Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ar tificial intelligence. According to news reporting originating from Guangxi, Peo ple’s Republic of China, by NewsRx correspondents, research stated, “The study c omes up with a new way to improve the accuracy of image matching in binocular vi sion systems, especially those that are mounted on vehicles. It combines machine learning with the ORB (Oriented FAST and Rotated BRIEF) image-matching algorith ms.” Our news journalists obtained a quote from the research from Guangxi University: “Standard ORB matching frequently encounters mismatches in complex and repetiti ve environments. To minimize false positives in matches, our strategy utilizes t he EfficientPS (Efficient Panoptic Segmentations) algorithm, a panoramic segment ation technique that uses machine learning in conjunction with ORB. The procedur e begins with the EfficientPS approach, which delivers fine-grained and efficien t segmentation of images, assigning semantic category labels and unique identifi ers to each pixel. The ORB feature point matching process is refined using seman tic data to filter out mismatches between foreground objects and the background effectively. This machine-learning-augmented method significantly decreases the frequency of erroneous matches in intricate settings. Empirical findings from th e KITTI dataset demonstrate that in non-targeted environments, the accuracy of o ur proposed method (0.978) is marginally less than that of LoFTR (0.983). Still, it surpasses other methods when utilizing 50 ORB parameters. In more intricate situations, such as multi-target scenarios with an increased number of ORB param eters (200), our method maintains a high level of accuracy (0.883), outperformin g the conventional ORB (0.732) and rivaling the performance of DL-BDLMR (0.790) and ORB-MFD-FPMC (0.835). Our method’s processing time is competitive and slight ly higher than the standard ORB, but it improves accuracy. In scenarios without targets and with single targets, our method’s processing time (0.195 seconds and 0.211 seconds, respectively) is greater than that of ORB and ORB-MFD-FPMC. Yet, it is significantly lower than that of LoFTR.”
NETL
NSTL