual Tracking via Online Learning Interference-Target Spatial Structure.

Correlation Filter (CF) based trackers have demonstrated superior performance to many complex scenes in smart and autonomous systems, but similar object interference is still a challenge. When the target is occluded by a similar object, they not only have similar appearance feature but also are in same surrounding context. Existing CF tracking models only consider the target's appearance information and its surrounding context, and have insufficient discrimination to address the problem. We propose an approach that integrates interference-target spatial structure (ITSS) constraints into existing CF model to alleviate similar object interference. Our approach manages a dynamic graph of ITSS online, and jointly learns the target appearance model, similar object appearance model and the spatial structure between them to improve the discrimination between the target and a similar object. Experimental results on large benchmark datasets OTB-2013 and OTB-2015 show that the proposed approach achieves state-of-the-art performance.

Real-time automated detection of older adults' hand gestures in home and clinical settings.

There is an urgent need, accelerated by the COVID-19 pandemic, for methods that allow clinicians and neuroscientists to remotely evaluate hand movements. This would help detect and monitor degenerative brain disorders that are particularly prevalent in older adults. With the wide accessibility of computer cameras, a vision-based real-time hand gesture detection method would facilitate online assessments in home and clinical settings. However, motion blur is one of the most challenging problems in the fast-moving hands data collection. The objective of this study was to develop a computer vision-based method that accurately detects older adults' hand gestures using video data collected in real-life settings. We invited adults over 50 years old to complete validated hand movement tests (fast finger tapping and hand opening-closing) at home or in clinic. Data were collected without researcher supervision via a website programme using standard laptop and desktop cameras. We processed and labelled images, split the data into training, validation and testing, respectively, and then analysed how well different network structures detected hand gestures. We recruited 1,900 adults (age range 50-90 years) as part of the TAS Test project and developed UTAS7k-a new dataset of 7071 hand gesture images, split 4:1 into clear: motion-blurred images. Our new network, RGRNet, achieved 0.782 mean average precision (mAP) on clear images, outperforming the state-of-the-art network structure (YOLOV5-P6, mAP 0.776), and mAP 0.771 on blurred images. A new robust real-time automated network that detects static gestures from a single camera, RGRNet, and a new database comprising the largest range of individual hands, UTAS7k, both show strong potential for medical and research applications. Supplementary Information: The online version contains supplementary material available at 10.1007/s00521-022-08090-8.